Robots that redesign themselves through kinematic self-destruction
This addresses the challenge of adaptive robot design for robotics, offering a novel strategy that could be broadly applicable, though it is incremental as it builds on existing concepts of self-modification.
The paper tackles the problem of robots being predesigned before deployment by introducing a robot that actively redesigns itself during its lifetime through kinematic self-destruction, resulting in more effective forward locomotion compared to policies that cannot remove or randomly remove links.
Every robot built to date was predesigned by an external process, prior to deployment. Here we show a robot that actively participates in its own design during its lifetime. Starting from a randomly assembled body, and using only proprioceptive feedback, the robot dynamically ``sculpts'' itself into a new design through kinematic self-destruction: identifying redundant links within its body that inhibit its locomotion, and then thrashing those links against the surface until they break at the joint and fall off the body. It does so using a single autoregressive sequence model, a universal controller that learns in simulation when and how to simplify a robot's body through self-destruction and then adaptively controls the reduced morphology. The optimized policy successfully transfers to reality and generalizes to previously unseen kinematic trees, generating forward locomotion that is more effective than otherwise equivalent policies that randomly remove links or cannot remove any. This suggests that self-designing robots may be more successful than predesigned robots in some cases, and that kinematic self-destruction, though reductive and irreversible, could provide a general adaptive strategy for a wide range of robots.