video – Robohub

Underwater Human-Robot Interaction #ICRA2022

Abate De Mey — Fri, 22 Jul 2022 16:54:09 +0000

How do people communicate when they are underwater? With body language, of course.

Marine environments present a unique set of challenges that render several technologies that were developed for land applications completely useless. Communicating using sound, or at least as people use sound to communicate, is one of them.

Michael Fulton tackles this challenge with his presentation at ICRA 2022 by using body language to communicate with an AUV underwater. Tune in for more.

His poster can be viewed here.

Michael Fulton

Michael Fulton is a Ph.D. Candidate at the University of Minnesota Twin Cities. His research focuses primarily on underwater robotics with a focus on applications where robots work with humans. Specifically, human-robot interaction and robot perception using computer vision and deep learning, with the intent of creating systems that can work collaboratively with humans in challenging environments.

ep.354: Autonomous Flight Demo with CMU AirLab #ICRA2022, with Sebastian Scherer

Abate De Mey — Tue, 24 May 2022 05:11:57 +0000

Sebastian Scherer from CMU’s Airlab gives us a behind-the-scenes demo at ICRA of their Autonomous Flight Control AI. Their approach aims to cooperate with human pilots and act the way they would.

The team took this approach to create a more natural, less intrusive process for co-habiting human and AI pilots at a single airport. They describe it as a Turing Test, where ideally the human pilot will be unable to distinguish an AI from a person operating the plane.

Their communication system works parallel with a 6-camera hardware package based on the Nvidia AGX Dev Kit. This kit measures the angular speed of objects flying across the videos.

In this world, high angular velocity means low risk — since the object is flying at a fast speed perpendicular to the camera plane.

Low angular velocity indicates high risk since the object could be flying directly at the plane, headed for a collision.

Robots that feel by seeing

Carlo Sferrazza — Sat, 06 Mar 2021 09:30:07 +0000

Humanoid robot hand. Futuristic cyborg concept.

While modern cameras provide machines with a very well-developed sense of vision, robots still lack such a comprehensive solution for their sense of touch. At ETH Zurich, in the group led by Prof. Raffaello D’Andrea at the Institute for Dynamic Systems and Control, we have developed a tactile sensing principle that allows robots to retrieve rich contact feedback from their interactions with the environment. I recently described our approach in a TEDx talk at the last TEDxZurich. The talk features a tech demo that introduces the novel tactile sensing technology targeting the next generation of soft robotic skins.

Design

The sensing technique is based on a camera that tracks fluorescent particles, which are densely and randomly distributed within a soft, deformable gel. The randomness of the patterns simplifies production of the gel and their density provides strain information at each pixel of the resulting image. In addition, the technique does not make any assumption about the shape of the sensing surface, which can exhibit an arbitrary geometry.

Data Processing

While the images capturing the particles’ motion are intuitive and to some extent visually interpretable, the extraction of accurate physical quantities is challenging. In order to overcome the complexity of modeling the behavior of soft materials in real-time, the information extracted from the images is mapped to the distribution of the applied (shear and pressure) contact forces in a data-driven fashion. Specifically, a neural network is employed, which is trained entirely via accurate finite-element simulations to extract the aforementioned mapping.

Applications

This technology has the potential to impact several application fields, the obvious one being robotic manipulation. In a recent proof-of-concept, we have demonstrated how highly dynamic manipulation tasks can be achieved via the sole use of tactile sensing, as shown in the video below.

In addition, the versatility of this approach makes it suitable for various products beyond the robotics domain. In fact, an artificial sense of touch may find applications in smart prosthetic systems, with the potential to restore tactile sensations to people who have lost limbs.

ROBOTT-NET pilot project: Urban pest control

Thilo Zimmermann — Sun, 20 Oct 2019 23:07:20 +0000

“Within the framework of the European project ROBOTT-NET we are developing software and robotic solutions for the prevention and control of rodents in enclosed spaces”, says Marco Lorenzo, Service Supervisor at Irabia Control De Plagas.

You can learn more about the urban pest control project here:

This type of prevention is designed to help technicians and companies have better efficiency and control and a faster response, when it comes to controlling rodent pests.

“The project uses a mobile autonomous robotic platform with a robot arm to introduce a camera into the trap. It captures an image that is uploaded to the cloud”.

“The project is in collaboration with Robotnik, which is responsible for the assembly of the robot; and Hispavista, which is in charge of the cloud part”, Marco Lorenzo adds.

Aritz Zabaleta, a Systems Technician at Hispavista Labs explains that the application consists of two components:

“The first manages the entire fleet of robots that communicate with the server in the cloud and it processes the information collected by them. The second component is the one that allows customers to access processed images”.

If you want to watch more fascinating robotics videos, you can explore ROBOTT-NET’s pilot projects on our YouTube-channel.

SMART trials self-driving wheelchair at hospital

MIT News — Wed, 26 Jul 2017 19:00:53 +0000

Image: MIT CSAIL

Singapore and MIT have been at the forefront of autonomous vehicle development. First, there were self-driving golf buggies. Then, an autonomous electric car. Now, leveraging similar technology, MIT and Singaporean researchers have developed and deployed a self-driving wheelchair at a hospital.

Spearheaded by Daniela Rus, the Andrew (1956) and Erna Viterbi Professor of Electrical Engineering and Computer Science and director of MIT’s Computer Science and Artificial Intelligence Laboratory, this autonomous wheelchair is an extension of the self-driving scooter that launched at MIT last year — and it is a testament to the success of the Singapore-MIT Alliance for Research and Technology, or SMART, a collaboration between researchers at MIT and in Singapore.

Rus, who is also the principal investigator of the SMART Future Urban Mobility research group, says this newest innovation can help nurses focus more on patient care as they can get relief from logistics work which includes searching for wheelchairs and wheeling patients in the complex hospital network.

“When we visited several retirement communities, we realized that the quality of life is dependent on mobility. We want to make it really easy for people to move around,” Rus says.

The Robot Academy: Lessons in inverse kinematics and robot motion

Peter Corke — Fri, 30 Jun 2017 10:00:34 +0000

The Robot Academy is a new learning resource from Professor Peter Corke and the Queensland University of Technology (QUT), the team behind the award-winning Introduction to Robotics and Robotic Vision courses. There are over 200 lessons available, all for free.

The lessons were created in 2015 for the Introduction to Robotics and Robotic Vision courses. We describe our approach to creating the original courses in the article, An Innovative Educational Change: Massive Open Online Courses in Robotics and Robotic Vision. The courses were designed for university undergraduate students but many lessons are suitable for anybody, as you can easily see the difficulty rating for each lesson. Below are lessons from inverse kinematics and robot motion.

You can watch the entire masterclass on the Robot Academy website.

Introduction

In this video lecture, we will learn about inverse kinematics, that is, how to compute the robot’s joint angles given the desired pose of their end-effector and knowledge about the dimensions of its links. We will also learn about how to generate paths that lead to a smooth coordinated motion of the end-effector.

Inverse kinematics for a 2-joint robot arm using geometry

In this lesson, we revisit the simple 2-link planar robot and determine the inverse kinematic function using simple geometry and trigonometry.

Inverse kinematics for a 2-joint robot arm using algebra

You can watch the entire masterclass on the Robot Academy website.

If you liked this article, you may also enjoy:

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

From drinking straws to robots

Harvard Gazette — Fri, 16 Jun 2017 14:00:41 +0000

Image: Harvard Gazette

By Peter Reuell, Harvard Staff Writer

At the beginning of the decade, George Whitesides helped rewrite the rules of what a machine could be with the development of biologically inspired “soft robots.” Now he’s poised to rewrite them again, with help from some plastic drinking straws.

Inspired by arthropod insects and spiders, Whitesides and Alex Nemiroski, a former postdoctoral fellow in Whitesides’ Harvard lab, have created a type of semi-soft robot capable of standing and walking. The team also created a robotic water strider capable of pushing itself along the liquid surface. The robots are described in a recently published paper in the journal Soft Robotics.

Unlike earlier generations of soft robots, which could stand and awkwardly walk by inflating air chambers in their bodies, the new robots are designed to be far nimbler. Though real-world applications are still far off, the researchers hope the robots eventually could be used in search operations following natural disasters or in conflict zones.

“If you look around the world, there are a lot of things, like spiders and insects, that are very agile,” said Whitesides, the Woodford L. and Ann A. Flowers University Professor at Harvard. “They can move rapidly, climb on various items, and are able to do things that large, hard robots can’t do because of their weight and form factor. They are among the most versatile organisms on the planet. The question was, how can we build something like that?”

The answer, Nemiroski said, came in the form of your average drinking straw.

“This all started with an observation that George made, that polypropylene tubes have an excellent strength-to-weight ratio. That opened the door to creating something that has more structural support than purely soft robots have,” he said. “That was the building block, and then we took inspiration from arthropods to figure out how to make a joint and how to use the tubes as an exoskeleton. From there it was a question of how far can your imagination go? Once you have a Lego brick, what kind of castle can you build with it?”

What they built, he said, is a surprisingly simple joint.

Whitesides and Nemiroski began by cutting a notch in the straws, allowing them to bend. The scientists then inserted short lengths of tubing which, when inflated, would force the joints to extend. A rubber tendon attached on either side would then cause the joint to retract when the tubing deflated.

Armed with that simple concept, the team built a one-legged robot capable of crawling, and moved up in complexity as they added a second and then a third leg, allowing the robot to stand on its own.

“With every new level of systems complexity, we would have to go back to the original joint and make modifications to make it capable of exerting more force or to be able to support the weight of larger robots,” Nemiroski said. “Eventually, when we graduated to six- or eight-legged arthrobots, making them walk became a challenge from a programming perspective. For example, we looked at the way ants and spiders sequence the motion of their limbs and then tried to figure out whether aspects of these motions were applicable to what we were doing or whether we’d need to develop our own type of walking tailored to these specific types of joints.”

While Nemiroski and colleagues were able to control simple robots by hand, using syringes, they turned to computers to control the sequencing of their limbs as the designs increased in complexity.

“We put together a microcontroller run by Arduino that uses valves and a central compressor,” he said. “That allowed us the freedom to evolve their gait rapidly.”

Though Nemiroski and colleagues were able to replicate ants’ distinctive “triangle” gait using their six-legged robot, duplicating a spider-like gait proved far trickier.

“A spider has the ability to modulate the speed at which it extends and contracts its joints to carefully time which limbs are moving forward or backward at any moment,” Nemiroski said. “But in our case, the joints’ motion is binary due to the simplicity of our valving system. Either you switch the valve to the pressure source to inflate the balloon in the joint, and thus extend the limb, or you switch the valve to atmosphere to deflate the joint and thus retract the limb. So in the case of the eight-legged robot, we had to develop our own gait compatible with the binary motion of our joints. I’m sure it’s not a brand-new gait, but we could not duplicate precisely how a spider moves for this robot.”

Developing a system that can fine-tune the speed of actuation of the legs, Nemiroski said, would be a useful goal for future research, and would require programmable control over the flow rate supplied to each joint.

“We hit that limitation in the system, which I’m actually pretty proud of, because it means we pushed it to its absolute limit,” he said. “We took the basic concept and asked how far can we go before we would have to make radical alterations to how these limbs work, and we found that limit at the eight-legged robot. We were able to make it walk, but if you wanted to make it walk faster, or to add more limbs — for example, to support a load — you would have to start rethinking the system from the ground up.”

Though it may be years before the robots find their way into real-world applications, Whitesides believes the techniques used in their development — particularly the use of everyday, off-the-shelf materials — can point the way toward future innovations.

“I don’t see any reason to reinvent wheels,” he said. “If you look at drinking straws, they can make them at, effectively, zero cost and with great strength, so why not use them? These are academic prototypes, so they’re very light weight, but it would be fairly easy to imagine building these with a lightweight structural polymer that could hold a substantial weight.”

“What’s really attractive here is the simplicity,” added Nemiroski. “This is something George has been championing for some time, and something I grew to appreciate deeply while I was in his lab. For all the complexity of movement and structural integrity we get out of these robots, they’re remarkably simple in terms of construction and control. Using a single, easy-to-find material and a single concept for an actuator, we could achieve complex, multidimensional motion.”

This post was originally published on The Harvard Gazette. Click here to view the original.

This research was supported with funding from the U.S. Department of Energy, DARPA, the Natural Sciences and Engineering Research Council of Canada, the National Science Foundation, the Swedish Research Council, and the Wyss Institute for Biologically Inspired Engineering at Harvard University.

The Robot Academy: Lessons in image formation and 3D vision

Peter Corke — Tue, 13 Jun 2017 12:00:43 +0000

A 3D model of organic molecules created using Rhinoceros 3D and rendered with Vray. Source: Wikipedia Commons

The geometry of image formation

The real world has three dimensions but an image has only two. We can use linear algebra and homogeneous coordinates to understand what’s going on. This more general approach allows us to model the positions of pixels in the sensor array and to derive relationships between points on the image and points on an arbitrary plane in the scene.

Watch the rest of the Masterclass here.

How images are formed

How is an image formed? The real world has three dimensions but an image has only two: how does this happen and what are the consequences? We can use simple geometry to understand what’s going on.

Watch the rest of the Masterclass here.

3D vision

An image is a two-dimensional projection of a three-dimensional world. The big problem with this projection is that big distant objects appear the same size as small close objects. For people, and robots, it’s important to distinguish these different situations. Let’s look at how humans and robots can determine the scale of objects and estimate the 3D structure of the world based on 2D images.

Watch the rest of the Masterclass here.

If you liked this article, you may also enjoy:

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

The Robot Academy: An open online robotics education resource

Peter Corke — Fri, 26 May 2017 11:11:39 +0000

Educators are encouraged to use the Academy content to support teaching and learning in class or set them as flipped learning tasks. You can easily create viewing lists with links to lessons or masterclasses. Under Resources, you can download a Robotics Toolbox and Machine Vision Toolbox, which are useful for simulating classical arm-type robotics, such as kinematics, dynamics, and trajectory generation.

Under Masterclasses, students can choose a subject and watch a set of videos related to that particular topic. Single lessons can offer a short training segment or a refresher. Three online courses, Introducing Robotics, are also offered.

Below are two examples of a lesson and masterclass. We encourage everyone to take a look at the QUT Robot Academy by visiting our website.

Single Lesson

Out and about with robots

In this video, we look at a diverse range of real-world robots and discuss what they do and how they do it.

