持续前行：通过选择性对抗训练学习鲁棒的人形机器人运动技能
Keep on Going: Learning Robust Humanoid Motion Skills via Selective Adversarial Training
AI总结：
针对强化学习人形机器人运动策略易受干扰失稳的问题，提出SA2RT选择性对抗训练方法，在宇树G1上验证可显著提升地形穿越成功率、降低跟踪误差，实现鲁棒长时域运动。
摘要：
人形机器人被期望能够在执行多样化全身技能的同时，实现长时域可靠运行。然而强化学习（RL）运动策略通常在长时间运行、传感器/执行器噪声以及真实世界干扰下丧失稳定性。本研究提出选择性对抗攻击鲁棒训练方法（Selective Adversarial Attack for Robust Training，SA2RT）以提升运动技能的鲁棒性。该方法中的对抗器在攻击预算约束下，学习识别并稀疏扰动最脆弱的状态与动作，从而暴露策略的真实缺陷且不会引发保守过拟合问题。由此产生的非零和交替优化过程，会持续强化运动策略以抵御已发现的最强攻击。我们在宇树G1人形机器人上，针对感知 locomotion（运动）与全身控制任务验证了所提方法。实验结果显示，经对抗训练的策略将地形穿越成功率提升了40%，轨迹跟踪误差降低了32%，并能维持长时域机动性与跟踪性能。这些结果共同表明，选择性对抗攻击是学习鲁棒、长时域人形机器人运动技能的有效驱动手段。
英文摘要：
Humanoid robots are expected to operate reliably over long horizons while executing versatile whole-body skills. Yet Reinforcement Learning (RL) motion policies typically lose stability under prolonged operation, sensor/actuator noise, and real world disturbances. In this work, we propose a Selective Adversarial Attack for Robust Training (SA2RT) to enhance the robustness of motion skills. The adversary is learned to identify and sparsely perturb the most vulnerable states and actions under an attack-budget constraint, thereby exposing true weakness without inducing conservative overfitting. The resulting non-zero sum, alternating optimization continually strengthens the motion policy against the strongest discovered attacks. We validate our approach on the Unitree G1 humanoid robot across perceptive locomotion and whole-body control tasks. Experimental results show that adversarially trained policies improve the terrain traversal success rate by 40%, reduce the trajectory tracking error by 32%, and maintain long horizon mobility and tracking performance. Together, these results demonstrate that selective adversarial attacks are an effective driver for learning robust, long horizon humanoid motion skills.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
