论文/arXiv 2610.01397·27 天前

继续、中止还是跌倒：面向安全人形机器人杂技动作的 Viability-Aware Policy Selection（VAPS）

VAPS用短时域可行性预测在跟踪、中止和保护性跌倒策略间选择，并在仿真及LimX Oli侧空翻上验证安全杂技。

AI 整理

• 硬件零部件
• 本体 SDK 与控制
• 仿真与训练

宇树 G1

原文链接：Continue, Abort, or Fall: Viability-Aware Policy Selection (VAPS) for Safe Humanoid Acrobatics（arXiv 2610.01397 · 发布日期：2026-10-01）

Continue, Abort, or Fall: Viability-Aware Policy Selection (VAPS) for Safe Humanoid Acrobatics

VAPS用短时域可行性预测在跟踪、中止和保护性跌倒策略间选择，并在仿真及LimX Oli侧空翻上验证安全杂技。

核心要点

• 动态人形翻转在策略不佳、扰动或仿真到现实差距下易损硬件，单一跟踪策略偏离参考后缺少退路。
• VAPS把安全视为策略条件的滚动时域决策，训练保护性跌倒与可随时落脚的中止策略。
• 每个控制步预测标称跟踪和中止策略短时域可行性，并按最小牺牲层级保留可行的最积极行为。
• 随机扰动仿真中，VAPS在Unitree G1和LimX Oli上减少头部和手部接触，并优于强单网络替代方案。

验证范围与局限：验证范围包括随机扰动仿真中的Unitree G1和LimX Oli，以及LimX Oli上的侧空翻动作。

英文摘要 (Abstract)

Dynamic humanoid motions such as flips risk hardware damage due to suboptimal policies, disturbances or sim-to-real gaps. A motion tracking policy offers no way out once the maneuver leaves its reference, and a backup policy needs to take over to protect the hardware for a minimum-damage landing. Which backup to use matters as much as when to switch. We present Viability-Aware Policy Selection (VAPS), which treats safety as a policy-conditioned, receding-horizon decision. Besides a protective fall policy, we also train an abort policy which can abort the motion at any time, landing on its feet. At every control step, learned predictors estimate whether the nominal tracking policy and the abort policy remain viable over a short horizon, and a least-sacrificial hierarchy keeps the most task-ambitious behavior that remains viable. In simulation with randomized disturbances, VAPS sharply reduces head contact and hand contact, which are the dominant sources of hardware damage, with both a Unitree G1 and a LimX Oli; on the LimX Oli, we validate the viability predictors and the full VAPS controller for side-flip motions. VAPS Pareto-dominates the strongest single-network alternatives we could train, including an end-to-end safe-tracking policy and students distilled from VAPS's own oracle-routed decisions, in both task success and head impact. We also show that VAPS is a powerful framework to supervise undertrained policies and protect the hardware.

作者：居思伟, Lu Liu, Jan Peters, Oleg Arenz

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.01397：Continue, Abort, or Fall: Viability-Aware Policy Selection (VAPS) for Safe Humanoid Acrobatics访问 2026-10-21