The virtual robots look weird, but they get the job done
First, a design-optimization algorithm "Generates a bunch of random robot designs," Bhatia says.
The algorithm creates each soft robot by combining up to 100 individual building blocks, which can be rigid or flexible and can move vertically or horizontally.
Then these patchwork designs go to the control-optimization algorithm, which generates a "Brain" for each robot that will enable it to perform a given task.
Next, the various bot designs try an assigned task in the Evolution Gym while the control-optimization algorithm measures how well they perform and returns the scores to the design algorithm.
This goes on, with robots passing from the design algorithm to the controller algorithm to testing in the Evolution Gym environment and back again to the design algorithm until the system converges on the highest score.
Bhatia's favorite resulted from a task in which the robot had to slip under randomly spaced tiles, then drag an object across the top of those tiles while still underneath them.
Copying robot body plans from nature often does not work, he says, "Because dogs and humans evolved to fill very different environmental niches from those we try to introduce our humanoid or canine bots into." Aviation is a good example, Bongard explains.
"Only when we built non-bird-like machines did we get them to fly." Similarly, robot bodies produced by evolutionary algorithms often look strange but seem to work well at given tasks.
Others have attempted to co-design virtual robot bodies and brains, Bhatia says, but they have focused on simple tasks such as walking and jumping.
This shows there is a lot more work to do in designing truly intelligent robots, Bhatia says, making a standard platform such as Evolution Gym even more important to collectively advance the development of robot design.