Masterclass

Robot joint control: Introduction (Video 1 of 12)

In this video, students learn how we make robot joints move to the angles or positions that are required to achieve the desired end-effector motion. This is the job of the robot’s joint controller. In the lecture, we will take discuss the realms of control theory.

Robot joint control: Architecture (video 2 of 12)

In this lecture, we discuss a robot joint is a mechatronic system comprising motors, sensors, electronics and embedded computing that implements a feedback control system.

Robot joint control: Actuators (video 3 of 12)

Actuators are the components that actually move the robot’s joint. So, let’s look at a few different actuation technologies that are used in robots.

To watch the rest of the video series, visit their website.

If you enjoyed this article, you may also want to read:

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

Programming your NAO robot for human interaction

Philip English — Tue, 09 May 2017 08:15:19 +0000

Today we are looking at how to program your NAO Robot for Human Interaction. Watch the video and follow the steps below to get interactive with your robot pal!

Create an animation of movements
- Right click, select “Create a new box”
- Select “Timeline”

We want the robot to do 3 things, a five high, a hello, and a goodbye move:

On the Timeline Edit Box
- Name: High Five
- Image: Click “Edit”
  - On the Edit box image
  - Click “Browse” and select a file
- Click “OK”

Now, as you can remember, if we take it to the box, we can get access to the NAO’s Timeline. Mine now is connected to the PC. So what I’m going to do is I’m going to set some points of the NAO to do some movements. As I have said before on one of my tutorial I’m going to make it set all the joints to the whole body.

We want to make him look like he is doing a high five:

Right click the arm
- Click “Stiffen chain on/off”
- Raise his arm up
Set joints and keyframe
- Select “Arms”
Click “Play” on the Motion Controller

That’s a quite quick high five actually. What we want to do is to actually give him a pause when he got his arm in the air. So, the way we do that is to copy and paste the keyframe.

Grab a few already built in animation, just to show you how much it works:

Go to Motions>Animations
- Drag a “Hello” box to the workspace
- Drag a “Wipe Forehead” box for a goodbye move to the workspace

We want to hear him speak, so:

Go to Voice
- Drag a “Speech Recognition” box to the workspace
Drag a “Switch Case”
- Connect the “Speech Recognition” box to the “Switch Case” box
- On the first case, write “Hello” and connect to the “Hello” box
- On the second case, write “High Five” and connect it to the “High Five” box
- On the third case, write “Goodbye” and connect it to the “Wipe Forehand” box
Set parameters of Speech Recognition
- Word list: Hi; High Five; Goodbye;
- Play with the threshold to see what works better
- Click “OK”

So there we have a speech recognition, he will listen to what I am saying and then we will act a motion. Now, what we need to do is to make sure that the robot doesn’t repeat it, so you know, it doesn’t loop back. Before we do that, we are going to:

Drag 3 “Say” box to the workspace so he can speak back to us
- On the “Switch case”, connect the “Hello” case on the “Say” box
  - Localized Text
    - Change the language to English(United States)
    - Write “Hi” on the textbox
- Connect the “High Five” case on the “Say (1)” box
  - Localized Text
    - Change the language to English(United States)
    - Write “High Five” on the textbox
- Connect the “Goodbye” case on the “Say(2)” box
  - Localized Text
    - Change the language to English(United States)
    - Write “Goodbye” on the textbox

So, here’s what we are saying, he recognizes it, says a word and does an animation, now what we want to do is we don’t want him to loop, as in he keeps hearing the same sound and maybe he starts to hear himself and repeat himself, so to stop that we need to connect the end of the motion boxes back to the “Speech Recognition” box. A simple output to the input speech.

I am going to make a little change actually, instead of “Hello”, we should put “Hi” here and I’m going to put “Hi” in there which is already done because they have to match otherwise if it doesn’t match he won’t recognize it. So if he hit “Load”

Philip: High Five!

Nao: High Five!

Philip: Goodbye!

Nao: Goodbye!

Philip: Hi!

Nao: Hello!

Brilliant! So that looks likes he’s working very well, so again if we says “Hi”, “High Five” or “Good bye” then he will greet you. If you walk in to room and you say “Hi” to a robot, obviously, he will do his animation and say a speech. Here you can use your imagination and try different things, different animations.

If you liked this article, you may also enjoy these from Robo-Phil:

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

TrotBot take two: Galloping like a horse

Ben Vagle — Thu, 04 May 2017 08:30:33 +0000

Hi, I’m Ben. I was a member of the team that developed a new walking mechanism, TrotBot, that we eventually scaled up to the size of a mini-van (you can read my original post here). Now, at DIYwalkers, I’ve posted plans for TrotBot Ver. 2, designed to handle the weight of the EV3 brick. As you can see in the following videos, we were able to improve TrotBot by borrowing some ideas from a galloping horse.

Just like lunges are more tiring by simply walking, robots with bumpy gaits require more power to walk. This may not be a problem at small scales, but as a robot’s weight increases, smoother gaits are required. TrotBot Ver. 1 has somewhat of a bumpy gait, but as you can see in my video below, TrotBot’s weight at LEGO-scale is low enough that it walks well:

However, when I added LEGO’s relatively heavy EV3 brick to TrotBot it didn’t perform so well. To reduce its power requirements, I needed to smooth TrotBot’s gait, which I did by adding active feet that mimic the leg action of a galloping horse.

Background on TrotBot and its Feet

Our goal for TrotBot was to create a walking mechanism capable of walking on rough terrain and areas generally inaccessible to wheeled vehicles, so we designed its linkage to step high. We initially prototyped TrotBot in LEGO with 8 legs. It walked well enough that we—somewhat naively—thought we could scale it up to mini-van size with only 8 legs. A team of us spent most of that summer’s boiling hot weekends building our large TrotBot in my garage, only to find, during our first walking test, that too much torque was required to drive the robot up from the gait’s low point. As we discovered, large walkers should always have at least one foot in contact with the ground at each corner, like how a car’s four wheels are always in contact with the ground. Below, I simulated one corner of a 12 leg version of TrotBot, and as you can see we should have scaled up TrotBot with 12 legs like Theo Jansen’s famous Strandbeest has:

It would have required too many new parts to switch to a 12 leg version of TrotBot, and we didn’t want to start over from scratch, so instead we explored ideas for active feet that could smooth TrotBot’s 8 legged gait.

Using a galloping horse’s gait as inspiration we sought to add some sort of second foot to each leg that would mimic how a horse’s rear then front legs land in pairs. This resulted in the additional linkage that we call TrotBot’s “heel” which increased TrotBot’s foot-contact with the ground by about 10%, reduced how much the feet skidded, and increased the step-height of TrotBot’s rear legs. Shown below is a video comparing TrotBot with these “heels” to a galloping horse:

Next, we explored adding some sort of toe that would push down on the ground as the foot begins to lift, just like how humans use their toes to walk. We installed one of these toe ideas on our large TrotBot but they didn’t smooth the gait enough, and since they were attached to the legs at a fixed angle they tended to catch on obstacles. Catching on obstacles occasionally caused the linkage to lock and gears to grind. In other words, this toe compromised our main goal of creating a mechanism that could walk on rough terrain! Here’s a photo of that toe:

TrotBot’s fixed angle toe

Looking again to a galloping horse for inspiration we started to experiment with linkages that mimicked how horses paw their hooves backward and then keep them folded back as they lift their legs to strike the ground again. We discovered a few options that mimicked this action, and they smoothed the gait by increasing TrotBot’s foot-contact by another 10% while maintaining its high foot-path. I added one of these toe options to TrotBot Ver. 2, and while I couldn’t make a toe with accurate dimensions using LEGO’s integer-based beams, it still smoothes TrotBot’s gait significantly:

Click here for instructions on how to build your own TrotBot Ver. 2!

UgCS photogrammetry technique for UAV land surveying missions

SPH Engineering — Thu, 09 Mar 2017 14:00:00 +0000

Figure 15: Adding 40m overshot to both ends of each survey line

UgCS is easy-to-use software for planning and flying UAV drone-survey missions. It supports almost any UAV platform, providing convenient tools for areal and linear surveys and enabling direct drone control. What’s more, UgCS enables professional land survey mission planning using photogrammetry techniques.

How to plan photogrammetry mission with UgCS

Standard land surveying photogrammetry mission planning with UgCS can be divided into following steps :

Obtain input data
Plan mission
Deploy ground control points
Fly mission
Image geotagging
Data processing
Map import to UgCS (optional)

https://www.youtube.com/watch?v=SalCQoG6WUw&feature=youtu.be

Step one: Obtain input data

Firstly, to reach the desired result, input settings have to be defined:

Required GSD (ground sampling distance – size of single pixel on ground),
Survey area boundaries,
Required forward and side overlap.

GSD and area boundaries are usually defined by the customer’s requirements for output material parameters, for example by scale and resolution of digital map. Overlap should be chosen according to specific conditions of surveying area and requirements of data processing software.

Each data processing software (e.g., Pix4D, Agisoft Photoscan, Dronedeploy, Acute 3d) has specific requirements for side and forward overlaps for different surfaces. To choose correct values, please refer to documentation of chosen software. In general, 75% forward and 60% side overlap will be a good choice. Overlapping should be increased for areas with small amount of visual cues, for example for deserts or forests.

Often, aerial photogrammetry beginners are excited about the option to produce digital maps with extremely high resolution (1-2cm/pixel), and to use very small GSD for mission planning. This is very bad practice. Small GSD will result in longer flight time, hundreds of photos for each acre, tens of hours of processing and heavy output files. GSD should be set according to the output requirements of the digital map.

Other limitations can occur. For example, GSD of 10cm/pixel is required, but designed to use a Sony A6000 camera. Based on mentioned GSD and camera’s parameters, the flight altitude would be set to 510 meters. In most countries, maximum allowed altitude of UAV’s (without special permission) is limited to 120m/400ft AGL (above ground). Taking into account the maximum allowed altitude, the maximum possible GSD in this case could be no more than 2.3cm.

Step two: Plan your mission

Mission planning consists of two stages:

Initial planning,
Route optimisation.

-Initial planning:

The first step is to set surveying area using UgCS Photogrammetry tool. Area can be set using visual cues on underlying map or using exact coordinates of edges. The result – survey area is marked with yellow boundaries (Figure 1).

Figure 1: Setting the survey area

The next step is to set GSD and overlapping for the camera in Photogrammetry tool’s settings window (Figure 2).

Figure 2: Setting camera’s Ground Sampling Distance and overlapping

To take photos in Photogrammetry tool’s setting window, define the control action of the camera (Figure 3). Set camera by distance triggering action with default values.

Figure 3: Setting camera’s control action

At this point, initial route planning is completed. UgCS will automatically calculate photogrammetry route (see Figure 4).

Figure 4: Calculated photogrammetry survey route before optimisation

-Route optimisation

To optimise the route, it’s calculated parameters should be known: altitude, estimated flight time, number of shots, etc.

Part of the route’s calculated information can be found in the elevation profile window. To access the elevation profile window (if it is not visible on screen) click the parameters icon on the route card (lower-right corner, see Figure 5), and from the drop-down menu select show elevation:

Figure 5: Accessing elevation window from Route cards Parameters settings

The elevation profile window will present an estimated route length, duration, waypoint count and min/max altitude data:

Figure 6: Route values in elevation profile window

To get other calculated values, open route log by clicking on route status indicator: the green check-mark (upper-right corner, see Figure 7) of the route card:

Figure 7: Route card and status indicator, Route log

Using route parameters, it can be optimised to be more efficient and safe.

-Survey line direction

By default, UgCS will trace survey lines from south to north. But, in most cases, it will be more optimal to fly parallel to the longest boundary line of the survey area. To change survey line direction, edit direction angle field in the photogrammetry tool. In the example, by changing angle to 135 degrees, the number of passes is reduced from five (Figure 4) to four (Figure 8) and route length is 1km instead of 1.3km.

Figure 8: Changed survey line angle to be parallel to longest boundary

-Altitude type

UgCS Photogrammetry tool has the option to define how to trace the route according to altitude, with constant altitude above ground (AGL) or above mean sea level (AMSL). Please refer to your data processing software requirements as to which altitude tracking method it recommend.

In the UgCS team’s experience, the choice of altitude type depends on desired result. For orthophotomap (standard aerial land survey output format) it is better to choose AGL to ensure constant GSD for the entire map. If the aim is to produce DEM or 3D reconstruction, use AMSL so the data processing software has more data to correctly determine ground elevation by photos in order to provide more qualitative output.

Figure 9: Elevation profile with constant altitude above mean sea level (AMSL)

In this case, UgCS will calculate flight altitude based on the lowest point of the survey area.

If AGL is selected in photogrammetry tool’s settings, UgCS will calculate the altitude for each waypoint. But in this case, terrain following will be rough if no “additional waypoints” are added (see Figure 10).

Figure 10: Elevation profile with AGL without additional waypoints

Therefore, if AGL is used, add some “additional waypoints” flags and UgCS will calculate a flight plan with elevation profile accordingly (see Figure 11).

Figure 11: Elevation profile with AGL with additional waypoints

-Speed

In general, if flight speed is increased it will minimise flight time. But high speed in combination with large camera exposure can result in blurred images. In most cases 10m/s is the best choice.

-Camera control method

UgCS supports 3 camera control methods (actions):

Make a shot (trigger camera) in waypoint,
Make shot every N seconds,
Make shot every N meters.

Not all autopilots support all 3 camera control options. For example (quite old) DJI A2 does support all three options, but newer (starting from Phantom 3 and up to M600) cameras support only triggering in waypoints and by time. DJI promised to implement triggering by distance, but it’s not available yet.

Here are some benefits and drawbacks for all three methods:

Table 1: Benefits and Drawback for camera triggering methods

In conclusion:

Trigger in waypoints should be preferred when possible
Trigger by time should be used only if no other method is possible
Trigger by distance should be used when triggering in waypoints is not possible to use

To select triggering method in UgCS Photogrammetry tool accordingly, use one of three available icons:

Set camera mode
Set camera by time
Set camera by distance

-Glibal control

Drones, e.g., DJI Phantom 3, Phantom 4, Inspire, M100 or M600 with integrated gimbal, have the option to control camera position as part of an automatic route plan.

It is advisable to set camera to nadir position in the first waypoint, and in horizontal position before landing to prevent lenses from potential damage.

To set camera position, select the waypoint preceding the photogrammetry area and click set camera attitude/zoom (Figure 12) and enter “90” in the “Tilt” field (Figure 13).

Figure 12: Setting camera attitude

Figure 13: Setting camera position

As described previously, this waypoint should be a Stop&Turn type, otherwise the drone could skip this action.

