Abstract
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. We ask whether these benefits can be strengthened by explicitly modeling higher-order mechanical structure. We represent the Unitree Go1 as a cell complex with limb- and body-level rank-2 cells and apply Hodge-based message passing. 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. These results support higher-order morphology as a useful inductive bias for whole-body compensation under actuator degradation.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
You, D., Shamsi, Z., Wang, K., & Allen-Blanchette, C. (2026). Higher-Order Morphology Priors for Quadruped Reinforcement Learning Under Actuator Degradation. https://omanscience.com/en/articles/higher-order-morphology-priors-for-quadruped-reinforcement-learning-under-actuator-degradation
MLA 9
You, Derek, et al. "Higher-Order Morphology Priors for Quadruped Reinforcement Learning Under Actuator Degradation." https://omanscience.com/en/articles/higher-order-morphology-priors-for-quadruped-reinforcement-learning-under-actuator-degradation.
Chicago (author–date)
You, Derek, Zafir Shamsi, Keqin Wang, and Christine Allen-Blanchette. 2026. "Higher-Order Morphology Priors for Quadruped Reinforcement Learning Under Actuator Degradation." https://omanscience.com/en/articles/higher-order-morphology-priors-for-quadruped-reinforcement-learning-under-actuator-degradation.
Harvard
You, D., Shamsi, Z., Wang, K. and Allen-Blanchette, C. (2026) 'Higher-Order Morphology Priors for Quadruped Reinforcement Learning Under Actuator Degradation', Available at: https://omanscience.com/en/articles/higher-order-morphology-priors-for-quadruped-reinforcement-learning-under-actuator-degradation.
Vancouver
You D, Shamsi Z, Wang K, Allen-Blanchette C. Higher-Order Morphology Priors for Quadruped Reinforcement Learning Under Actuator Degradation. https://omanscience.com/en/articles/higher-order-morphology-priors-for-quadruped-reinforcement-learning-under-actuator-degradation
IEEE
D. You, Z. Shamsi, K. Wang, and C. Allen-Blanchette, "Higher-Order Morphology Priors for Quadruped Reinforcement Learning Under Actuator Degradation," https://omanscience.com/en/articles/higher-order-morphology-priors-for-quadruped-reinforcement-learning-under-actuator-degradation.