Robust Fall Recovery for Armless Bipedal-Wheeled Robots Via Force-Guided Learning

📄 arXiv: 2606.14270v1 📥 PDF

作者: Haidong Hou, Zhangguo Yu, Tao Han, Hengbo Qi, Khaleel Ghazal, Yu Zhang, Yidong Du, Xuechao Chen, Fei Meng

分类: cs.RO, cs.AI

发布日期: 2026-06-12

备注: 8 pages, 6 figures, accepted by IEEE Robotics and Automation Letters (RA-L)

期刊: IEEE Robotics and Automation Letters, 2026

DOI: 10.1109/LRA.2026.3701481

🔗 代码/项目: PROJECT_PAGE


💡 一句话要点

提出基于力引导学习的无臂双足轮式机器人跌倒恢复方法

🎯 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)

关键词: 跌倒恢复 双足机器人 力引导学习 强化学习 机器人运动控制 教师-学生架构 阶段性奖励

📋 核心要点

  1. 现有的跌倒恢复方法依赖于手臂或多条腿的协调,无法满足无臂双足轮式机器人的需求。
  2. 本文提出FTSR框架,通过力引导和阶段性奖励,优化机器人在跌倒后的恢复策略。
  3. 实验结果显示,该方法在多种复杂环境下实现了可靠的跌倒恢复,且运动能力得以保持。

📝 摘要(中文)

跌倒恢复对于自主腿部运动至关重要。现有方法已证明某些腿部机器人(如人形和四足机器人)能够通过利用手臂或协调多条腿来产生支撑力,从多种姿态中恢复。然而,无臂或缺乏其他腿部支撑的双足轮式机器人必须依靠腿部的驱动,恢复过程尤为困难。为此,本文提出了FTSR(力引导教师-学生框架与阶段性奖励)。该方法在模拟训练中构建与机器人实时高度直接相关的外部辅助力,将其明确地制定为可优化的约束。通过约束强化学习,策略逐渐减少对外部力的依赖并提高身体高度,尽管没有手臂支撑,仍能发展内部恢复策略。实验结果表明,该框架在多种挑战条件下实现了稳健可靠的跌倒恢复,展示了强大的环境适应性和运动鲁棒性。

🔬 方法详解

问题定义:本文旨在解决无臂双足轮式机器人在跌倒后恢复的困难,现有方法无法提供有效的支撑,导致恢复能力不足。

核心思路:提出FTSR框架,通过在模拟训练中引入与机器人高度相关的外部辅助力,作为优化约束,逐步引导机器人减少对外部力的依赖。

技术框架:FTSR框架包含三个主要模块:力引导模块、阶段性奖励模块和教师-学生架构。力引导模块提供外部辅助力,阶段性奖励模块根据恢复过程中的高度变化给予奖励,教师-学生架构用于知识蒸馏。

关键创新:最重要的创新在于通过力引导的方式构建可优化的约束,使机器人在没有手臂支撑的情况下,仍能有效学习到内部恢复策略,显著提高了恢复能力。

关键设计:在训练过程中,设置了与机器人高度相关的损失函数,采用了阶段性奖励机制,确保机器人在恢复过程中逐步稳定姿态,并保持运动能力。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果表明,经过FTSR训练的无臂双足轮式机器人在多种挑战条件下实现了超过90%的跌倒恢复成功率,展示了优越的环境适应性和运动鲁棒性,且在恢复后能够保持完整的运动能力。

🎯 应用场景

该研究的潜在应用领域包括服务机器人、救援机器人和自主移动设备等,能够在复杂环境中实现安全可靠的自主运动。未来,该方法有望推广到其他类型的机器人,提升其在跌倒恢复和运动稳定性方面的能力。

📄 摘要(原文)

Fall recovery is critical for autonomous legged locomotion. Existing methods have demonstrated that some legged robots, such as humanoids and quadrupeds, are capable of fall recovery from diverse postures by utilizing arms or coordinating multi-legs to generate support forces. Without arms or other legs to provide supportive assistance, a bipedal-wheeled robot must rely solely on the actuation of its legs, making recovery particularly difficult. To address this, we introduce FTSR (Force-guided Teacher-student framework with Stage-wise Rewards). The force-guided method constructs an external auxiliary force during simulation training that correlates directly with the robot's real-time height, explicitly formulating this force as an optimizable constraint. Through constrained reinforcement learning, the policy is guided toward reducing force dependency gradually and increasing the body height, developing internal recovery strategies despite having no arms for support. Height-progressive stage-Wise rewards progressively structure posture stabilization during recovery and transition to sustained locomotion, integrated with teacher-student architecture distilling privileged knowledge of force effects and recovery dynamics. After simulation training, the policy is deployed on a physical armless bipedal-wheeled robot and extensively evaluated. Experiments confirm robust and reliable fall recovery under diverse challenging conditions, demonstrating strong environmental adaptability and motion robustness, while maintaining full post-recovery motion capability. The framework also generalizes effectively to a high-DOF humanoid, confirming its practical generalizability. The project page is available at https://2350575870.github.io/force-guided.github.io/