To set camera to horizontal position, select last waypoint of survey route and click set camera attitude/zoom and enter “0” in the “Tilt” field.

-Turn types

Most autopilots or multirotor drones support different turn types in waypoints. Most popular DJI drones have three turn-types:

Stop and Turn: drone flies to the fixed point accurately, stays at that fixed point and then flies to next fixed point.
Bank Turn: the drone would fly with constant speed from one point to another without stopping.
Adaptive Bank Turn: It is almost the same performance like Bank Turn mode (Figure 13), but the real flight routine will be more accurately than Bank Turn.

It is advisable not to use Bank Turn for photogrammetry missions. Drone interprets Bank Turns as “recommendation destination waypoint”. The drone will fly towards this direction but will almost never pass through the waypoint. Because drone will not pass the waypoint, no action will be executed, meaning the camera will not be triggered, etc.

Adaptive Bank Turn should be used with caution because a drone can miss waypoints and, again, no camera triggering will be initiated.

Figure 14: Illustration of typical DJI drone trajectories for Bank Turn and Adaptive Bank Turn types

Sometimes, adaptive bank turn type has to be used in order to have shorter flight time compared to stop and turn. When using adaptive bank turns, it is recommended to use overshot (see below) for the photogrammetry area.

-Overshot

Initially overshot was implemented for fixed wing (airplane) drones in order to have enough space for manoeuvring a U-turn.

Overshot can be set in photogrammetry tool to add an extra segment to both ends of each survey line.

Figure 15: Adding 40m overshot to both ends of each survey line

In the example (Figure 15) can be seen that UgCS added 40m additional segments to both ends of each survey line (comparing to Figure 8).

Adding overshot is useful for copter-UAVs in two situations:

When Adaptive Bank Turns are used (or similar method for non-DJI drones), adding overshot will increase the chance that drone will precisely enter survey line and camera control action will be triggered. UgCS Team recommends to specify overshot that is approximately equal to distance between the parallel survey lines.
When Stop and Turn type is in use in combination with action to trigger camera in waypoints, there is a possibility that before making the shot, drone will start rotation to next waypoint – it can result in having photos with wrong orientation or blurred. To avoid that, shorter overshot has to be set, for example 5m. Don’t specify too short value (< 3m) because some drones could ignore waypoints, that are too close.

Figure 16: Example of blurred image taken by drone in rotation to next waypoint

-Takeoff point

It is important to check the takeoff area at site before flying any mission! To better explain best practice on how to set takeoff point, first discuss an example of how it should not be done. Supposing that the takeoff point in our example mission (Figure 17) would be from the point marked with the airplane-icon, and drone pilot would upload the route on the ground with set automatic mission for automatic take-off.

Figure 17: Take-off point example

Most drones in automatic takeoff mode would climb to low altitude about 3-10meters and then fly straight towards the first waypoint. Other drones would fly towards first waypoint straight from ground. Looking closely at the example map (Figure 17), some trees between the takeoff point and the first waypoint can be noticed. In this example, the drone more likely will not reach a safe altitude and will hit the trees.

Not only the surroundings can affect takeoff planning. Drone manufacturers can change drones elevation behavior in drone firmware, therefore after firmware updates it is recommended that you check drones automatic takeoff mode.

Also, a very important consideration is that most small UAVs use relative altitude for mission planing. Altitude counted relatively according to first waypoint is a second reason why an actual takeoff point should be near the first waypoint, and on the same terrain level.

UgCS Team recommends placing the first waypoint as close as possible to actual takeoff point and specifying a safe takeoff altitude (≈30m in most situations will be above any trees, see Figure 18). This is the only method that warrants safe takeoff for any mission. It also protects from any weird drone behaviour and unpredictable firmware updates, etc.

Figure 18: Route with safe take-off

-Entry point to the survey grid

In the previous example, (see Figure 18), it can be noticed, that after adding the takeoff point, the route’s survey grid entry point was changed. This is because if additional waypoint is added subsequently to the photogrammetry area, UgCS will plan to fly the survey grid starting from nearest corner to the previous waypoint.

To change the entry point to survey grid, set additional waypoint close to the desired starting corner (see Figure 19).

Figure 19: Changing survey grid entry point by adding additional waypoint

-Landing point

If no landing point will be added outside the photogrammetry area after the survey mission, the drone will fly and hover in the last waypoint. There are two options for landing:

Take manual control over the drone and fly to landing point manually,
Activate the Return Home command in UgCS or from Remote Controller (RC).

In situations when the radio link with the drone is lost, for example if the survey area is large or there are problems with the remote controller, depending on the drone and it’s settings, one of these actions can occur:

Drone will return to home location automatically if lost radio link with ground station,
Drone will fly to last waypoint of survey area and hover as long as battery capacity will enable that, then: drone will perform emergency landing, or it will try to fly to home location.

The recommendation is to add an explicit landing points to the route in order to avoid relying on unpredictable drone behavior or settings.

If the drone doesn’t support automatic landing, or the pilot prefers to land manually, place the route’s last waypoint over the planned landing point with an altitude for comfortable manual drone descending and landing above any obstacles in the surrounding area. In general 30m is best choice.

-Action execution

Photogrammetry tool has a magic parameter “Action Execution” with three possible values:

Every point
At start
Forward passes

This parameter defines how and where camera actions specified for photogrammetry tool will be executed.

The most useful option for photogrammetry/survey missions is to set forward passes, the drone will make photos only on survey lines, but will not make excess photos on perpendicular lines.

-Complex survey areas

UgCS enables photogrammetry/survey mission planning for irregular areas, having functionality to combine any number of photogrammetry areas in one route, avoiding splitting the area in separate routes.

For example, if a mission has to be planned for two fields connected in a T-shape, and if these two fields are marked as one photogrammetry area, the whole route will not be optimal, regardless any direction of survey lines.

Figure 20: Complex survey area before optimisation

If the survey area is marked as two photogrammetry areas within one route, survey lines for each area can be optimised individually (see Figure 21).

Figure 21: Optimised survey flight passes for each part of a complex photogrammetry area

Step three: deploy ground control points

Ground control points are mandatory if the survey output map has to be precisely aligned to coordinates on Earth.

There are lots of discussions about the necessity of ground control points in cases when a drone is equipped with Real Time Kinematics (RTK) GPS receivers with centimeter-level accuracy. This is useful, but the drone coordinates are not in themselves sufficient because, for precise map aligning, image center coordinates are necessary.

Data processing softwares like Agisoft Photoscan, Dronedeplay, Pix4d, Icarus OneButton and others will produce very accurate maps using geotagged images, but the real precision of the map will not be known without ground control points.

Conclusion: ground control points have to be used to create survey-grade result. For a map with approximate precision, it is sufficient to rely just on RTK GPS and the capabilities of data processing software.

Step four: fly your mission

For carefully planned missions, flying it is the most straightforward step. Mission execution differs according to the type of UAV and equipment used, therefore it will not be described in detail in this article (please refer to equipment’s and UgCS documentation).

Important issues before flying:

In most countries there are strict regulations for UAV usage. Always comply with the regulations! Usually these rules can be found on web-site of local aviation authority.
In some countries special permission for any kind of aerial photo/video shooting is needed. Please check local regulations.
In most cases missions are planned before arriving to flying location (e.g., in office, at home) using satellite imaginary from Google maps, Bing, etc. Before flying always check actual circumstances at the location. There could be a need to adjust take-off/landing points, for example, to avoid tall obstacles (e.g., trees, masts, power lines) in your survey area.

Step five: image geotagging

Image geotagging is optional if ground control points were used, but almost any data processing software will require less time to process geotagged images.

Some of the latest and professional drones with integrated cameras can geotag images automatically during flight. In other cases images can be geotagged in UgCS after flight.

Very important: UgCS uses the telemetry log from drone, that is received via radio channel, to extract the drone’s altitude for any given moment (when pictures were taken). To geotag pictures using UgCS, assure robust telemetry reception during flight.

For detailed information how to geotag images using UgCS refer to UgCS User Manual.

Step six: data processing

For data processing, use third party software or services available on the market.

From UgCS Team experience, the most powerful and flexible software is Agisoft Photoscan (http://www.agisoft.com/), but sometimes too much user input is required to get necessary results. The most uncomplicated solution for users is online service Dronedeploy (https://www.dronedeploy.com/). All other software packages and services will fit somewhere between these two in terms of complexity and power.

Step seven (optional): import created map to UgCS

Should the need arise for the mission to be repeated in the future, UgCS enables importing the GeoTiff file as a map layer and using it for mission planning. More detailed instructions can be found in UgCS User Manual. See the result of an imported map created using UgCS photogrammetry tool imported as GeoTiff file in Figure 22.

Figure 22: Imported GeoTiff map as layer. The map is output of a Photogrammetry survey mission panned with UgCS

Visit the UgCS homepage

Download this tutorial as a PDF

If you liked this tutorial, you may also enjoy these:

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

Programming for robotics: Introduction to ROS

Péter Fankhauser — Tue, 07 Mar 2017 15:15:39 +0000

This handy video-tutorial course gives an introduction to the Robot Operating System (ROS), including many of the available tools that are commonly used in robotics. With the help of different examples, the tutorials offer a great starting point to learn programming robots. You will learn how to create software including simulation, to interface sensors and actuators, and to integrate control algorithms.

The course consists of a guided tutorial and exercises with increasing level of difficulty working with an autonomous robot. We provide recordings of the lectures and give an introduction to the exercises. From the course website, you can download all the material including exercise sheets and templates, and use the provided Virtual Machine (VM) image to start programming right away.

Objectives:

ROS architecture: Master nodes, topics, messages, services, parameters and actions
Console commands: Navigating and analyzing the ROS system and the catkin workspace
Creating ROS packages: Structure, launch-files, and best practices
ROS C++ client library (roscpp): Creating your own ROS C++ programs
Simulating with ROS: Gazebo simulator, robot models (URDF) and simulation environments (SDF)
Working with visualizations (RViz) and user interface tools (rqt)
Inside ROS: TF transformation system, time, bags

Course 1:

Course 2:

Course 3:

Course 4:

Download the full presentation here.

P. Fankhauser, D. Jud, M. Wermelinger, M. Hutter, “Programming for Robotics – Introduction to ROS”, ETH Zurich, 2017. DOI: 10.13140/RG.2.2.14140.44161

If you liked this tutorial, you may also enjoy these:

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

Leg over wheels: Ghost robotics’ Minitaur proves legged capabilities over difficult terrain

Alex Kirkpatrick — Tue, 07 Mar 2017 10:00:28 +0000

Ghost Robotics—a leader in fast and lightweight direct-drive legged robots—announced recently that its Minitaur model has been updated with advanced reactive behaviors for navigating grass, rock, sand, snow and ice fields, urban objects and debris, and vertical terrain.

The latest gaits adapt reactively to unstructured environments to maintain balance, ascend steep inclines up to 35º, climb up to 15cm curb-sized steps, crouch to fit under crawl spaces as low as 27cm, and operate at variable speeds and turning rates. Minitaur’s high-force capabilities enable it to leap up to 40cm onto ledges and across gaps of up to 80cm. Its high control bandwidth allows it to actively balance on two legs, and its high speed operation allows its legs to navigate challenging environments rapidly, whilst reacting to unexpected contact.

“Our primary focus since releasing the Minitaur late last year has been expanding its behaviors to traverse a wide range of terrains and real-world operating scenarios,” said Gavin Kenneally, and Avik De, Co-founders of Ghost Robotics. “In a short time, we have shown that legged robots not only have superior baseline mobility over wheels and tracks in a variety of environments and terrains, but also exhibit a diverse set of behaviors that allow them to easily overcome natural obstacles. We are excited to push the envelope with future capabilities, improved hardware, as well as integrated sensing and autonomy.”

Ghost Robotics is designing next-generation legged robots that they claim are superior to wheeled and tracked autonomous vehicles in real-world field applications. They are also attempting to substantially reduce costs to drive adoption and scalable deployments. Whilst a commercial version of the Ghost Minitaur robot is slated for delivery in the future, the current development platform is in high demand, and has been shipped to many top robotics researchers worldwide (Carnegie Mellon, University of Pennsylvania, University of Washington, U.S. Army Research Labs and Google) for use in a broad range of research and commercialization initiatives.

“We are pleased with our R&D progress towards commercializing the Ghost Minitaur to prove legged robots can surpass the performance of wheel and track UGVs, while keeping the cost model low to support volume adoption—which is certainly not the case with existing bipedal and quadrupedal robot vendors,” said Jiren Parikh, Ghost Robotics, CEO.

In the coming quarters, the company plans to demonstrate further improvements in mobility, built-in manipulation capabilities, integration with more sensors, built-in autonomy for operation with reduced human intervention, as well as increased mechanical robustness and durability for operation in harsh environments. Watch this space.

If you enjoyed this article, you might also be interested in:

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

Hard at work: A review of the Laevo Exoskeleton

Philip English — Thu, 23 Feb 2017 11:10:32 +0000

Back pain is one of the leading causes of work absenteeism in the UK, with 8.8 million days lost to work-related muscoskeletal disorders per year. On average, each case causes 16 days of absenteeism, and chronic conditions can cause some absences to become permanent.

But working in a bent forward, back straining posture is unavoidable in a great many professions, like in hospital, agricultural and warehouses environments to name but a few. This regular exposure to demanding postures increases the risk of debilitating pain, which can severely reduce productivity and moral in the workforce.

The Laevo Exoskeleton aims to alleviate this problem. The Laevo is a unique, wearable back-support that aids users working in a bent forward posture or lifting objects. The wearable frame carries part of the upper body weight of the user, thereby decreasing the strain on the lower back and improves the long-term employability of employees.

Video 1: The product

Video 2: See it in action

If you liked this article, you may also enjoy these:

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

Python programming your NAO robot

Philip English — Thu, 09 Feb 2017 12:05:44 +0000

These videos aim to teach you how to begin programming your NAO with Python. The NAO can be programmed using several programming languages, including C++, MATLAB, JAVA, LabVIEW and Python. Instead of using the drag and drop boxes in the Choreograph, we’re going to get our NAO robot walking and talking using coding.

Tutorial 1: Speech

Helpful hints:

Follow these steps to create a box that we could put our python code into, and have our robot speak: “Hello”. “Hello I am a robot”.

Right click the main section box and go to “add new box”
Create a name for the box
Input main image
Select the type of box

Now we’re having a look at the script. Go into the scripts and click ok. And there we have our NAO little box. If we click into it, we have the python code. What we are going to do is change some of the codes to get our robot to speak.

