In this episode, Audrow Nash speaks to several robotics companies at the company showcase at RoboBusiness 2014, which took place in Boston, Massachusetts.
The following is an ordered list of the people interviewed.
- Norm Domholt (1m 40s), CEO of NPC Robotics, talks about their modular remote operate vehicle Black Dog.
- Annemarie Laudanski (6m 20s), Lead Field Applications Engineer at Xsens, demos their inertial motion capture system.
- Carl Vause (9m 14s), CEO of Soft Robotics, speaks about the capability of the soft robotic manipulators, which can be used to pick fruit, among other applications.
- Konrad Fagertun (13m 56s), COO of NLinks, tells about their new robot which drills holes in ceilings – a laborious and difficult task for humans.
- Asim Ikram (15m 51s), CEO of Neo Robotics, discusses the market for robots in the Gulf Cooperation Council region.
- Harri Valpola (21m 40s), Head of Technology at Zen Robotics, talks about the companies waste sorting robotic system.
- Dick Zhang (26m 15s), CEO of Identified Technology, speaks about their self-piloting aerial drone systems for automated energy, mining, and construction site monitoring, surveying, and mapping.
Norm Domholt (1m 40s), CEO of NPC Robotics:
Audrow Nash: Hi, can you introduce yourself and your company?
Norm Domholt: Yes, thank you. My name is Norm Domholt and I’m president of NPC Robotics. Today, at the show, we’re featuring and debuting our latest invention. We’ve been working on it for three years and it’s called the Black Dog.
Audrow Nash: Now, you have the Black Dog here. Can you describe it?
Norm Domholt: Black Dog is a remote control mobile platform. It’s designed modularly, so that it can be repaired in the field without probing with any sort of instruments and with the use of one particular tool – a quarter inch hex wrench. All the parts can be taken apart and replaced in minutes.
Audrow Nash: Can you tell me a bit more about how it’s modular?
Norm Domholt: We realized, through our experience with Battle Box, that the teams that seemed to win were the teams that designed their robots to be repaired quickly and without the need to take apart wiring.
It’s something that can be plugged in and replaced quickly. So, we decided that there should be around eight components in here that can be replaced with the use of this one tool and they should all be modular. There are no internal wires that you have to worry about, so everything unplugs and plugs together very quickly.
Audrow Nash: So it’s a trunk-treaded robot that has two motors driving everything and it’s three feet long, a foot tall and two feet wide?
Norm Domholt: Yes, 42 inches long, 22 inches wide and 12 inches tall. It weighs 200 pounds and it goes four miles an hour. It’s got a lot of torque. Each motor is two-and-a-half horsepower – that’s a 24volt lithium battery.
Audrow Nash: Can you give me some examples of how it could be fitted with different components in the field?
Norm Domholt: Yes. Let’s say a SWAT team buys our robot power base; there are many different applications and mission-specific needs that they could have throughout a day. For example, they go to a house with something suspicious going on inside. They can put a telescoping camera, called RibbonLift, on the robot, within – say – ten seconds. They can then maneuver it to the building from a safe distance. If they hear shots fired and see there’s no need for the camera, they can pull the robot back within seconds, take their camera off and put a 300 pound bullet-proof shield on instead. Then, a SWAT person could operate this with a thumb throttle, while crouching behind the shield, and approach the house from a safe position. He can direct it to come back and hurl a teargas canister through the window. It could be adapted to any particular use very quickly.
Audrow Nash: Very good, and can you tell me at what stage of production your company is?
Norm Domholt: We’re debuting this today. We were hoping it would be a little further along and we could operate it. Some of the electronics are not completed yet; the mechanics are almost done and the modularity is complete. The technology that’s going in is already in place and, in another two months, we’ll be testing at facilities – breaking down doors, going through hallways, up and down stairs. We’ll be testing to see how far – wirelessly – this thing can go into a building.
Audrow Nash: Who would be interested in this product?
