Automated shapeshifting for function recovery in damaged robots

Abstract

A robot's mechanical parts routinely wear out from normal functioning and can be lost to injury. For autonomous robots operating in isolated or hostile environments, repair from a human operator is often not possible. Thus, much work has sought to automate damage recovery in robots. However, every case reported in the literature to date has accepted the damaged mechanical structure as fixed, and focused on learning new ways to control it. Here we show for the first time a robot that automatically recovers from unexpected damage by deforming its resting mechanical structure without changing its control policy. We found that, especially in the case of "deep insult", such as removal of all four of the robot's legs, the damaged machine evolves shape changes that not only recover the original level of function (locomotion) as before, but can in fact surpass the original level of performance (speed). This suggests that shape change, instead of control readaptation, may be a better method to recover function after damage in some cases.

References in corpus (7)

• Universal Robotic Gripper based on the Jamming of Granular Material
• Learning agile and dynamic motor skills for legged robots
• Robots that can adapt like animals
• Reset-free Trial-and-Error Learning for Robot Damage Recovery
• Sim-to-Real Reinforcement Learning for Deformable Object Manipulation
• Multiple chaotic central pattern generators with learning for legged locomotion and malfunction compensation
• Interoceptive robustness through environment-mediated morphological development

Cited by in corpus (9)

• Embodied Intelligence via Learning and Evolution
• A soft robot that adapts to environments through shape change
• Stretchable Arduinos embedded in soft robots
• Modular Controllers Facilitate the Co-Optimization of Morphology and Control in Soft Robots
• Word2vec to behavior: morphology facilitates the grounding of language in machines
• Regenerating Soft Robots through Neural Cellular Automata
• Towards Multi-Morphology Controllers with Diversity and Knowledge Distillation
• Design, Validation, and Case Studies of 2D-VSR-Sim, an Optimization-friendly Simulator of 2-D Voxel-based Soft Robots
• A review paper of bio-inspired environmental adaptive and precisely maneuverable soft robots