Double click the box
Select the piece of code you need to alter to get our robot to speak(“def onInput_onStart(self)”)
Take out the pass section
Type in “ttsproxy = ALProxy(“ALTextToSpeech”)”. (Make sure you get the comment in there).
Underneath that, we are going to put “ttsproxy.say” and add the comment “Hello, I am a robot”.

The first line could create an object that gives us access to the robot’s text to speech capabilities. This object is assigned to the variable ttsProxy. We can access the object later through the name ttsProxy. I am going to mount the top line, and the alspeech is there. The second line calls a different function site. This function takes an argument “Hello, I am a robot” and then he uses a string or sequence of characters between two double quoted marks. The robot will speak the string that will pass to the say message aloud. There are your simple first steps into python and choreograph.

You can now, hopefully, get your NAO robot to talk by using your python programming skills. Now have a play with it’s behavior to see if you can get your NAO to say a longer sentence, or maybe even sing a song. Have a play, and use your imagination!

Tutorial 2: Walking

Helpful hints:

No we’re going get your robot to walk using Python. The NAO can be program to walk to any point using the in-build Python Programming Language instead of using the drag and drop boxes in the choregraphe. Python is more expressive and allows you to do things like computing trigonometric calculations on the robot.

Right click the main section box and go to “add new box”
Create a name for the box
Input main image
Select the type of box

First, we want our robot to stand up. Drag a stand up icon into the box. I am actually using the NAO key so the 3D robot in the robot view, and this because we need to put the robot on connecting so we can see what’s going on quite clearly. Oversee when you are using this on the real robot and never forget to trigger on the motors and connect everything up properly.

Open the Code Box

Go to “def onInput_onStart(self):”
Write “motionProxy = ALProxy(“ALMotion”)”
On the next line write “walkTo(0.2,0.0,0.0)”
End it with “self.onStopped()”

The first line is a proxy called ALmotion, which what is we created here, which allows us to call the motion functions up. The second line is the walkTo, which moves the robot to a specific distance. Now, look on the decimal places: see that .2 is X and Y and the radius, so he’s going to move .2 forward. Then if I start playing with the other numbers here, he’ll move to the Y radius and then to the other turning point as well. The final bit is the self.on. To stop this, we will call and tell the choregraphe to stop the procedure when it is at the end and just simple loop and loop and loop.

If we are good, we should see this now on the 3D NAO. So if I hit play, we can see it walking along. Well done guys, you can now get your NAO Robot to walk by using
your Python programming skills. Tread carefully!

If you liked this article, you may also enjoy these:

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

Artificial intelligence and ethics: Who does the thinking?

Alex Kirkpatrick — Fri, 27 Jan 2017 14:30:19 +0000

Image: IEEE

On the 15th November 2016, the IEEE’s AI and Ethics Summit posed the question: “Who does the thinking?” In a series of key-note speeches and lively panel discussions, leading technologists, legal thinkers, philosophers, social scientists, manufacturers and policy makers considered such issues as:

The social, technological and philosophical questions orbiting AI.
Proposals to program ethical algorithms with human values to machines.
The social implications of the applications of AI.

Click here to read the final report, and enjoy a selection of videos from the conference below.

Welcome: Marko Delimar
Keynote Speaker: Wojciech Wiewiórowski

Panel 1: Autonomous Systems – Managing Risk and Reward
Panel Members: Raja Chatila, Kay Firth-Butterfield, Juha Heikkilä, Jérôme Perrin

Panel 2: Programming Human Ethics: Cui Bono?
Panel Members: Joanna Bryson, Mady Delvaux, Sarah Spiekermann, Corrine Cath

Panel 3: Social Implications – Perils & Promises of AI
Panel Members: Greg Adamson, Nikolaos Mavridis, Paul Nemitz, Aurélie Pols

Closing Remarks: John C. Havens

You might also enjoy the following articles about AI and AI/robotics policy:

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

Responsive and Responsible Leadership given prominance at #WEF17 World Economic Forum

Alex Kirkpatrick — Fri, 20 Jan 2017 12:30:56 +0000

The population of the scenic ski-resort Davos, nestled in the Swiss Alps, swelled by nearly +3,000 people between the 17^th and 20^th of January. World leaders, academics, business tycoons, press and interlopers of all varieties were drawn to the 2017 World Economic Forum (WEF) Annual Meeting. The WEF is the foremost creative force for engaging the world’s top leaders in collaborative activities to shape the global, regional and industry agendas for the coming year and beyond. Perhaps unsurprisingly given recent geopolitical events, the theme of this year’s forum was Responsive and Responsible Leadership.

With the onset of the fourth industrial revolution, increasingly discontented segments of society not experiencing congruous economic and social progress are in danger of existential uncertainty and exclusion. Responsive and Responsible Leadership entails inclusive development and equitable growth, both nationally and globally. It also involves working rapidly to close generational divides by exercising shared stewardship of those systems that are critical to our prosperity.

In the end, leaders from all walks of life at the Annual Meeting 2017 must be ready to react credibly and responsibly to societal and global concerns that have been neglected for too long.”

Developing last year’s theme—“The fourth industrial revolution”—this year’s luminaries posited questions, among many others, concerning incipient robotics and artificial intelligence technologies set to have a pronounced impact on the global economy and global consciousness alike. What can we learn from the first wave of AI? How can the humanitarian sector benefit from big data algorithms? How will drone technology change the face of warfare? Can AI and computational tech help foster responsive and responsible leadership? What are the downsides of technology in the fourth industrial revolution?

Enjoy a selection of tech-themed videos below.

And a bit about global science including big data, open source science and education.

What is machine learning?

Oxford Sparks — Mon, 16 Jan 2017 09:15:15 +0000

In this fascinating animation from Oxford Sparks, we take a look at how statistics and computer science can be used to make machines that learn for themselves, without being explicitly programmed.

Machine learning is a burgeoning breed of artificial intelligence (AI), and it’s all around us already; on our phones, powering social networks, helping the police and doctors, scientists and mayors. But how does it work? Enjoy the video below, and visit Oxford Sparks to discover more science and research from Oxford University.

You might also enjoy the following posts about AI and AI/robotics policy:

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

Brian Cox presents Science Matters: Machine learning and artificial intelligence

Robohub Editors — Wed, 11 Jan 2017 18:41:50 +0000

We’re beginning to see more and more jobs being performed by machines, even creative tasks like writing music or painting can now be carried out by a computer.

But how and when will machines be able to explain themselves? Should we be worrying about an artificial intelligence taking over our world or are there bigger and more imminent challenges that advances in machine learning are presenting here and now?

Join Professor Brian Cox, the Royal Society Professor of Public Engagement, as he brings together experts on AI and machine learning to discuss key issues that will shape our future. Panelists include:

Professor Jon Crowcroft FRS, Marconi Professor of Networked Systems at the University of Cambridge
Professor Joanna Bryson, Reader in AI Ethics, University of Bath and Affiliate, Center for Information Technology Policy, Princeton University
Professor Sabine Hauert, Lecturer in Robotics at the University of Bristol, and President and Co-Founder of Robohub.org
Professor Murray Shanahan, Professor of Cognitive Robotics at Imperial College London
Professor Peter Donnelly FRS FMedSci, Director, Wellcome Trust Centre for Human Genetics, and Professor of Statistical Science, University of Oxford

https://www.youtube.com/watch?v=IunNpGGt3H8

You might also enjoy the following articles about AI and AI/robotics policy:

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

Call for holiday robot videos 2016

Robohub Editors — Fri, 09 Dec 2016 21:05:55 +0000

That’s right! You better not run, you better not hide, you better watch out for brand new robot holiday videos on Robohub! Drop your submissions down our chimney at editors@robohub.org and share the spirit of the season, like these vids-of-Christmas-past…

Sticky business: Five adhesives tested for 3D printing

George Fomitchev — Fri, 28 Oct 2016 10:00:45 +0000

https://www.youtube.com/watch?v=ipPzi9J-M9w

We compared five adhesives for 3D printing applications on a Wanhao Duplicator i3. We’ll print a PLA (polylactide) cube, 1х1х1 cm in size.

1. NELLY LACQUER: We spread it on the clean surface of the table and turn on the Print Mode. The printed model is very well stuck—a pallet-knife is needed to separate it from the surface of the table. The adhesion result is very good.

2. THE 3D GLUE: We apply it to the table with a cloth, wait for the table to warm up, then start printing. The result is similar to Nelly lacquer. We can’t separate the printed model from the table without any tools. The bottom of the cube is smooth.

3. PVA GLUE: We spread a small quantity on the table and let it dry before printing. It is not easy to tear the model from the table. The bottom surface of the cube is rather rough and has PVA glue stains.

4. GLUE STICK: We try to apply a thin layer of it to the hot platform but, because the adhesive is very thick, we can’t do it using a microfiber cloth. To separate the cube from the platform we use a pallet-knife. The bottom surface of the model and the platform surface have white glue stains. Now we need to clean the table and apply an adhesive anew.

5. STICKY TAPE (an analogue of a blue Scotch): Finally, we paste one layer of it to the table, carefully smoothing it out to avoid blistering. This adhesive is no good for big ABS models as they tend to break away from the table along with the tape.

We try to accurately separate the cube from the table to prevent the tape from peeling off, but part of the tape stuck too well to the cube and came off the table along with the model. Now we’ll have a naked spot (without the tape layer) on the table when we print next time.

Conclusions

The lacquer and 3D glue give the best results; the bottom surface of the printed models is clean and smooth, without any traces of adhesives.
The glue stick stains the models.
The Scotch tape tends to stick to the model and comes off from the table partially or fully.
For ABS printing we recommend using a closed 3D printer and a strong adhesive, like NELLY.

If you liked this article, you may also want to read these other articles on 3D printing:

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

In motion: Video transmission by mobile drones

Christian Bettstetter — Fri, 07 Oct 2016 09:30:42 +0000

Raheeb Muzaffar, an information technology specialist, has developed an application-layer framework that improves the transmission of videos between moving drones and mobile devices located at ground level. His work within the Interactive and Cognitive Environments (ICE) doctoral programme will be completed soon. Raheeb explains what makes this technology innovative and talks about his plans for the future in a conversation with Romy Mueller.

Raheeb Muzaffar was already aware of what to expect when he arrived in Klagenfurt as a PhD student, travelling from Islamabad, the capital of Pakistan, December 2012: He’s travelled well before, had experience working with various universities and professional organizations, and was acquainted both with the European culture and the research environment. The doctoral programme “Interactive and Cognitive Environments (ICE)” suited him perfectly, allowing him to conduct research in an international environment. Doctoral students accepted into the programme are funded for a period of three years. During this time, they work at two universities. The research teams at the Alpen-Adria-Universität and the Queen Mary University in London offered Muzaffar, who wanted to work on the communication between drones, an environment that allowed him insight into various laboratories and research approaches. By combining the key research areas he experienced in Austria and Great Britain, he ultimately arrived at his very own topic: video transmission in drone networks.

He spotted a problematic issue in this context, which he has studied very closely over the past few years. “In a situation where several drones are airborne and are transmitting videos to several units located at ground level, we cannot currently guarantee that the footage will be reliably transmitted.” The problem is that the receiving devices do not have a feedback mechanism for the video packets being transmitted from the drones. The missing feedback mechanism causes unreliability rendering a distorted video reception. Also, when the transmitting devices and the receiving devices are in motion, the wireless transmission conditions are subject to continuous change, introducing an additional factor of uncertainty.

To address this problem, Raheeb Muzaffar has developed a so-called “video multicast streaming framework”, which allows feedback from multiple ground devices to the drones to add reliability allowing a smooth video reception. However, the framework is even more capable: “The drone does not only learn whether the video has arrived, but thanks to the feedback mechanism, the drone can adjust the transmission rate and the video quality to match the prevailing wireless conditions. Thus, the transmitting drones can re-send lost video packets following the transmission and video rate adaption.” Video communication between drones and receiving devices is useful for various applications such as search and rescue, surveillance, and disaster management.

When we asked him, if he can make profitable use of his technology, Raheeb Muzaffar laughed. At various conferences, he talked to the developers from the industry, who confirmed to him that modules endowed with similar functionality are expensive and that the WLAN protocol requires modification. However, his application is freely available. Anyone wishing to commercialise the technology as a product, is able to do so. In any case, over the course of numerous simulations and experiments, he has demonstrated that the streaming framework works and uses the conventional WLAN protocol without modifications.

Muzaffar’s research in Klagenfurt is coming to an end. By November, he will complete his doctoral thesis, and will pull up stakes in Klagenfurt, following his hopes and dreams to work in the research-based industry. The researcher was accompanied by his wife when he came to Klagenfurt. In the meantime, they celebrated the birth of their daughter. The Muzaffar family intends to travel more: “I am not tied to one location. I would enjoy working anywhere in Europe, but we also like the idea of moving to New Zealand.”

A few words with Raheeb Muzaffar

What career would you have chosen, if you had not become a scientist?

If I would not have become a scientist, I would have become a social worker. Before turning to research, I worked with Non-governmental organizations including iMMAP and UNICEF thinking that my technical expertise could help expedite the social work that the organizations are involved in. Besides the work I do plan to involve myself in some sort of social work may it be technical, educational, financial or emotional.

Do your parents understand what it is you are working on?

Yes, especially my father, he is quite interested in technology. He may not have the technical details but he is aware of research and the work I am involved in.

What is the first thing you do when you arrive at the office in the morning?

First thing in the morning is to check and answer my emails. Thereafter, I work by the plan. I always have a plan for the week/month regarding the tasks I need to do. Although sometimes things don’t go by the plan and I have to readjust the plan to meet deadlines.

Do you have proper holidays? Without thinking about your work?

Yes, at least once a year.

Why are so many people afraid of technical sciences?

In my opinion, every individual has a different aptitude to his/her work domain and one should do what one thinks he/she is interested in and can perform best. Having said that, working in the domain of technical science is quite challenging. The field has advanced and it is getting increasingly complex to even gain the basic understanding of different domains. To work in this field, one has to stay up to date. Developing something new involves a minimal margin of error. I think, people are afraid due to the complex nature of the studies that involve an extra bit of hard work, understanding, and patience.

Written by: Romy Müller, University of Klagenfurt

Originally published in German language in AAU News of the University of Klagenfurt, Austria. Also published at Medium.com.

WeRobot 2015 Keynote: The future of robotics, with R2D2 maker Tony Dyson

Robohub Editors — Fri, 04 Mar 2016 11:46:44 +0000

Photo courtesy We Robot 2015.

