SWAP: Test-Time Steerable Humanoid Whole-Body Collision Avoidance

📄 arXiv: 2610.25711v1 📥 PDF

作者: Zeji Yi, Guanqi He, Xiaofeng Guo, Guannan Qu, Pieter Abbeel, Yan Duan, Karen Liu, Guanya Shi

分类: cs.RO

发布日期: 2026-10-19

备注: 20 pages, 11 figures, 4 tables. Project website: https://iscoyizj.github.io/SWAP-steerable-humanoid-oa-website/

🔗 代码/项目: PROJECT_PAGE


💡 一句话要点

提出SWAP以解决人形机器人全身碰撞避免问题

🎯 匹配领域: 支柱一:机器人控制 (Robot Control) 支柱二:RL算法与架构 (RL & Architecture) 支柱九:具身大模型 (Embodied Foundation Models)

关键词: 人形机器人 碰撞避免 强化学习 多模态策略 动态稳定性 感知条件策略 自主导航

📋 核心要点

  1. 现有方法难以同时考虑动态稳定性和碰撞避免,尤其是在复杂环境中。
  2. 提出SWAP框架,通过高层扩散策略生成多模态运动提案,低层控制器负责平衡与跟踪。
  3. 实验表明,SWAP在静态和动态障碍物下均能实现可靠的碰撞避免,且目标奖励提升34%。

📝 摘要(中文)

人形机器人在以人为中心的环境中操作时,必须协调全身以穿越狭窄、杂乱的空间,同时保持平衡。现有方法往往难以从高维感知输入中共同考虑动态稳定性和碰撞避免。此外,对于人形机器人而言,安全行为本质上是多模态的:同一障碍物可能允许多种有效的穿越方式,这难以用单一的确定性策略表示。为了解决这些挑战,本文提出了SWAP(可调节的全身避免策略),一个将碰撞意识决策与稳定性分开的分层框架。高层的感知条件扩散策略生成多模态的碰撞意识运动提案,而低层的全身强化学习控制器跟踪这些提案并维持动态平衡。实验结果表明,该方法在静态和动态障碍物下均能可靠避免碰撞,并在测试时的调节能力上提高了34%的目标奖励。

🔬 方法详解

问题定义:本文旨在解决人形机器人在复杂环境中全身碰撞避免的问题。现有方法在动态稳定性与碰撞避免的联合考虑上存在不足,难以应对多模态的安全行为需求。

核心思路:SWAP框架通过将碰撞意识决策与动态平衡分离,采用高层扩散策略生成多模态运动提案,低层控制器则负责跟踪这些提案并维持平衡。这种设计使得机器人能够在复杂环境中灵活应对多种障碍物。

技术框架:SWAP框架分为两个主要模块:高层感知条件扩散策略和低层全身强化学习控制器。高层模块生成多模态运动提案,低层模块则通过强化学习跟踪这些提案并保持动态稳定。

关键创新:SWAP的核心创新在于引入了高层扩散策略与低层控制器的分层设计,使得机器人能够在复杂环境中实现灵活的碰撞避免。这与现有方法的单一策略设计形成了本质区别。

关键设计:在训练高层策略时,采用了后见标签的可扩展监督方法,通过随机命令下的低层策略回放,确保生成的运动在构造上是无碰撞的。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果显示,SWAP在静态和动态障碍物下均能实现可靠的碰撞避免,且在测试时调节能力上平均提升了34%的目标奖励,展示了其在实际应用中的有效性和灵活性。

🎯 应用场景

该研究的潜在应用领域包括人形机器人在家庭、医疗和服务行业的自主导航与操作。通过提高碰撞避免能力,SWAP可以增强机器人在复杂环境中的安全性和灵活性,推动人形机器人技术的实际应用与发展。

📄 摘要(原文)

Humanoid robots operating in human-centric environments must coordinate the entire body to traverse tight, cluttered spaces while maintaining balance. Existing methods often struggle to jointly consider dynamic stability and collision avoidance from high-dimensional perceptual inputs. Moreover, for humanoids, safe behavior is inherently multimodal: the same obstacle may admit multiple valid traversals, which is difficult to represent with a single deterministic policy. To address these challenges, we propose SWAP (Steerable Whole-body Avoidance Policy), a hierarchical framework that separates collision-aware decision making from stabilization. A high-level, perception-conditioned diffusion policy generates multimodal, collision-aware motion proposals, while a low-level whole-body RL controller tracks these proposals and maintains dynamic balance. To efficiently train the high-level policy, we obtain scalable supervision via hindsight labeling: we roll out the low-level policy under randomized commands, place obstacles only in the space that each executed motion did not sweep, so the motion is collision-free by construction, and re-render the perception the robot would have seen. At deployment, Monte Carlo sampling with simple cost signals steers the diffusion model toward safe, task-aligned behaviors without heavy reward tuning. Experiments in simulation and on a real Unitree G1 humanoid show reliable avoidance with static and dynamic obstacles. Test-time steering further enables customization, improving targeted rewards (e.g., speed, orientation, or posture) by 34% on average while maintaining a high collision avoidance rate. Together, these results support a practical solution to humanoid whole-body collision avoidance with test-time steerability. Project website: https://iscoyizj.github.io/SWAP-steerable-humanoid-oa-website/