Resilient Machines Through Continuous Self-Modeling

TLDR

Animals sustain operation after injury by creating compensatory behaviors, a robustness that engineered systems lack, and this concept may help develop more robust machines and shed light on self‑modeling in animals. The study presents a robot that autonomously recovers from damage through continuous self‑modeling. The robot infers its own structure from actuation‑sensation relationships and uses the resulting self‑model to generate forward locomotion. When a leg part is removed, it adapts its self‑model and generates alternative gaits.

Abstract

Animals sustain the ability to operate after injury by creating qualitatively different compensatory behaviors. Although such robustness would be desirable in engineered systems, most machines fail in the face of unexpected damage. We describe a robot that can recover from such change autonomously, through continuous self-modeling. A four-legged machine uses actuation-sensation relationships to indirectly infer its own structure, and it then uses this self-model to generate forward locomotion. When a leg part is removed, it adapts the self-models, leading to the generation of alternative gaits. This concept may help develop more robust machines and shed light on self-modeling in animals.