UPDATED 4 Mar: We’re sad to report that Professor Tony Dyson, who built the original Star Wars R2-D2 droid, has died. We’re reposting this excellent video of his keynote at WeRobot to highlight his contribution to the field of robotics and culture.

Raffaello D’Andrea at TED2016: Novel flying machines and swarms of tiny flying robots

Robohub Editors — Mon, 22 Feb 2016 13:18:26 +0000

Last week Raffaello D’Andrea, professor at the Swiss Federal Institute of Technology (ETH Zurich) and founder of Verity Studios, demonstrated a whole series of novel flying machines live on stage at TED2016: From a novel Tail-Sitter (a small, fixed-wing aircraft that can optimally recover a stable flight position after a disturbance and smoothly transition from hover into forward flight and back), to the “Monospinner” (the world’s mechanically simplest flying machine, with only a single moving part), to the “Omnicopter” (the world’s first flying machine that can move into any direction independent of its orientation and its rotation), to a novel fully redundant quadrocopter (the world’s first, consisting of two separate two-propeller flying machines), to a synthetic swarm (33 flying machines swarming above the audience).

Most of D’Andrea’s work shown at this latest demonstration is dedicated to pushing the boundary of what can be achieved with autonomous flight. One key ingredient is localization: To function autonomously, robots need to know where they are in space. Previously his team has relied on an external high-precision motion capture system available in his Flying Machine Arena at ETH Zurich for positioning. In his previous TED talk on robot athletes for example, you can clearly see the reflective markers required by the motion capture system. This meant that most algorithms were difficult to demonstrate outside the lab. It also meant that the system had a single point of failure (SPOF) in the centralized server of the mocap system — a highly problematic point for any safety critical system.

In another world first, Raff and his team are now showing a newly developed, doubly redundant localization technology from Verity Studios, a spin-off from his lab, which gives flying machines, and robots in general, new levels of autonomy. For the live demonstrations, all flying machines use on-board sensors to determine where they are in space and on-board computation to determine what their actions should be. There are no external cameras. The only remote commands the flying robots receive are high level ones, such as “take-off” or “land”.

The nature of this performance was also unprecedented in that it did not use safety nets to separate the audience from the action, and in that it even saw dozens of vehicles fly directly above the audience.

The performance included demonstrations of various safety systems for flying machines, including a large, high-performance quadcopter that is fully redundant and that utilizes a state-of-the-art failsafe algorithm (see previous Robohub article) among its many other onboard and offboard safety features.

Following extensive technical discussions on the various failure modes of the positioning system and of each flying machine as well as on the systems’ numerous redundancies and safety features, the organizers of TED had full faith in the systems’ safety and reliability. So much so that they decided to indemnify the venue against any lawsuits to overcome its ban on drones.

Here is the video:

And here is a more in-depth breakdown of what you are seeing, based on a transcript of the presentation and information from Raff D’Andrea’s team:

Intro video – Institute for Dynamic Systems and Control (IDSC), ETH Zurich

The video shows some of the previous work of D’Andrea’s group on aerial construction: A 6-meter tall tower built out of 1500 foam bricks by four autonomous quadcopters over a three day period in front of a live audience and a rope bridge built by three autonomous quadcopters in the Flying Machine Arena.

Live demo 1: Tail-Sitter – IDSC, ETH Zurich

The Tail-sitter. Photo: Bret Hartman / TED

“This is a so-called tail-sitter. It’s an aircraft that tries to have its cake and eat it: Like other fixed wing aircraft, it is efficient in forward flight, much more so than helicopters and variations thereof. Unlike most other fixed wing aircraft, however, it can hover, which has huge advantages for take-off, landing, and general versatility. There is no free lunch, unfortunately, and one of the challenges with this type of aircraft is its susceptibility to disturbances, such as wind-gusts, while hovering. We are developing control architectures and algorithms that address this limitation. [Pushes the vehicle, then grabs it and throws it] The idea is to allow the aircraft to autonomously recover no matter what situation it finds itself in. [Second throw] And through practice, improve its performance over time. [Third throw, violently spinning the vehicle]”

Demo 2 (video of demo the night before): Monospinner – IDSC, ETH Zurich

The Monospinner. Photo: Marla Aufmuth / TED

“When doing research we often ask ourselves abstract, fundamental questions that try to get at the heart of a matter. One such question: What is the minimum number of moving parts necessary for controlled flight? This line of exploration may have practical ramifications; take helicopters, for example, which are affectionately known as “machines with over 1000 moving parts all conspiring to cause bodily harm”. Turns out that decades ago skilled pilots were flying RC airplanes with only 2 moving parts: a propeller and a tail rudder. We recently discovered that it could be done with only 1.”

“This is the monospinner, the world’s mechanically simplest, controllable flying machine, invented just a few months ago. It has only one moving part, a propeller. There are no flaps or hinges, no control surfaces or valves, no other actuators. Just one propeller. Even though it is mechanically simple, there is a lot going on in its electronic brain to keep it stable and move through space in a controllable fashion. Even so, it does not yet have the recovery algorithms of the tail-sitter, which is why I have to throw it just right.”

Live demo 3: Omnicopter – IDSC, ETH Zurich:

The Omnicopter. Photo: Bret Hartman / TED

“If the monospinner is an exercise in frugality, this machine here, the omnicopter, with its 8 propellers, is an exercise in excess. What can you do with this surplus? The thing to notice is that it is highly symmetric, and as a result it is ambivalent to orientation. This gives it an unprecedented capability: It can move anywhere in space, independently of where it is facing, and even of how it is rotating. It has its own complexities, mainly due to the complex, interacting flows of its 8 propellers. Some of this can be modeled, while the rest can be learned on the fly. [Omnicopter takes off, manoeuvres around the stage, lands]”

Live demo 4: Fully redundant multicopter – Verity Studios

Fully redundant quadcopter. Photo: Ryan Lash / TED

“If flying machines are going to find their way into our daily lives, they will need to become extremely safe. This machine here is a prototype being developed by Verity Studios. It actually consists of two separate, two propeller flying machines, each capable of controlled flight. One wants to rotate clockwise, the other one counter clockwise. When all systems are operational, it behaves like a high-performance, 4 propeller quadrocopter. [Quadcopter takes off and flies an arc across the stage] If anything fails, however – propeller, motor, electronics, even a battery pack – it is still able to fly, albeit in a degraded way [One half of the quad is de-activated, the quadrocopter starts to spin and fall, the failsafe mode kicks in and the quadrocopter recovers, flies to the back of the stage, and performs a controlled landing at the takeoff spot].”

Live demo 5: Synthetic swarm, 33 small flying machines – Verity Studios

Photo: Bret Hartman / TED

“This last demonstration is an exploration of synthetic swarms. The large number of coordinated autonomous entities offers a radically new palette for aesthetic expression. We have taken commercially available micro-quadrocopters, each weighing less than a slice of bread, and equipped them with our localization technology and custom algorithms. Because each unit knows where it is in space and is self-controlled, there really is no limit to their number. [Swarm performance]”

Raffaello D’Andrea wrapped up with: “Hopefully these demonstrations will motivate you to dream up new revolutionary roles for flying machines. For example, the ultra-safe flying machine [points to the fully redundant multicopter] has aspirations to become a flying lampshade on Broadway. The reality is that it is difficult to predict the impact of nascent technology. And for folks like us, the real reward is the journey, and act of creation. It is also a continual reminder of how wonderful and magical the universe we live in is; that it permits clever, creative creatures to sculpt it in such spectacular ways. The fact that this technology has huge commercial potential is just icing on the cake.”

More photos for your viewing pleasure:

Photo: Bret Hartman / Ryan Lash / TED

Photo: Steven Rosenbaum / Waywire

The Year of CoCoRo Video #51/52: Big Vision

Thomas Schmickl — Tue, 22 Dec 2015 21:28:09 +0000

Our penultimate video features the initial “Big Vision” trailer we produced at the beginning of this project. The video showcases the basic components of the robotic system we targeted (surface station, relay chain, ground swarm) and how we imagined our collective of underwater robots forming coherent swarms.

Our “Big Vision” helped us stay focussed on the project, ensuring that all project partners shared the same goal for their work. We based the video on a small simulator, written by us. Little did we know that this simple simulator would develop into a critical tool that would eventually include underwater physics with fluid dynamics for simulating underwater swarms. The simulator was also used in evolutionary computation to find good shoaling behavior for our robots.

Next week we will be publishing our final video in the Year of the CoCoRo. Our finale will show the whole system on real underwater robots in a comparable setting and how our initial vision finally became reality!

Holiday robot videos 2015: Part 1

Robohub Editors — Mon, 21 Dec 2015 22:33:04 +0000

Have a holiday robot video of your own that you’d like to share? Send your submissions to info [at] robohub.org!

Autonomous Systems Lab and Robotics Systems Lab at ETHZ:

This is what happens when a robot wishes for Christmas!

Department of Advanced Robotics (ADVR) at IIT:

Made from the many robots we built at the iCub facility and the ADVR department at ITT.

Want to watch them all? Check out the full playlist on Youtube here:

Brown University wins inaugural Rethink Robotics Video Challenge

Rethink Robotics — Wed, 16 Dec 2015 18:05:52 +0000

As the worldwide leader in collaborative robotics research and education, Rethink Robotics is excited to announce the winner of the inaugural Rethink Robotics Video Challenge. Launched in the summer of 2015, the Challenge was created to highlight the amazing work being done by the research and education community with the Baxter robot. With more than 90 total entries from 19 countries around the globe, the Humans to Robots Lab at Brown University was a standout in the criteria of relevancy, innovation and breadth of impact.

A significant obstacle to robots achieving their full potential in practical applications is the difficulty in manipulating an array of diverse objects. The Humans to Robots Lab at Brown is driving change in this area by using Baxter to collect and record manipulation experiences for one million real-world objects.

Central to the research at the Humans to Robots Lab is the standardization and distribution of learned experience, where advances on one robot in the network will improve every robot. This research seeks to exponentially accelerate the advancement in capabilities of robots around the world, and establish a framework by which the utility of these types of systems advances at a pace never before seen.

http://origin-qps.onstreammedia.com/origin/multivu_archive/PRNA/ENR/294915-Brown-University-H2R.mp4

To better collaborate with labs around the world, Professor Stefanie Tellex and the team at Brown use the Baxter robot, an industrial robot platform that has the capability to automatically scan and collect a database of object models, the flexibility of an open source software development kit and an affordable price that makes the platform accessible to researchers all over the world. As a result of the Rethink Robotics Video Challenge, Brown will have an additional Baxter that will accelerate this research, while also providing new opportunities for continued experimentation.

“Our goal in creating the Rethink Robotics Video Challenge was to raise awareness of the tremendous amount of unique, cutting-edge research being conducted using collaborative robots that advances our collective education. The response far exceeded our expectations, and narrowing this down to one winner was an extremely difficult task for our judging panel,” said Rodney Brooks, founder, chairman and CTO of Rethink Robotics. “Brown was ultimately chosen as the best entry because the work being conducted by the Humans to Robots Lab at Brown University is critical to helping robots become more functional in our daily lives. There is a stark contrast between a robot and human in the ability to manipulate and handle a variety of objects, and closing that gap will open up a whole new world of robotic applications.”

Educational institutions, research labs and companies from around the world submitted an abstract and video showcasing their work with Baxter in one of three categories: engineering education, engineering research, or manufacturing skills development. The submissions encompassed a wide range of work, including elementary school STEM education, assistance to the physically and visually impaired, mobility and tele-operation, advanced and distributed machine learning and cloud-based knowledge-sharing for digital manufacturing and IoT, to name a few. After a detailed vetting process, the field was narrowed to 10 finalists from the following organizations: Brown University, Cornell University, Dataspeed Inc., Glyndwr University, Idiap Research Institute, North Carolina State University, Queens University, University of Connecticut, University of Sydney and Virginia Beach City Public Schools.

Finalist entries were reviewed by a premier panel of judges, including Rodney Brooks of Rethink Robotics; Lance Ulanoff, chief correspondent and editor-at-large of Mashable; Erico Guizzo, senior editor at IEEE Spectrum; Steve Taub, senior director, advanced manufacturing at GE Ventures; and Devdutt Yellurkar, general partner at CRV.

To view the ten finalist entries, please visit www.rethinkrobotics.com/videos.

Scaling up underwater swarmbot research from tabletop ‘aquarium’ to the Venice Lagoon (CoCoRo Video #50/52)

Thomas Schmickl — Tue, 15 Dec 2015 20:45:39 +0000

CoCoRo’s humble beginnings.

Our underwater swarm research started in a few cubic centimeters of water with some naked electronics on a table. Over the next three and a half years, our swarm increased by a factor of 40, and the size of our test waters increased by a factor of 40 million as we went from aquariums and pools, to ponds, rivers and lakes, and finally ending up in the salt water basin of the Livorno harbour. Quite a stretch for a small project!

Our new project, subCULTron, which extends the work of CoCoRo, will scale up the swarm size to 120+ robots, and will take place in an even larger body of water: the Venice Lagoon.

The Year of CoCoRo Video #49/52: Base stations

Thomas Schmickl — Tue, 08 Dec 2015 20:32:33 +0000

During the past year we have shown many swarm algorithms in various experiments. The spotlight was always on the Lily and the Jeff robots. However, there is now another star in the team and this trailer is dedicated to this special agent: the base station!

The base station was finished towards the end of the project, thus, we had to develop (i.e. hack) many surrogates and placeholders for it over the course of the project. We got so experienced with it that we could quickly hack a surrogate base station from almost anything that was lying around in the lab: styrofoam, cans, boxes … whatever was around and handy. This video shows some of those creations.

A few months before the final review we had the real thing ready: a typical Italian machine (like Italian cars) made by our partners from SSSA (Pontedera). It was fast as hell, highly manoeuvrable, and elegant. The base station has a docking device and can actively manoeuvre, dock and undock robots and carry three attached spare robots with it. With this central masterpiece, we were ready for our final review.

The Year of CoCoRo Video #48/52: Workshops

Thomas Schmickl — Tue, 01 Dec 2015 10:25:53 +0000

Most of the videos from The Year of CoCoRo were shot during workshops we held throughout the project. These workshops, which were usually focussed on one or several specific demonstrators, were what drove our international team of collaborators to implement mechanical hardware, electronics and software into working installations. This form of workshop-driven development proved to be very successful, and by the end of the project we were able to show 17 working final demonstrators that show the versatility of robot swarms.