Norm Domholt: The same people who would be interested in a multi-purpose tool. Police can use it, the home-owner Who would use a power-base? SWAT, the oil industry, hazardous waste…
Audrow Nash: So, lots of applications?
Norm Domholt: A lot of applications, yes.
Audrow Nash: Thank you.
Norm Domholt: You’re welcome, thank you.
Annemarie Laudanski (6m 20s), Lead Field Applications Engineer at Xsens:
Audrow Nash: Hi, can you introduce yourself and tell me about your company?
Annemarie Laudanski: Hi, my name is Annemarie Laudanski and I work for Xsens, we do animation promotion capture.
Audrow Nash: Can you tell me about what you have set up at this booth and describe it?
Annemarie Laudanski: Today we’re trying out our inertial motion capture system. It’s a full body- measure-capture system built of 17 inertial sensors. In each of these, there are 3-D accelerometers, gyroscopes and magnetometers. They’re used to measure the movement of arms and legs and send information wirelessly to the computer, where it’s translated into a bio-chemical model. So, we can measure exactly what someone is doing and portray that on our software.
Audrow Nash: At the booth you have a dancer?
Annemarie Laudanski: We do, yes. We hired Ashley. She’s the cheerleader for the Boston Celtics and she’s with us during the conference to showcase the use of our system.
Audrow Nash: You mentioned you were using exonorometers, gyroscopes and Megnatometers. So, it doesn’t require any external visual system to track them? You’re just taking the raw data from all of these sensors, running that through, and then feeding it to a model, to develop a person?
Annemarie Laudanski: That’s right. The exonorometers measure how fast each limb segment is moving, the gyroscopes measure the rate of turn of the limb and then we use the megnatometers to correct the drift in the other sensors. A fusion of these three sets of sensor data is sent wirelessly to the computer where it’s combined with our calibration procedure to build a human model. The calibration takes an average reading from the sensors, while the subject is standing still for five-seconds. This is a known position for taking sensor data, that then informs each of the trackers, so that the model is built correctly.
Audrow Nash: I see. As the dancer moves, it’s happening in real time.
Annemarie Laudanski: Yes, all of it is done in real time so all of the sensors are sending data at 30 bites per second to the computer and everything is shown with a latency of, at most, ten milliseconds, which is mostly due to the Microsoft operating system we are working with.
Audrow Nash: What are some applications?
Annemarie Laudanski: The applications are really wide for this type of technology. They go from entertainment purposes, where people are using it for movie and game design, to movement science, where it’s used for sport, rehabilitation or ergonomics and also human-robot interaction. So, you can even have someone in the system and driving a robot, or building up a database of human movements that can be used to program one and allow it to move like a human would.
Audrow Nash: Thank you.
Annemarie Laudanski: Thank you.
Carl Vause (9m 14s), CEO of Soft Robotics:
Audrow Nash: Hi, can you introduce yourself and the company?
Carl Vause: I’m Carl Vause and this is Soft Robotics Incorporated. We’re a Boston-based company that got spun out as a research group at Harvard about a year ago. We’re taking soft robotics technology and making it real, producing commercial products to solve new problems across a variety of markets.
Audrow Nash: Can you tell me about what you’ve displayed at the booth?
Carl Vause: At the booth today we have two soft hands: A very large hand for handling pumpkins, shoe bags and objects of very weighty geometry, and a small-handed, or short, robotic arm. What we wanted to show here is that, currently, there are a lot of problems with robotic manipulation. Manipulators don’t do well with soft, curvy, easily damaged objects and they don’t do well in unstructured gripping scenarios.
What we have solved using soft actuators is the ability to pick up anything with this arm, from a prickly cactus, which you would never pick up with your bare hand, to a racket ball or a cupcake. We want to show that, with almost no control system, building a very clever, soft actuator can solve a problem that has been vexing robotics: How to develop a gripper that is as adaptable and conformal as a human hand. People are spending millions of dollars to solve this problem using traditional hard robotics.
