Higher-Order Morphology Priors for Quadruped Reinforcement Learning Under Actuator Degradation

Key points

• Prior work suggests that morphology-aware graph policies improve learning and generalization under body perturbations.1
• We represent the Unitree Go1 as a cell complex with limb- and body-level rank-2 cells and apply Hodge-based message passing.1
• Under degradation training, the node-edge-face Hodge actor achieves the highest return on unseen actuator degradations, with higher survival and lower velocity-tracking error.1
• These results support higher-order morphology as a useful inductive bias for whole-body compensation under actuator degradation.1

Sources (1)

• [1]Higher-Order Morphology Priors for Quadruped Reinforcement Learning Under Actuator Degradation
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 09:42 PM

  Actuator degradation turns quadruped locomotion into a coordination problem requiring joints to compensate for lost actuation.

  Prior work suggests that morphology-aware graph policies improve learning and generalization under body perturbations.

Extractive summary: sentences quoted from the sources.