Robohub.org
 

Video: Quadrocopter learns from its mistakes, perfects air racing

by
08 November 2012



share this:

First person view of the quadrocopter racing through a pylon slalom course.

Manual programming of robots only gets you so far. And, as you can see in the video, for quadrocopters that’s not very far at all (see the “Without Learning” part starting at 1:30):

On its first try to navigate the obstacle course, the flying robot attempts to navigate based on a pre-computed flight path. The path is derived using a basic mathematical (“first principles”) model. But quadrocopters have complex aerodynamics – the force produced by the propellers changes depending on the vehicle’s velocity and orientation, and thus the actual amount of force produced is quite different from what the simple math describes.

What’s worse, these flying vehicles use soft propellers for safety, which bend differently depending on how much thrust is applied and wear rapidly with use (and even more rapidly when crashing).

Even with continuous feedback on the robot’s position from the motion capture system, manually programming the robots with a control sequence that takes all these imperfections into account is impractical.

 

My colleague Angela Schoellig and the Flying Machine Arena team here at ETH Zurich have now developed and implemented algorithms that allow their flying robots to race through an obstacle parcours – and learn to improve their performance.

Here is how Angela described the process to me:

The learning algorithm is applied to a quadrocopter that is guided by an underlying trajectory-following controller. The result of the learning is an adapted input trajectory in terms of desired positions. The algorithm has been equipped with several unique features that are particularly important when pushing vehicles to the limits of their dynamic capabilities and when applying the learning algorithm to increasingly complex systems:

1. We designed an input update rule that explicitly takes actuation and sensor limits into account by solving a constrained convex problem.
2. We developed an identification routine that extracts the model data required by the learning algorithm from a numerical simulation of the vehicle dynamics. That is, the algorithm is applicable to systems for which an analytical model is difficult (or impossible) to derive.
3. We combined model data and experimental data, traditional filtering methods and state-of-the- art optimization techniques to achieve an effective and computationally efficient learning strategy that achieves convergence in less than ten iterations.

 

The result is a robot that learns and improves each time it tries to perform a task.

In this example the robot races through a pylon parcours, calling to mind air races, such as the Red Bull Air Racing Championships or the Reno Air Races – except that there are no human pilots that spent their life learning to fly – here it’s robots doing the learning. And they are efficient, taking less than 10 training sessions to find the optimal steering commands!

Moreover, the learning algorithms are not specific to slalom racing, they can be used to learn other tasks. As Angela points out:

Our goal is to enable autonomous systems – such as the quadrocopter in the video – to ‘learn’ the way humans do: through practice.

 

The videos below show how learning algorithms can be used for other robotic tasks:

 

 

 

 

Full disclosure: Angela and the Flying Machine Arena team work in the same lab as I. Also, I’m working on RoboEarth, trying to allow robot learning on a much larger scale.

 



tags: , , , , , , , , ,


Markus Waibel is a Co-Founder and COO of Verity Studios AG, Co-Founder of Robohub and the ROBOTS Podcast.
Markus Waibel is a Co-Founder and COO of Verity Studios AG, Co-Founder of Robohub and the ROBOTS Podcast.





Related posts :



#ICRA2022 networking events

This year at ICRA there were great number of opportunities to involve and engage as well including networking events.
04 July 2022, by

ROS Awards 2022 results

The intention of these awards is to express recognition for contributions to the ROS community and the development of the ROS-based robot industry, and to help those contributions gain awareness.
02 July 2022, by
ep.

357

podcast

Origin Story of the OAK-D, with Brandon Gilles

Brandon Gilles, the founder of Luxonis and maker of the OAK-D, describes the journey and the flexibility of the OAK-D line of products
01 July 2022, by

The one-wheel Cubli

Researchers Matthias Hofer, Michael Muehlebach and Raffaello D’Andrea have developed the one-wheel Cubli, a three-dimensional pendulum system that can balance on its pivot using a single reaction wheel. How is it possible to stabilize the two tilt angles of the system with only a single reaction wheel?
30 June 2022, by and

At the forefront of building with biology

Raman is, as she puts it, “a mechanical engineer through and through.” Today, Ritu Raman leads the Raman Lab and is an Assistant Professor in the Department of Mechanical Engineering.
28 June 2022, by

Hot Robotics Symposium celebrates UK success

An internationally leading robotics initiative that enables academia and industry to find innovative solutions to real world challenges, celebrated its success with a Hot Robotics Symposium hosted across three UK regions last week.
25 June 2022, by





©2021 - ROBOTS Association


 












©2021 - ROBOTS Association