Metraipolis › archive › dc_211d100b9fef

Joint-Health-Aware Reinforcement Learning for Robust Robot Control Under Actuator Degradation — arXiv:2610.41348

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41348
License (as archived): CC0-1.0
Archived: 2026-11-02T05:04:34.854Z
SHA-256 of the archived text: f87681b1a09c4a7edd47b9adbcda73f17fb02eb5b6c4fee01aa4a079e6b086ab
Stable URL of this page: https://metraipolis.com/documento/dc_211d100b9fef

How to cite

Joint-Health-Aware Reinforcement Learning for Robust Robot Control Under Actuator Degradation — arXiv:2610.41348 — arXiv (en), https://arxiv.org/abs/2610.41348 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_211d100b9fef (Metraipolis archive dc_211d100b9fef, sha256 f87681b1a09c4a7edd47b9adbcda73f17fb02eb5b6c4fee01aa4a079e6b086ab)

BibTeX

@misc{dc211d100b9fef,
  title = {Joint-Health-Aware Reinforcement Learning for Robust Robot Control Under Actuator Degradation — arXiv:2610.41348},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41348},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_211d100b9fef; sha256 f87681b1a09c4a7edd47b9adbcda73f17fb02eb5b6c4fee01aa4a079e6b086ab},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41348. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Robots deployed in unstructured environments are susceptible to actuator-authority degradation, which reduces the effective control authority of individual actuators and can cause reinforcement learning policies trained under nominal dynamics to fail. Existing robustness approaches rely on discrete fault labels, broad domain randomization, or global latent variables, often without explicitly modeling continuous per-joint residual actuation capability. We propose a joint-health-aware reinforcement learning framework for robust robot control under simulated actuator degradation. Our framework encodes actuator condition in a continuous joint-health vector and models degradation as multiplicative attenuation of executed actions. A dedicated HealthNet estimator infers per-joint health from recent observations and actions, allowing the policy to redistribute control effort across healthy and degraded joints. We evaluate the method on Walker, Go2, Cassie, and Panda-based ManiSkill manipulation tasks under diverse degradation masks and severity levels. The method outperforms nominal and degradation-trained no-health baselines on the main evaluated metrics. Relative to the nominal baseline, task-level locomotion returns improve by up to 250.1\% and manipulation success rates by up to 15.2 percentage points; in the high-degradation Cassie group, return increases from 3.94 to 40.50 (+928.0\%). Ablations support the contribution of per-joint health estimation, action-degradation modeling, and health-conditioned control.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.41348 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-02T04:49:13.295Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).