The Year of CoCoRo Video #47/52: Underwater robots swarm at CEBIT consumer electronics show

Thomas Schmickl — Tue, 24 Nov 2015 17:21:43 +0000

In March 2014, we exhibited CoCoRo in Hannover, Germany at the CEBIT — Europe’s largest consumer electronics fair. At first we thought we might be out of place and that our exhibit would be overshadowed by the latest flatscreen TVs, smartphones and gaming consoles. We were very wrong: though we had the smallest booth, we were overrun with thousands of people throughout the week, and television and radio crews also stopped by for interviews. By our own estimates, we may just have had the highest rate of visitors per square meter in the whole fair.

It’s not easy to bring a swarm of underwater robots and run live experiments at a consumer electronic show, but we gained a lot of motivation from the public interest we felt there. Thanks to our enduring team members and also to all the people who visited us!

Drones light up the sky with animated letters & shapes in award-winning video

Hallie Siegel — Fri, 20 Nov 2015 21:53:13 +0000

Check out this great little film by drone startup PRENAV, which took home the LOL WTF prize at the Flying Robot International Film Festival last night. According to Nathan Schuett, CEO of PRENAV, the team was looking for a way to demonstrate precision drone flight in a visually appealing way. “We decided to try something that had never been done before – drawing accurate shapes, letters and animations in the sky with a drone – and we’re very pleased with how ‘Hello World’ turned out.” Fun stuff.

According to a recent press release,

PRENAV and partner Hawk Aerial today announced that they have been granted the first Section 333 exemptions from the Federal Aviation Administration to operate the PRENAV precision drone system. PRENAV drones are capable of autonomously navigating in complex, cluttered, or GPS-denied environments. The two companies plan to use the system to perform close proximity visual inspections of cell phone towers, wind turbines, bridges, oil tankers, industrial boilers, and other large structures.

If you liked this article, you may also be interested in:

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

New video shows bionic athletes rehearsing for upcoming Cybathlon competition

NCCR Robotics — Thu, 19 Nov 2015 19:44:24 +0000

Credit: ETH Zurich / Alessandro Della Bella

In 21 countries across the globe, hundreds of people are preparing for Cybathlon 2016, where cutting edge robotic assistive technologies will help people with disabilities to compete in a series of races. This summer the Cybathlon practice session took place at the Swiss Arena in Kloten so that the teams could test out the courses. Watch the trailer for the rehearsal games!

Cybathlon 2016 is organised by ETH Zurich and will showcase six disciplines:

BCI Race Functional Electrical Stimulation (FES) Bike Race
Powered Arm Prosthesis Race
Powered Leg Prosthesis Race
Powered Exoskeleton Race
Powered Wheelchair Race

The finals will take place on October 8, 2016.

Find out more at www.cybathlon.com

If you liked this article, you may also be interested in:

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

The Year of CoCoRo Video #46/52: JeffShoaling

Thomas Schmickl — Tue, 17 Nov 2015 16:23:43 +0000

The body shape of Jeff robots is much closer to that of a fish than the Lily robots are. With their slim bodies, Jeff robots can tightly flock together and move in one direction as a group. We implemented a simple blue-light-LED-based algorithm that allows neighboring robots to align to each other. This doesn’t work 100% of the time, but it still works quite often. And when we filmed the little fish that observed our experiments with robots in Livorno harbor (see at beginning of the movie), we observed that the natural fish also did not align 100% of the time. In other words, we came pretty close.

We implemented this code in a very short period of time (hours!) towards the end of the project. With more time and more local neighbor communication, the shoaling can be much improved in future. We hope to be able to further extend this in our follow up project, subCULTron.

Four-legged robot that efficiently handles challenging terrain

ETH Zurich — Fri, 30 Oct 2015 15:13:50 +0000

StarlETH is a multi-purpose legged transporter robot developed at ETH Zurich’s Autonomous Systems Lab. Combining versatility, speed, robustness, and efficiency, StarlETH walks, climbs, and runs over varied terrain.

Precisely controlled elastic actuators allow for temporary energy storage – in fact this robotic system consumes 10 times less power than other hydraulic systems. Weighing in at just 26 kg, it can be handled by a single operator, but operates autonomously at a speed of 2km per hour walking or running. Potential applications for such a highly mobile robot include: inspection of industrial, construction, or polluted environments, search and rescue operations, security, or even the entertainment industry.

Further reading:
http://www.leggedrobotics.ethz.ch/doku.php?id=robots:starleth:starleth
http://www.leggedrobotics.ethz.ch/doku.php?id=robots:scarleth
http://www.leggedrobotics.ethz.ch/lib/exe/fetch.php?media=robots:starleth:description:201401_descriptiontransporter.pdf

If you liked this article, you may also be interested in:

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

Robots in Depth: Melonee Wise on building robots, and robot companies

Per Sjöborg — Tue, 06 Oct 2015 16:37:06 +0000

Robots in Depth is a new video series featuring interviews with researchers, entrepreneurs, VC investors, and policy makers in robotics, hosted by Per Sjöborg. In this interview, Per talks to Melonee Wise, lifelong robot builder and developer, and CEO of Fetch Robotics.

Melonee shares how she first got into building things at a young age and how that led to studying mechanical engineering and leaving her PhD project behind to become the second employee of Willow Garage. She shares some personal anecdotes from the first few years at Willow Garage, including both successes like the PR2 and some less successful moments.

Melonee also gives her perspective on the development phase robotics is in now and what the remaining challenges are. Related to that, she discusses what is feasible to deliver in the next five years vs. what her dream robot would be.

You can support Robots in Depth on Patreon. Check out all the Robots in Depth videos here.

Air and ground robot collaborate to map and safely navigate unknown, changing terrain

Autonomous Systems Lab — Mon, 05 Oct 2015 18:52:44 +0000

This video shows how a robot team can work together to map and navigate toward a goal in an unknown terrain that may change over time. Using an onboard monocular camera, a flying robot first scouts the area, creating both a map of visual features for simultaneous localization and a dense elevation map of the environment. A legged ground robot then localizes itself against the global map, and uses the elevation map to plan a traversable path to a goal.

While following the planned path, the absolute pose corrections are fused with the legged robot’s state estimation and the elevation map is continuously updated with distance measurements from an onboard laser range sensor. This allows the legged robot to safely navigate towards its goal while taking into account any changes in the environment.

More info: http://leggedrobotics.ethz.ch

This work was published as:
P. Fankhauser, M. Bloesch, P. Krüsi, R. Diethelm, M. Wermelinger, T. Schneider, M. Dymczyk, M. Hutter, and R. Siegwart, “Collaborative Navigation for Flying and Walking Robots,” in IEEE International Conference on Intelligent Robots and Systems (IROS), 2016.

Robots in Depth: Gregory Dudek on field robotics

Per Sjöborg — Thu, 24 Sep 2015 19:23:11 +0000

Robots in Depth is a new video series featuring interviews with researchers, entrepreneurs, VC investors, and policy makers in robotics, hosted by Per Sjöborg. In this first episode, Per speaks to Gregory Dudek, Research Director of the McGill Mobile Robotics Lab, about field robotics. They discuss air, surface and underwater vehicles, and review challenges and best practices for using field robots, both individually and as a collaborative team.

Robots in Depth is recorded at different robotics events around the world. You can support Robots in Depth on Patreon.

Interview with Danica Kragic

International Journal of Advanced Robotic Systems (IJARS) — Fri, 18 Sep 2015 01:36:40 +0000

In this wide ranging interview, Danica Kragic, professor at the Royal Institute of Technology (KTH), Sweden, and General Chair of ICRA 2016, discusses the nature of collaborative research, shares her opinions on the robotics projects financed by Horizon2020, speculates on the reasons behind the different research agendas for robotics in the US, the EU and in Asia, and tells us why she chooses to publish her team’s research in open access publications.

Kragic underlines the importance of good organisation when it comes to promoting interdisciplinarity among scientific fields, and incentives to attract students in taking up robotics, and shares her views on why robotics is so often negatively portrayed in the media. Finally, will robots be as intelligent as humans? Watch the latest IJARS video to find out.

Danica Kragic is a Professor at the School of Computer Science and Communication at the Royal Institute of Technology, KTH. She received her MSc in Mechanical Engineering from the Technical University of Rijeka, Croatia, in 1995 and PhD in Computer Science from KTH in 2001. She has been a visiting researcher at Columbia University, Johns Hopkins University and INRIA Rennes. She is the Director of the Centre for Autonomous Systems. Danica received the 2007 IEEE Robotics and Automation Society Early Academic Career Award. She is a member of the Royal Swedish Academy of Sciences and Young Academy of Sweden. She holds a Honorary Doctorate from the Lappeenranta University of Technology. She chaired IEEE RAS Technical Committee on Computer and Robot Vision and served as an IEEE RAS AdCom member. Her research is in the area of robotics, computer vision and machine learning. In 2012, she received an ERC Starting Grant. Her research is supported by the EU, Swedish Foundation for Strategic Research and Swedish Research Council.

Kragic D. IJARS Video Series: Danica Kragic Interview with the International Journal of Advanced Robotic Systems [online video]. International Journal of Advanced Robotic Systems, 2015, 12:V7. DOI: 10.5772/61490

The Year of CoCoRo Video #36/52: Relay swarm

Thomas Schmickl — Tue, 08 Sep 2015 21:20:31 +0000

The EU-funded Collective Cognitive Robotics (CoCoRo) project has built a swarm of 41 autonomous underwater vehicles (AVs) that show collective cognition. Throughout 2015 – The Year of CoCoRo – we’ll be uploading a new weekly video detailing the latest stage in its development. Over the last four posts we demonstrated how the robots use a relay chain to communicate between the sea ground and the surface station. The following two videos show an alternative to this communication principle. The “relay swarm” scenario uses a swarm of Lily robots performing random walks in 3D for transmitting information about the status of the search swarm of Jeff robots on the ground.

This first video explains the scenario in a computer animation:

The second video shows the real-world experiments performed in the “relay swarm” scenario. First Jeff robots search the ground of a fragmented habitat for a magnetic target. As soon as it finds the target it signals this locally with blue-light LEDs. Lily robots that also roam the habitat can pick up the signal from this Jeff robot. The info can also spread from Lily robot to Lily robot as they meet, spreading like an infectious process. Finally, Lily robots inform the surface station that the Jeff robot on the ground has found an interesting target. Future extensions foresee that after informing the surface station another phase starts: a second signal spreads from the surface station through the Lily robots back to the Jeff robot on the ground, and ultimately makes the Jeff robot to go up to the surface above the found target.

The Year of CoCoRo Video #35/52: Relay chain communication

Thomas Schmickl — Tue, 01 Sep 2015 21:05:03 +0000

At one of these places we trigger a special RF (radio frequency) pulse to be emitted by a robot. Neighboring robots that receive this pulse send out a similar pulse, relaying the signal along the chain. To control the directionality of the spreading signal, there is also a refractory period after each relaying act in which the robot is unreceptive for the relayed signal. This system is inspired by slime mold amoebas and giant honeybees and serves very well for the underwater communication purpose.

The Year of the CoCoRo Video #20/52: Autonomous docking with Jeff robots

Thomas Schmickl — Fri, 22 May 2015 13:47:03 +0000

For the sake of achieving long-term energy autonomy with our CoCoRo system, we constructed a docking/undocking mechanism for Jeff robots on our surface station. This functionality was first tested with a fixed mounted docking device, and then with a docking device floating around in our pool. The autonomous docking worked exceptionally well under all conditions.

To learn more about the project, see this introductory post, or check out all the videos from the Year of CoCoRo on Robohub.

The Year of the CoCoRo Video #19/52: Electric confinement in the harbour

Thomas Schmickl — Wed, 20 May 2015 14:15:29 +0000

The EU-funded Collective Cognitive Robotics (CoCoRo) project has built a swarm of 41 autonomous underwater vehicles (AUVs) that show collective cognition. Throughout 2015 – The Year of CoCoRo – we will be uploading a new weekly video detailing the latest stage in its development. This video shows how we used an electric underwater field in Livorno harbour to field test confining the robots to a specific area around the base station so that they don’t get lost.

After having tested the electric-field confinement of the Jeff robots to the base station in our pool, we went out to Livorno harbour to test it under out-of-the-lab conditions. Although our CoCoRo prototype robots were not designed to operate in salty ocean water — there is a significantly different electrical conductivity compared to freshwater — the electrical confinement worked there quite well.

To learn more about the project, see this introductory post, or check out all the videos from the Year of CoCoRo on Robohub.

Multiple tethered quadrotors performing high-g, high-speed formation maneuvers

Robohub Editors — Tue, 05 May 2015 18:46:56 +0000

This video shows tethered quadrocopters flying steadily together at high speeds exceeding 50 km/h in a confined space. With the tether exerting more than 13 gs of centripetal force, multiple quadrotors are able to fly 1.7m- radius circular trajectories in formation across different orientations in space and then successfully perform a coordinated braking maneuver.

The testbed allows the quadrocopter’s high speed flight behavior to be characterized in order to determine drag characteristics, propeller efficiency, and the physical limits of the machine. It is also being used to safely develop high-speed maneuvers such as emergency braking.

Note that it is possible to remove the central pole by balancing the forces acting on the strings; this could be then used in performance settings, possibly enhanced by light and sound effects.

This research was conducted at the Flying Machine Arena at ETH Zurich.

Reference:

Maximilian Schulz, Federico Augugliaro, Robin Ritz, Raffaello D’Andrea , “High-speed, Steady Flight with a Quadrocopter in a Confined Environment Using a Tether “, IROS 2015, submitted.

If you liked this article, you may also be interested in:

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

The Year of the CoCoRo Video #18/52: Confining Jeff robots with an electric field

Thomas Schmickl — Mon, 04 May 2015 14:22:59 +0000

The EU-funded Collective Cognitive Robotics (CoCoRo) project has built a swarm of 41 autonomous underwater vehicles (AUVs) that show collective cognition. Throughout 2015 – The Year of CoCoRo – we will be uploading a new weekly video detailing the latest stage in its development. This video shows how we used an electric underwater field to confine the robots of a specific area around the base station so that they don’t get lost.

We use a submerged electrode below the CoCoRo surface station to generate a pulsing electric field underwater around this station. The Jeff robots have electrodes on their outer hull to be able to sense such fields. This way we can confine the robots into a specific area (volume) around the base station. This is important to keep the swarm together in the water, otherwise robots can get lost. We first tested this system in a pool, as it is shown in this video here.

