跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.23916 · v1

ReLoco: Unified Humanoid Locomotion and Fall Recovery via Behavior-Conditioned Motion Priors

首次提交 2026-11-18 14:06
版本更新 2026-11-18 14:06
雷达观测 2026-11-19 19:08
arXiv ↗PDF ↗

摘要

Humanoid robots must recover from falls and resume commanded motion to sustain locomotion. Learning these behaviors in one policy requires supervision that accommodates both upright movement and ground-contact recovery. We present ReLoco, a framework that uses behavior-conditioned adversarial motion priors to learn locomotion, get-up from arbitrary fallen postures, and command resumption within one proprioceptive policy. During training, robot posture selects the expert pool and conditions a shared discriminator with two behavior-specific outputs. Task rewards and shared regularization support command tracking and recovery, while temporary assistance facilitates exploration. A simulation-based refinement stage supplies robot-executed motion references for this supervision. Ablations examine conditional supervision, output separation, and reference quality under matched settings. At a common training iteration, the full policy achieves 96.80%96.80\% independent get-up success and 96.96%96.96\% push-recovery success, including command resumption. Its torso planar velocity root-mean-square error is 0.12660.1266~m/s, 14.7%14.7\% lower than the conditional single-output variant, with similar joint-angle discrepancy measured by dynamic time warping. Deployment on the 64.5-kg Tiangong~3.0 humanoid demonstrates walking, running, get-up, and locomotion resumption after falls using one proprioceptive actor, without controller switching or on-robot policy fine-tuning.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-18 14:06 · 最新观测版本

ReLoco: Unified Humanoid Locomotion and Fall Recovery via Behavior-Conditioned Motion Priors

Humanoid robots must recover from falls and resume commanded motion to sustain locomotion. Learning these behaviors in one policy requires supervision that accommodates both upright movement and ground-contact recovery. We present ReLoco, a framework that uses behavior-conditioned adversarial motion priors to learn locomotion, get-up from arbitrary fallen postures, and command resumption within one proprioceptive policy. During training, robot posture selects the expert pool and conditions a shared discriminator with two behavior-specific outputs. Task rewards and shared regularization support command tracking and recovery, while temporary assistance facilitates exploration. A simulation-based refinement stage supplies robot-executed motion references for this supervision. Ablations examine conditional supervision, output separation, and reference quality under matched settings. At a common training iteration, the full policy achieves 96.80%96.80\% independent get-up success and 96.96%96.96\% push-recovery success, including command resumption. Its torso planar velocity root-mean-square error is 0.12660.1266~m/s, 14.7%14.7\% lower than the conditional single-output variant, with similar joint-angle discrepancy measured by dynamic time warping. Deployment on the 64.5-kg Tiangong~3.0 humanoid demonstrates walking, running, get-up, and locomotion resumption after falls using one proprioceptive actor, without controller switching or on-robot policy fine-tuning.

查看此版本解读 →查看此版本原文 ↗