Audrow Nash: Can you describe the hand and the smaller robotic arm?
Carl Vause: One is a four-finger hand. It’s based on proprietary actuator geometry. We use vacuum to curl the fingers out of the way and they pressurize to create a grasp. We have a three-finger gripper as well. It actually has fingernails, so it can access a low profile object like a circuit board.
Audrow Nash: Can you tell me some potential applications of these soft hands? I know there are a lot.
Carl Vause: A lot, but how do you interface a robot with something that has an unknown shape? Or when the position is unknown? Or something easily damaged? Agricultural processing is interesting. Picking lettuces heads, for example. There’s a danger of introducing E. coli into the food chain, so washing and cleaning lettuce. Robotics companies and the US Food and Drug Administration want to automate that task. But robots today can’t handle lettuce, because their heads vary in size, shape and weight, and they are delicate objects. So, one of the things that we really wanted to do with our soft robotic technology is unlock that market for automation, and automate data handling.
They can even work in wet conditions; there are no electrical connections here. You can sterilize them and wash them down with bleach at the end of the day. It really does bring automation into the agricultural process. It makes it a reality.
There’s also a light-weight version for working side-by-side with a human collaborator. In a lab, for example where you need to be careful what you touch. A manipulator can pick up a range of lab instruments, or tools, and hand them safely to you. It has the credentials of collaboration.
Audrow Nash: The ones that you have on display are on open feedback loops. As in, they don’t sense what they’re picking up, they just actuate. You’ve talked a little bit about embedding sensors into the fingers in the hands. Can you tell me more about that?
Carl Vause: We can easily embed sensors to give an object grasp detection. We can embed it in our proprietary manufacturing process, in simple off-the-shelf sensors and feed them back into something very basic. If you want it very simple, take an Arduino and provide passive grasp detection. That’s very simple.
Audrow Nash: Thank you.
Carl Vause: Alright.
Konrad Fagertun (13m 56s), COO of NLinks:
Audrow Nash: Hi, can you introduce yourself and tell me about your company?
Konrad Fagertun: Yes, my name is Konrad Fagertun. I’m a co-founder of NLink Robotics. We’ve come all the way from Norway to Boston, to showcase the world’s first mobile drilling robot. We’re excited to be here at Robobusiness, showing what we’ve been working on for the last two years.
Audrow Nash: Can you describe the robot to me?
Konrad Fagertun: Yes. The challenge in the construction industry is hard labor – manual work – and the hardest of all is drilling holes in concrete ceilings. So, we made a mobile drilling robot. It comprises a mobile lift – that can drive around – and, on top of that, is a robotic arm holding a rotary hammer drill. It thrusts that up to the ceiling and can drill holes wherever you want. It uses lasers and cameras to position itself, so it can drill to a millimeter’s precision. This can be done hundreds of thousands of times, say for a large shopping mall or an office building. It’s repetitive work.
The robot is a little bit bigger than a man, and can reach several feet high, so you don’t have to get up on scaffolding or stairs to do the work; the operator can stand on the ground, safely at a distance. But, if he wants to get close, no problem, the robot is certified to work with humans, so it doesn’t matter if it crashes into your arm, it won’t hurt you and it’ll stop. It’s useful for electrical contractors, plumbers, mechanical engineers…
Audrow Nash: Thank you.
Konrad Fagertun: Thanks.
Asim Ikram (15m 51s), CEO of Neo Robotics:
Audrow Nash: Can you introduce yourself and your company?
Asim Ikram: Yes, my name is Asim Ikram and I’m the CEO of Neo Robotics in Dubai.
Audrow Nash: What do you guys do?
Asim Ikram: We’re a new start up in Dubai, not limited to robotics. In that region, they are not exposed to robots at the moment. We are starting at the lower level, to introduce smart apps and ICT, Information Communication Technologies. Then, we want to switch to robots, because the customers are the same.
