Robots that redesign themselves through kinematic self-destruction

TL;DR

This paper introduces a self-designing robot that uses proprioceptive feedback and a universal controller to dynamically modify its body through self-destruction, improving locomotion and adaptability in real-world scenarios.

Contribution

It presents a novel approach where robots actively redesign themselves during operation via kinematic self-destruction, using a single learned policy transferable from simulation to reality.

Findings

Self-destructing robots outperform non-destructive policies in locomotion tasks.

The approach generalizes to unseen kinematic structures.

The method successfully transfers from simulation to real-world robots.

Abstract

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.