To learn more about the project, see this introductory post, or check out all the videos from the Year of CoCoRo on Robohub.

The Year of CoCoRo Video #17/52: Lily confinement by bluelight

Thomas Schmickl — Thu, 30 Apr 2015 16:19:10 +0000

The EU-funded Collective Cognitive Robotics (CoCoRo) project has built a swarm of 41 autonomous underwater vehicles (AUVs) that show collective cognition. Throughout 2015 – The Year of CoCoRo – we will be uploading a new weekly video detailing the latest stage in its development. In this video we use blue-light blinks to keep the swarm together and to keep it in vicinity of the moving base station.

Due to this “confinement”, the radio-controlled base-station can pull a whole swarm of Lily robots like a tail behind itself. It is important to confine the robots into specific areas in larger water bodies because the swarm requires normally a minimum connectivity among agents to work efficiently, which is achieved only with a critical minimum swarm density. Without keeping the robots in a controlled area, robots could get lost and the robot density could fall below the critical density. Thus, confinement was identified to be a critical functionality.

To learn more about the project, see this introductory post, or check out all the videos from the Year of CoCoRo on Robohub.

CoCoRo: New video series tracks dev’t of collective behaviour in autonomous underwater swarm

Thomas Schmickl — Tue, 28 Apr 2015 20:41:22 +0000

The EU-funded Collective Cognitive Robotics (CoCoRo) project comprises the largest autonomous underwater swarm in the world. Following three-and-a-half years of intensive research, CoCoRo’s interdisciplinary team of scientists from universities in Austria, Italy, Germany, Belgium, and the UK built a swarm of 41 autonomous underwater vehicles (AUVs) that show collective cognition. Swarm members are not only aware of their own surroundings, but also of their own and other vehicles’ experiences. Throughout 2015 – The Year of CoCoRo – the research team will be uploading a new weekly video detailing a new stage in its development and reporting updates here on Robohub. Check out the first ten videos below!

Overview of the CoCoRo system

The swarm consists of Jeff robots (the highlight of the project), 20 smaller (and slower) Lily robots, as well as a base station at the surface. The setting is shown in a short overview video.

In this simple form of collective self-awareness, the swarm processes information collectively, such that, as a whole it knows more than any single swarm member. The swarm not only collects information about the environment, but also about its own state. As well as staying together as a swarm, it’s also capable of navigating and diving, searching for sunken targets and communicating and processing information as a group.

Research highlights

The swarm communicates findings via a self-established bridge to the “world above”

Not only can the swarm interact with itself, it can also communicate its findings and inner state to the world above. It does this by establishing, self-maintaining and even repairing a bridge between the swarm, located on the sea bed, and a human-controlled floating station that is located on the water’s surface.

During the project, many algorithms were developed and tested with the CoCoRo prototype swarm. Future applications include environmental monitoring and oceanic search missions.

Three-layer decentralized swarm design

When designing the swarm, the scientists decided to follow the KISS principle — Keep it Simple and Stupid. A decentralized approach was chosen for the CoCoRo project because in a swarm there is no single point of failure. Swarms are robust, flexible and scalable systems that can adapt easily to changing environments. Additionally, the technical and cost requirements for a single robot are less than in non-swarm systems.

Three different layers were implemented for the cognition: individual, group and global. Single AUVs collect information, local groups share and compare it and, finally, the whole swarm makes collective decisions.

Bio-inspired algorithms build core functions

While designing the software, the scientists decided to focus on bio-inspired algorithms because they are known to be very flexible and robust. The focal animals were slime mold, fireflies, honeybees, cockroaches or fish. The algorithms were programmed in a modular way; self-organizing cognition algorithms were merged with self-organizing motion algorithms that were inspired by various animals. In this way, totally new algorithms emerged.

Three types of AUVs communicate via a novel multichannel underwater network

A swarm of 41 prototype AUVs was built for the CoCoRo project, consisting of three different types of AUVs that range in size from a human hand to a man’s foot. Depending on their activity, the robots run from two to six hours without required a charge. A unique feature of the CoCoRo project is that sensors were implemented in a combination never used before in underwater robotics. These combinations were necessary to allow the construction of a autonomous underwater swarm that can coordinate mainly through simple signalling between nearest neighbors. In this way, a totally new heterogeneous underwater swarm system was created, consisting of three different types of AUVs: “Jeff” robots that search the sea bed; a base station on the water’s surface (connected to humans); and “Lilly” robots that bridge and communicate information between the Jeff robots and the base station.

Check out our other videos below!

Introducing Jeff

The Jeff robots are extremely agile and can resist water currents of 1m/sec. They have autonomous buoyancy control, lateral and vertical motion with optimized propellers and a rich set of sensors. For all these functions, novel energy-saving methods were implemented that guarantee autonomy and durability.

Jeff in turbulent waters

Jeff’s body shape and actuation also allows it to operate in turbulent waters, as is tested in the following video with a remote-controlled Jeff. In this video it was purposely driven into the most turbulent areas to see how it would be affected by the water currents.

Feeding Jeff with magnets

Even in turbulent water, Jeff can be controlled with enough precision to reach a specific point in 3D space. This is demonstrated by holding a small magnet in the water for Jeff to pick up.

The Jeff swarm explores its habitat

The researchers have produced 20 Jeff robots, able to swarm out and search complex habitats in parallel, as shown in the following video.

Collective search by Jeff and Lily Robots

An important aspect of the project is that all three types of robots help each other in the performance of their collective task. To achieve this, the scientists took inspiration from nature and combined several algorithms to generate a new collective program for the whole swarm. An example of this is their collective search for a magnetic (metallic) target on the sea ground, shown in a pool-based scenario. In this setting, a target is marked by a metal plate and some magnets. Several blocking objects, surrogates for debris and rocks, produce a structured habitat. The Jeff robots, on the ground, first have to spot the target by doing a search and observing their magnetic sense. After the first robot finds the target, it attracts others through the use of blue-light signals. The aggregation of Jeff robots then summons a swarm of Lily robots at higher water levels, which serve to pinpoint the site to humans.

Swarm-size awareness exhibited by Lily robots

It’s important for a swarm of robots to know its own size. In CoCoRo, this was achieved by a novel algorithm inspired by slime mold amoebas; in this case, however, the chemical signals amoebas exchange were substituted in the algorithm for blue-light blinks. These are transmitted by the robots to their neighbors and propagated to other robots in a wave-like manner. This behavior was first tested on the smaller Lily robots.

Swarm-size awareness exhibited by Jeff robots

After the algorithm was successfully tested on Lily robots, it was further polished to improve its reaction speed and prediction quality before it was implemented in Jeff robots, as shown by the following video.

Flocking by slime mold

The slime mold inspired algorithm doesn’t just allow the robots to know the size of the swarm. Combined with directed motion, it can also be used to generate slime mold-like flocks of underwater robots.

Emergent taxis of robots

After adding an additional environmental light sensor, this bio-mimicking collective behavior is turned into something the scientists call “emergent taxis.” When the entire swarm of robots run uphill in a light gradient, although individual members can’t read it (having only a very rough sensor impression of the local area), the swarm turns into a kind of moving compound eye, with all the robots observing their local environmental and influencing each other. Finally, an algorithm designed for counting swarm members transforms it into an acting organ, what might even be called a “super-organism”.

Outlook

The CoCoRo project developed and tested a whole set of “enabling technologies”, mostly in pools but sometimes in out-of-lab conditions. When the project ended in late 2014, it was clear to the research team that these technologies should be further developed and brought out of the lab. As a next step in their long-term roadmap, the research team (with additional partners) started a new project called “subCULTron” to develop the next generation of swarm robots and apply them in areas of high impact: fish and mussel farms and the Venice lagoon.

New footage of CoCoRo available on YouTube each week

During the runtime of CoCoRo, the swarm developed an enormous variety of functionalities, which were presented in several demonstrators at the project’s final review. A lot of footage was recorded and many videos were produced. These films not only give a deep insight into the different features of the CoCoRo swarm as it evolved, but also provide a behind-the-scenes glimpse into the scientific work and development that went into the project. The CoCoRo team will be uploading a new video on YouTube each week until the end of the year to celebrate the “The Year of CoCoRo” – stay tuned on Robohub for regular updates.

Links

CoCoRo Homepage
CoCoRo on Youtube
CoCoRo on Facebook

If you liked this article, you may also be interested in:

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

The Year of CoCoRo Video #16/52: JeffCam in a lake

Thomas Schmickl — Sun, 19 Apr 2015 22:25:32 +0000

Jeff is much more agile and powerful then Lily. So mounting a camera ontop of an autonomous Jeff robot produced an even better autonomous camera agent. After some preliminary tests and tuning in a pool, we went to an Italian lake to see how it looks down there below the surface.

To learn more about the project, see this introductory post, or check out all the videos from the Year of CoCoRo on Robohub.

The Year of CoCoRo Video #15/52: TRAILER LilyCam in a wild river

Thomas Schmickl — Sun, 12 Apr 2015 18:33:47 +0000

Austria is home not only to beautiful lakes, it also has wild rivers and creeks. After “Lily-Cam” did its job in the lakes, we threw it also into a fast whitewater river. We were lucky to catch it downriver after some minutes and the robot survived this adventure. However, our engineers, who have also to constantly maintain and repair the robots, didn’t like the movie. ;-)

To learn more about the project, see this introductory post, or check out all the videos from the Year of CoCoRo on Robohub.

When is an ice cube not an ice cube?

Frank Tobe — Mon, 06 Apr 2015 19:14:00 +0000

Japanese advertising agency wins award for Suntory Whisky ad campaign using CNC-milled ice cubes and a 3D printing app from Autodesk.

In 2014, Tokyo-based advertising agency TBWAHAKUHODO created an ad for Suntory Whisky that included the most gorgeous ice cubes you’ll ever see. The ad won six awards at this year’s Asia Pacific Ad Festival (AdFest) in Thailand.

The ice cubes were created from a block of ice using a CNC router to create ice sculptures. Basically this is an inverse 3D printing technique. The CNC router required chilling to -7 degrees Celsius to prevent the ice from melting. The creation of these ice sculptures is more like 3D milling than 3D printing. Rather than building up an object additively, the 3D mill shaves the ice away to create the desired shape. Like a 3D printer, the 3D mill is connected to a computer and uses a 3D-printing app from Autodesk, Autodesk 123D.

Is nothing sacred!

The Year of CoCoRo Video #14/52: LilyCam in a Lake

Thomas Schmickl — Sun, 05 Apr 2015 13:31:18 +0000

After our successful application of “Lily-Cam” in our small ponds, we went further. At several lovely places at Styria (Austria) we took a look below the water surface and encountered beautiful and pittoresque landscapes, fish and even diving ducks.

To learn more about the project, see this introductory post, or check out all the videos from the Year of CoCoRo on Robohub.

Peter Asaro: Challenges and approaches to developing policy for robots

CIS Blog — Thu, 02 Apr 2015 11:30:30 +0000

As part of the Center for Information Technology Policy (CIPT) Luncheon speaker series, Peter Asaro gives a talk on developing policy for robots.

Robotics stands on the cusp of an explosion of applications and wide-spread adoption. Already the development and popular use of small UAV drones is gaining momentum, self-driving cars could be market-ready in a few short years, and the next generation of fully-autonomous military drones are in development. Yet the regulatory policies necessary to ensure the social and economic benefits of these technologies are not yet in place. The FAA has struggled to devise operational regulations for small UAV drones, and has not yet addressed the privacy concerns they raise. Google has influenced state legislatures to pass laws permitting self-driving cars, yet the liability issues and insurance regulations are open questions, as are the safety requirements for these cars to interact with human drivers. And while the United Nations has begun discussions over the possible need to regulate fully autonomous weapons, the development of such systems continues at rapid pace. I will present my work on some of these issues, as well as ask whether a more comprehensive regulatory framework might be able to address the questions of ensuring public safety and privacy in the coming revolution in robotics.

Deep Learning Primer

Frank Tobe — Thu, 02 Apr 2015 11:28:00 +0000

3D brain scans analysis by applying Deep Learning algorithms – photo : Scyfer

The technology that unlocks intelligence from big data – deep learning – is explained in this video by Max Welling, a professor at the University of Amsterdam, and a founder of the Dutch deep learning startup Scyfer.

Even though I have a software and systems background in demographic data, this short video was a necessary and easily understood primer in this new science of deep learning.

Quadrotor automatically recovers from failure or aggressive launch, without GPS

Matthias Fässler — Mon, 30 Mar 2015 17:59:13 +0000

Photo credit: Robotics & Perception Group, University of Zurich.

When a drone flies close to a building, it can temporarily lose its GPS signal and position information, possibly leading to a crash. To ensure safety, a fall-back system is needed to help the quadrotor regain stable flight as soon as possible. We developed a new technology that allows a quadrotor to automatically recover and stabilize from any initial condition without relying on external infrastructure like GPS. The technology allows the quadrotor system to be used safely both indoors and out, to recover stable flight after a GPS loss or system failure. And because the recovery is so quick, it even works to recover flight after an aggressive throw, allowing you to launch a quadrotor simply by tossing it in the air like a baseball.

How it works

Photo credit: Robotics & Perception Group, University of Zurich.

Our quadrotor is equipped with a single camera, an inertial measurement unit, and a distance sensor (Teraranger One). The stabilization system of the quadrotor emulates the visual system and the sense of balance within humans. As soon as a toss or a failure situation is detected, our computer-vision software analyses the images for distinctive landmarks in the environment, and uses these to restore balance.

All the image processing and control runs on a smartphone processor on board the drone. The onboard sensing and computation renders the drone safe and able to fly unaided. This allows the drone to fulfil its mission without any communication or interaction with the operator.

The recovery procedure consists of multiple stages. First, the quadrotor stabilizes its attitude and altitude, and then it re-initializes its visual state-estimation pipeline before stabilizing fully autonomously. To experimentally demonstrate the performance of our system, in the video we aggressively throw the quadrotor in the air by hand and have it recover and stabilize all by itself. We chose this example as it simulates conditions similar to failure recovery during aggressive flight. Our system was able to recover successfully in several hundred throws in both indoor and outdoor environments.

More info: Robotics and Perception Group, University of Zurich.

References

M. Faessler, F. Fontana, C. Forster, D. Scaramuzza. Automatic Re-Initialization and Failure Recovery for Aggressive Flight with a Monocular Vision-Based Quadrotor. IEEE International Conference on Robotics and Automation (ICRA), Seattle, 2015.