Audrow Nash: So, basically you’re acting as a liaison between companies in the US and outside for bringing robots into Dubai?
Asim Ikram: Into the GCC region – the Gulf Cooperating Countries. There are six of them in the Middle East: Saudi Arabia, Bahrain, Oman, Kuwait, Emirates and Qatar. They have a strong focus on technology, they’re teaching robotics and megatronics and have labs at almost every university. The industry will develop but, at the moment, there’s no pull from for robots.
Audrow Nash: What are some of the more popular technologies that are being brought to Dubai?
Asim Ikram: Not so much industrial robotics, but there are new production lines coming up that have industrial robots in the blueprint. Those lines should start operating in six months. The financing and planning is already done. Healthcare and education, that’s much further ahead. On the education side, there’s big competition between the private schools that are teaching things like systems programming. Now they’re also trying to get robots into the classrooms and teach with them. There’s a lot of movement there.
Audrow Nash: What robotics opportunities do you think there are in Dubai for engineers and entrepreneurs from the rest of the world?
Asim Ikram: There’s a lot of work in real-world drone applications. Already, highway police are using drones. They’ve also started making some national identity card deliveries with drones. Real applications of technology are moving fast. On the security side, I’ve seen a lot of civil defense robots for bomb disposal.
Audrow Nash: How did you decide to take this opportunity and form a company?
Asim Ikram: I’ve been working in this market for some time and I’ve been seeing a lot of pull in different areas. Healthcare and education are moving very fast and the industrial side will come up in the next one or two years. There are a few robotics service companies, but not many locally so I found a gap. It’s a good time to start something.
Harri Valpola(21m 40s), Head of Technology at Zen Robotics:
Audrow Nash: Can you introduce yourself and your company?
Harri Valpola: Yes, hello. I’m Harri Holopainen. I’m one of the founders of Zen Robotics Company in Helsinki, Finland. Currently, our main application is robots that have learnt to pick up waste. A little bit like WALL-E…
Audrow Nash: It looks a little different than WALL-E. Can you describe the robotic system you have?
Harri Valpola: Whereas WALL-E is cute, a small Hollywood robot, our robot is more like an large industrial scale model. It doesn’t look like a human; it’s not cute, but it works very efficiently. It’s powerful. It can lift and throw objects that weigh up to 20 kilos – 40 pounds – like they were nothing.
Audrow Nash: It looks like a conveyor belt and has robotic arms that move around and pick objects off of the conveyor belt and throw them to sort them. Am I correct?
Harri Valpola: Yes. It works in a similar way to human hands. All around the waist is a conveyor belt. The robot recognizes the objects and sorts them, exactly as a human would do, but faster. It’s also stronger and it doesn’t break.
Audrow Nash: What kind of sensors are you using to identify the material? What waste are you sorting now?
Harri Valpola: We are currently focused on construction and demolition waste. The sensors we are using are tailored for that particular waste. The most important material we’re sorting is wood, followed by mineral-based parts and metal. We’re using sensors that can discriminate between these. They include metal detectors and spectrometers.
Audrow Nash: Where have you implemented the system and what sort of feedback are you getting from customers?
Harri Valpola: Currently, we have three customers in Europe; two in Finland and one in Holland. We’ve been developing this system for two years and now it’s working and customers are happy. We’re ready to scale up, now we have the product, so that other customers can start making use of this solution.
Audrow Nash: What’s the benefit of sorting the waste?
Harri Valpola: In Europe, at least, there are many companies that are floating in waste. Population densities are so high, there’s no place to put it. The only real option is to sort the waste. There are many valuable raw materials there. Sorting stones is not important but there are valuable metals, like copper and aluminum, and also wood. That’s particularly useful in Holland because they don’t have forests, and it can be recycled and used as a construction material.
Audrow Nash: Thank you.
