PREVIEW

Swiss scientists have programmed a remarkable robot to do ‘parkour’ and stylishly vault obstacles.
ETH Zurich researchers used machine learning to teach their robot, ANYmal, new skills.
ANYmal has for some time had no problem coping with the stony terrain of Swiss hiking trails, but now it has been taught parkour - using athletic manoeuvres to smoothly negotiate obstacles in the community urban environment.
To teach ANYmal these new party tricks, two teams, both from the group led by ETH Professor Marco Hutter of the Department of Mechanical and Process Engineering, followed different approaches.
ETH doctoral student Nikita Rudin, who does parkour in his free time, decided to teach the robot his hobby.
“Before the project started, several of my researcher colleagues thought that legged robots had already reached the limits of their development potential,” he says, “but I had a different opinion. In fact, I was sure that a lot more could be done with the mechanics of legged robots.”
With his own parkour experience in mind, Rudin set out to further push the boundaries of what ANYmal could do. ANYmal can now scale obstacles and perform dynamic manoeuvres to jump back down from them.
In the process, ANYmal learned like a child would – through trial and error. Now, when presented with an obstacle, ANYmal uses its camera and artificial neural network to determine what kind of impediment it’s dealing with. It then performs movements that seem likely to succeed based on its previous training.
The new skills it learnt aren’t just for show - as it can now traverse the kind of tricky terrain commonly found on building sites or in disaster areas.

Rudin’s colleague and fellow ETH doctoral student Fabian Jenelten used a method known as model-based control to teach the robot accurate manoeuvres, such as how to recognise and get past gaps and recesses in piles of rubble. In turn, machine learning helps the robot master movement patterns that it can then flexibly apply in unexpected situations.
As a result, the quadrupedal robot is now better at gaining a sure footing on slippery surfaces or unstable boulders. ANYmal is soon also to be deployed on building sites or anywhere that is too dangerous for people – for instance to inspect a collapsed house in a disaster area.