论文arXiv 2611.0885713 天前
STRIDE算法仅凭IMU实现人形机器人14分钟步态学习
本文由 AI 根据公开内容整理,可能有误,请以原文为准:STRIDE: Learning Humanoid Locomotion in Minutes with Acceleration-Based Rewards(arXiv 2611.08857)
核心内容
针对人形机器人强化学习依赖外部动捕或精密状态估计器的痛点,arXiv论文提出STRIDE方法,实现仅靠机载IMU的端到端步态学习。该方法摒弃传统速度跟踪奖励,改用指令加速度轮廓作为反馈信号。在Unitree G1与Booster T1人形机器人仿真测试中,STRIDE仅需14分钟采样数据即可完成行走策略收敛,相比未优化基线方案缩短至原耗时的四分之一以内。
技术架构上,STRIDE采用Off-policy RL算法XQC提升样本效率,并引入高增益关节位置控制器配合左右对称性数据增强策略。实验数据显示,这两项组件使训练过程中的跌倒次数减少81%,解决了纯加速度反馈下的早期探索不稳定问题。该方案验证了在缺乏绝对位姿真值条件下,通过动力学约束与算法工程优化实现快速Sim-to-Real迁移的可行性。
关键看点
- 纯IMU奖励机制:以指令加速度轮廓替代基底速度跟踪,彻底摆脱对外部动捕系统及复杂状态估计器的依赖
- 极速样本效率:在Unitree G1与Booster T1仿真环境中,仅需14分钟交互样本即可完成稳定行走策略学习
- 训练稳定性增强:结合XQC算法、高增益关节控制及对称性增强,使训练阶段机器人跌倒次数大幅降低81%
- 算法核心组件:采用Off-policy RL算法XQC,配合高增益关节位置控制器与左右对称性数据增强策略
工程与产业观察
STRIDE证明了在无外部真值条件下,通过重构奖励函数与算法工程优化可实现人形机器人分钟级步态冷启动。这对降低具身智能数据采集门槛、加速本体运动能力迭代具有显著工程价值,尤其适用于缺乏精密动捕设施的敏捷开发场景。
英文摘要 (Abstract)
Learning locomotion directly on a humanoid robot is a promising direction to avoid the sim-to-real gap. However, locomotion rewards in Reinforcement Learning (RL) typically track the base velocity, which cannot be measured onboard without an external motion capture system or well-calibrated state estimator. This is why we introduce \method{}, which learns humanoid locomotion from minutes of samples with a reward that only requires the onboard Inertial Measurement Unit (IMU). Instead of tracking the base velocity, STRIDE rewards the robot for following a commanded acceleration profile. To learn efficiently from this reward, we use the off-policy RL algorithm XQC and combine a high gain setting for the joint position controllers with left-right symmetry augmentation. In simulation, STRIDE learns to walk on the Unitree G1 and Booster T1 humanoids within 14 minutes of samples. Compared to learning without these two components, it reduces the falls during training by 81%, while without them the robot learns only in over an hour.
作者:Nico Bohlinger, Jan Peters
外部来源
本页事实对应的公开页面,以原文为准。(点击将离开本站)