We are interested in exploring how plausible it is to control creatures whose bodies contain muscle and no bone.
We optimized policies using a genetic algorithm (GA) and using Proximal Policy Optimization (PPO).
|
|
| Tetrapus with high springiness | Tetrapus with low springiness |
|
| PPO creates stochastic policies, which are not as effective as those found using GA. |
We wanted to compare how policy effectiveness changes when you go from a single controller with full state knowledge to a set of distributed controllers, with only local state knowledge and the ability to pass information to neighbouring controllers.
|
|
|
| Worm with global controller | Worm with local, communicating controllers | Worm with local controllers but no communication |
|
| GA can optimize quadrupeds too! |
|
|
| Alternative methods of locomotion | |
|
| When they play your song at the club |