M. Faessler, F. Fontana, C. Forster, E. Mueggler, M. Pizzoli, D. Scaramuzza. Autonomous, Vision-based Flight and Live Dense 3D Mapping with a Quadrotor Micro Aerial Vehicle. Journal of Field Robotics, 2015.

If you liked this article, you may also be interested in:

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

The Year of CoCoRo Video #13/52: Lilycam in nature

Thomas Schmickl — Sun, 29 Mar 2015 18:42:32 +0000

Lily is an autonomously diving robot. After we attached an underwater camera onto it, it became an autonomously driving camera agent. We used this “Lily-Cam” to look into the little fishing ponds that we have at our Zoological Department. The look below the surface offered a fascinating glimpse of the underwater world, including algae forests, fish and other water organisms.

To learn more about the project, see this introductory post, or check out all the videos

The Year of CoCoRo Video#12/52: Fun with Jeff in the pool

Thomas Schmickl — Sun, 22 Mar 2015 23:02:36 +0000

The EU-funded Collective Cognitive Robotics (CoCoRo) project has built a swarm of 41 autonomous underwater vehicles (AUVs) that show collective cognition. Throughout 2015 – The Year of CoCoRo – we will be uploading a new weekly video detailing the latest stage in its development. One day in early 2014, at one of those long workshops, we stayed at a hotel that had a large and deep outside pool. It was a nice day in Italy, so what else could we do than taking a JEFF robot in autonomous driving mode to this pool and have some fun with it?

It didn’t take long and more and more hotel guests gathered and watched. Special applause to Vega and Finn, the kids of the project coordinator, for helping with the filming (above and under the water), catching the robot and rescuing it sometimes from the ground after we pushed the robot beyond its limits.

To learn more about the project, see this introductory post, or check out all the videos from the Year of CoCoRo on Robohub.

The Year of CoCoRo Video #11/52: Out of the lab in Livorno

Thomas Schmickl — Sun, 15 Mar 2015 12:57:11 +0000

The EU-funded Collective Cognitive Robotics (CoCoRo) project has built a swarm of 41 autonomous underwater vehicles (AUVs) that show collective cognition. Throughout 2015 – The Year of CoCoRo – we will be uploading a new weekly video detailing the latest stage in its development.This video summarizes all out-of-the-lab activities in which we tested our robots (Lily and Jeff).

There will be more detailed videos following throughout this year showing some of those activities more specifically. The activities shown here show autonomous robots in larger outdoor pools, ponds, lakes, rivers and ocean harbours. They act there either alone (e.g. as autonomous underwater camera agents) or in smaller groups (swarms).

To learn more about the project, see this introductory post, or check out all the videos from the Year of CoCoRo on Robohub.

The Year of CoCoRo Video #10/52: Feeding Jeff with magnets

Thomas Schmickl — Sun, 08 Mar 2015 17:25:15 +0000

The EU-funded Collective Cognitive Robotics (CoCoRo) project has built a swarm of 41 autonomous underwater vehicles (AUVs) that show collective cognition. Throughout 2015 – The Year of CoCoRo – we will be uploading a new weekly video detailing the latest stage in its development. In this video we test Jeff’s ability to pick up a target (the magnet) while swimming in a current.

In this video we again generate water currents and turbulences by using a water hose in our outdoor pool. By radio-frequency control we navigate a Jeff robot remotely in those currents. To test the precision of the steering under these conditions we use some small magnets in our hands as targets that have to be picked up by the Jeff robot. Thus it looks like we feed the robot with magnets :-)

To learn more about the project, see this introductory post, or check out all the videos from the Year of CoCoRo on Robohub.

The Year of CoCoRo Video #09/52: Jeff in the water current

Thomas Schmickl — Sun, 01 Mar 2015 18:03:37 +0000

The EU-funded Collective Cognitive Robotics (CoCoRo) project has built a swarm of 41 autonomous underwater vehicles (AUVs) that show collective cognition. Throughout 2015 – The Year of CoCoRo – we will be uploading a new weekly video detailing the latest stage in its development. In this video we generate some water currents and turbulences by using a water hose in our outdoor pool.

The video shows our first tests of the Jeff robot performed under such conditions (performed in summer 2013 and spring 2014). Those tests clearly indicated that the maneuverability of the robot (steering, forward drive) is strong enough to compensate for currents and drifts up to approximately 1m/sec. In those days we were very happy to realize such impressive capabilities for such a small robot, as this maneuverability is a prerequisite for the good performance in an underwater swarm under out-of-the lab conditions (large outside tanks, lazy river arms, ponds, lakes).

To learn more about the project, see this introductory post, or check out all the videos from the Year of CoCoRo on Robohub.

Livestream: Rodney Brooks, Abhinav Gupta, Andrew McAfee on AI and the rise of robots

Robohub Editors — Fri, 27 Feb 2015 16:10:51 +0000

Livestream of the Council of Foreign Relations’ Malcolm and Carolyn Wiener Annual Lecture on Science and Technology starting 02/27/2015 at 12:45 EST.

The Malcolm and Carolyn Wiener Annual Lecture on Science and Technology addresses issues at the intersection of science, technology, and foreign policy. In this lecture, experts discuss artificial intelligence and robot technology, and their economic impact on industry and society over the next decade.

Speakers:

Rodney Brooks, Panasonic Professor of Robotics (Emeritus), Computer Science and Artificial Intelligence Lab, Massachusetts Institute of Technology; Founder, Chairman, and Chief Technology Officer, Rethink Robotics
Abhinav Gupta, Assistant Research Professor, Robotics Institute, Carnegie Mellon University
Andrew McAfee, Principal Research Scientist and Cofounder, Initiative on the Digital Economy, Sloan School of Management, Massachusetts Institute of Technology

Presider:

Nicholas Thompson, Editor, NewYorker.com

The Year of the CoCoRo Video #08/52: Lily emergent taxis

Thomas Schmickl — Sun, 22 Feb 2015 23:09:13 +0000

The EU-funded Collective Cognitive Robotics (CoCoRo) project has built a swarm of 41 autonomous underwater vehicles (AUVs) that show collective cognition. Throughout 2015 – The Year of CoCoRo – we will be uploading a new weekly video detailing the latest stage in its development. This video shows how a swarm of Lily robots can form a coherent group by exchanging light pulses among the group members, similar to how slime-mold does in biology.

By modulating the frequency of these signals the group can alter the path of the emerging blinking wave to turn the whole group towards the aggregation target. Such a target can be any form of gradient emitting source, regardless of the type of the emitted signal. We demonstrate this here by using a light source as a target.

To learn more about the project, see this introductory post, or check out all the videos from the Year of CoCoRo on Robohub.

Sensory-motor tissues for soft robots

NCCR Robotics — Wed, 18 Feb 2015 18:03:52 +0000

Sensory-Motor Tissues for Soft Robots

In this video, PhD student at LIS, EPFL and NCCR Robotics Jun Shintake explains his project “Sensory-Motor tissues for Soft Robots”.

For more information on this project please see:

The project’s website

New soft antagonistic actuator enables robots to fold

A foldable antagonistic actuator (academic paper)

Variable stiffness material based on rigid low-melting-point-alloy microstructures embedded in soft poly(dimethylsiloxane) (PDMS) (academic paper)

Ground-flight collaboration

NCCR Robotics — Mon, 16 Feb 2015 14:50:21 +0000

Ground-Air collaboration between robots (Photo: RPG and Alain Herzog).

Working in the field of rescue robotics, the Robotics Perception Group (UZH and NCCR Robotics) works on how to get air robots communicating with ground robots, with the aim of exploiting the strengths of each by working in a team. In the video below, student Elias Müggler explains how he is doing this.

For further information:

Robotics Perception Group website

Aerial-guided Navigation of a Ground Robot among Movable Obstacles (paper by Elias Müggler)

Autonomous flying robots – Davide Scaramuzza at TedxZurich:

Demonstration of the project, winning the Kuka innovation award 2014:

The Year of CoCoRo Video #07/52: Lily flocking by slimemold

Thomas Schmickl — Sun, 15 Feb 2015 19:59:11 +0000

The EU-funded Collective Cognitive Robotics (CoCoRo) project has built a swarm of 41 autonomous underwater vehicles (AUVs) that show collective cognition. Throughout 2015 – The Year of CoCoRo – we will be uploading a new weekly video detailing the latest stage in its development. This video shows how signal waves can be used to keep a swarm of Lily robots together as a group.

A group of Lily robots can achieve a coherent shoaling or flocking configuration by emitting and receiving pulsed light signals. Similar to slime mold or fireflies, such pulsed signals are relayed from one agent to the next, forming signal waves that move through the whole swarm. We use such waves to keep the swarm of Lily robots together as a group, to coordinate the swarm and to move it in a desired direction.

To learn more about the project, see this introductory post, or check out all the videos from the Year of CoCoRo on Robohub.

Pleurobot: Multimodal locomotion in a bioinspired robot

NCCR Robotics — Fri, 13 Feb 2015 04:56:04 +0000

The Pleurobot (Photo: Hillary Sanctuary & BioRob).

The Pleurobot is a bioinspired robot being developed by the BioRob at EPFL and NCCR Robotics. Taking it’s cues from the salamander, the Pleurobot is a walking robot that can change its gait to help it to navigate uneven terrain, and is currently learning to swim. Watch the video to see the researchers discuss what they are doing with the Pleurobot and how they hope to improve it in future.

For further information on the Pleurobot please see:

The project’s homepage

Introducing Pleurobot (video)

Introducing Spot, a new smaller 4-legged robot from Boston Dynamics

Ioannis K. Erripis — Tue, 10 Feb 2015 00:11:35 +0000

Boston Dynamics just released a video of a new four legged robot named “Spot”. It is an evolution along the lines of their previous four-legged robots like BigDog and Wildcat, but this one is much smaller and lighter (160lbs / 72.5kg). As usual not many details are known, but Spot is electrically powered (others had an internal combustion engine onboard) and has a prominent rotating LIDAR on top.

Spot can perform the usual Boston Dynamics trick: it can withstand a kick without tipping over in an eerie life-like manner; and it can also move slowly and accurately indoors while being able to run faster if necessary.

You can watch the video below and you can read other Boston Dynamics articles here.

Video: A day in the life of BeatBots’ Marek Michalowski

ConnectEd Studios — Mon, 09 Feb 2015 20:23:41 +0000

At ConnectEd Studios we had the pleasure of visiting the workshop of Marek Michalowski, a co-founder of BeatBots. BeatBots is the robotic design studio behind the Keepon, and creates dynamic robotic characters for therapy, research, education, and entertainment.

We interviewed Michalowski about his career in an effort to inspire and educate high school students about careers in robotics. Enjoy!

The Year of CoCoRo Video #06/52: Jeff swarm size measurement

Thomas Schmickl — Sun, 08 Feb 2015 18:09:36 +0000

It is important for our robot swarm that the swarm as a whole is aware of its size. We use a bio-inspired method, called the „fireslime algorithm“ to achieve this form of collective awareness. The algorithm makes the robots to spread a one-bit signal (pulse) among the swarm members allowing them to make quite reliable and precise estimates of the size of their swarm. This video shows an advanced version of the algorithm implemented on Jeff robots.

To learn more about the project, see this introductory post, or check out all the videos from the Year of CoCoRo on Robohub.

The Year of CoCoRo Video #05/52: Lily swarm size awareness

Thomas Schmickl — Sun, 08 Feb 2015 18:08:54 +0000

Lily robots build swarms that change in size over time. By using a bio-inspired method of signal exchange these swarms can make reliable estimates of their own swarm size. Our Lily robots emit a pulsed signal that is relayed by other Lily robots in the swarm, just like slime mold amoebas or fireflies relay their signals in nature. Based on this simple signal exchange every member can estimate the number of other swarm members around it.

To learn more about the project, see this introductory post, or check out all the videos from the Year of CoCoRo on Robohub.

The Year of CoCoRo Video #04/52: Aggregation parcour

Thomas Schmickl — Sun, 25 Jan 2015 21:59:09 +0000

The EU-funded Collective Cognitive Robotics (CoCoRo) project has built a swarm of 41 autonomous underwater vehicles (AUVs) that show collective cognition. Throughout 2015 – The Year of CoCoRo – we will be uploading a new weekly video detailing the latest stage in its development. This video shows how, in a complex underwater habitat, a swarm of Jeff robots searches for a magnetic target and then the communicate to Lily robots at smaller depths to join the group.

To learn more about the project, see this introductory post, or check out all the videos from the Year of CoCoRo on Robohub.

The Year of CoCoRo Video #03/52: Jeff robots explore

Thomas Schmickl — Sun, 18 Jan 2015 15:32:24 +0000

They use their front blue-light sensors to detect and avoid obstacles.

To learn more about the project, see this introductory post, or check out all the videos from the Year of CoCoRo on Robohub.

The Year of CoCoRo Video #02/52: Overview of largest swarm

Thomas Schmickl — Sun, 11 Jan 2015 22:03:33 +0000

The EU-funded Collective Cognitive Robotics (CoCoRo) project has built a swarm of 41 autonomous underwater vehicles (AUVs) that show collective cognition. Throughout 2015 – The Year of CoCoRo – we will be uploading a new weekly video detailing the latest stage in its development.The CoCoRo system is currently the largest autonomous underwater swarm in the world. This video briefly shows some of its components and functions.

To learn more about the project, see this introductory post, or check out all the videos from the Year of CoCoRo on Robohub.

The Year of CoCoRo Video #01/52: Overview of the Jeff robot

Thomas Schmickl — Sun, 04 Jan 2015 23:04:03 +0000

The EU-funded Collective Cognitive Robotics (CoCoRo) project has built a swarm of 41 autonomous underwater vehicles (AUVs) that show collective cognition. Throughout 2015 – The Year of CoCoRo – we will be uploading a new weekly video detailing the latest stage in its development. Our CoCoRo system consists of 3 types of robots. One is Jeff, a very fast and agile small autonomous swarm robot. This is an overview of its capabilities.

To learn more about the project, see this introductory post, or check out all the videos from the Year of CoCoRo on Robohub.

Holiday robot video 2014: Robot Drive-In Movies

Robohub Editors — Mon, 22 Dec 2014 19:31:14 +0000

From Penny and Harry at Robot Drive-In Movies:

Seasons Greetings, We have been watching your xmas robot videos – they are great! Ours features Ozobot, a small line-sensing robot being sold as a game piece. To us, he is an actor! In this case, Santa!

Have a holiday robot video of your own that you’d like to share? Send your submissions to info [at] robohub.org!