Harri Valpola: Thank you.
Dick Zhang (26m 15s), CEO of Identified Technology:
Audrow Nash: Interviewer: Can you introduce yourself and tell me about your company?
Dick Zhang: My name is Dick Zhang from Identified Technologies. We build and scale drones for commercial data capture. We work with construction and energy industry clients and help deliver data and insights. We get this information either by deploying robots on the ground, or by utilizing commercial planes and helicopters. It’s very expensive, it’s very dangerous and it’s very slow.
We deliver insights by collecting massive scale amounts of data on what has happened in the past, what’s going on now and what’s going to happen in the future, through predictive capabilities.
We collect the data via a three-part system: an autonomous drone, a dock station, that swaps batteries and uploads data, and a client dashboard that can be used to interact with and control the system from the cloud, from anywhere in real time.
We’ve been working with really exciting partners in energy and construction for the last six months. I run the business, look for exposure and develop partner and client relationships.
Audrow Nash: Can you tell me a bit about the demonstration – the drone, the quadcopter – you have on your booth?
Dick Zhang: The drone itself, everything inside, in terms of hardware, is really off-the-shelf components. Our dock station, that swaps batteries and outputs data, that’s all proprietary mechanical design and hardware. The software system is also proprietary. So a lot goes into flight control – safety checks, process checks, maintenance, things like that.
Audrow Nash: Swapping the batteries, is that automated?
Dick Zhang: Yes, that is automated. On the docking station, there’s a carrousel with six batteries that are always charged. It inserts another battery when the drone needs to fly.
To tell you a story, what inspired all of this was a talk with one of our clients. They run 5,000 job sites around the world. They bought an Internet tool but had no idea how they were going to train 1,500 people to use it. So I automated a system and made it self-operating and self-sufficient. We were able to employ 1,500 really rapidly across the country and across the world.
Audrow Nash: Is it totally self-sustaining?
Dick Zhang: Yes, right now all you need is a standard power plug. Future generations will evolve generators, solar panels and wind fans. But, apart from the source of power, everything happens on its own. It flies itself, captures data and swaps batteries.
Audrow Nash: What kind of navigation do you use on the drones?
Dick Zhang: Navigation in drone technology has become really sophisticated over the last couple of years. We have a combination of GPS and inertial sensors on board, so that, three or four hundred times every second, the drone is saying to itself: “I need to be in position XYZ. Right now I’m not there, but I’m close. Let me get there.” So, four hundred times every second, it’s making these corrections and adjustments so that it can fly along the path that the computer programmed.
Audrow Nash: Other than the IMU and the GPS, what other sensors do you use? Do you have a vision system for landing on the platform that swaps the batteries, and some other sensors?
Dick Zhang: Yes. Now we are working with cameras. We’ve done some early tests with our partners on infrared and gas effect. We do a lot of work in energy. As part of this start up growth, we’re going through a crafty process of crawl, walk and run. It’s the vision that enables the most capabilities, to help our clients right now, with the resources that we have. Now, to touch on how we land, that’s a huge problem. So, we built a proprietary vision system based on ultrasound. There’s a beacon and a dock and a transceiver, where you listen and triangulate.
Audrow Nash: Okay, so you use GPS to get it close enough…
Dick Zhang: Exactly.
Audrow Nash: Then the ultrasound takes over by localizing the sound somehow?
Dick Zhang: Yes, exactly.
Audrow Nash: Okay, thank you.
Dick Zhang: That was awesome. Thank you.
All audio interviews are transcribed and edited for clarity with great care, however, we cannot assume responsibility for their accuracy.
Robohub Podcast is a non-profit robotics podcast where we interview experts in robotics, including researchers, entrepreneurs, policy makers, and venture capitalists. Our interviewers are researchers, entrepreneurs, and engineers involved in robotics. Our interviews are technical and, often, get into the details of what we are discussing, but we make an effort to have our interviews understandable to a general audience.