论文arXiv 2611.191005 天前
Unitree H1-2基于采样MPC实现支撑探身,触及范围扩展50cm
本文由 AI 根据公开内容整理,可能有误,请以原文为准:Leaning Over to Reach Far-Away Objects(arXiv 2611.19100)
核心内容
针对人形机器人非结构化环境作业需求,研究团队在Unitree H1-2上验证了基于支撑的远距离抓取方案。该方案利用全身模型预测控制(MPC)主动借助环境稳定本体,突破了传统避碰策略限制。实验表明,机器人在仅依赖本地传感与标记点条件下,可将有效触及范围延伸约50cm,并在负载姿态下维持稳定超过4分钟,为在线接触丰富操作建立了实物基准。
技术层面采用采样式MPC算法,在笔记本电脑上实现34Hz实时推理并完成Sim-to-Real迁移。54组跨高度、多目标测试显示,目标到达率达89%,完整“探身-恢复”循环成功率为81%。研究证实动作的时间持久性与探索尺度是低采样预算下成功的关键,且交叉熵方法(CEM)在规划频率与模型失配工况下提供了最宽泛的稳定操作区域,相关代码与硬件细节已开源。
关键看点
- 工作空间扩展:通过主动环境支撑策略,Unitree H1-2有效触及范围较无支撑站立状态扩展约50cm,突破本体运动学极限。
- 实时控制性能:全身采样MPC控制器在笔记本端以34Hz运行,支持Sim-to-Real零样本迁移,负载姿态稳定保持超4分钟。
- 任务成功率:在6个目标位与3种桌高共54次试验中,目标到达率89%,完整探身及恢复循环成功率达81%。
- 算法鲁棒性:CEM规划器在低采样预算下表现最优,动作时间持久性与探索尺度被证实为决定实机成功率的核心因素。
工程与产业观察
该工作证明了低成本算力结合采样MPC即可实现人形机器人高难度接触操作,打破了全身控制对高频优化或昂贵传感器的依赖。其开源的Sim-to-Real流程与量化基准,为具身智能在非结构化场景下的长时序力控交互提供了可复现的工程范式,显著降低了接触丰富任务的落地门槛。
英文摘要 (Abstract)
We study supported reaching to extend a humanoid robot's workspace by bracing against the environment for stabilization using a straightforward yet capable whole-body model predictive control (MPC) approach, exclusively with local sensing and fiducial markers. While typical solutions for whole body humanoid control aim at avoiding or accommodating contact, contact is explicitly required to reach objects placed on surfaces far out of normal reach. We employ sampling-based MPC for whole-body leaning, bracing, reaching, and recovery on a Unitree H1-2 humanoid. The controller runs in real-time at 34 Hz on a laptop, transfers sim-to-real, extends reach by about 50 cm beyond the unbraced standing workspace, and sustains the loaded posture for over four minutes, before pose estimation drifts. The controller reaches the commanded target in 89% of trials and completes the full reach-and-recovery cycle in 81%, across 54 trials spanning six targets and three table heights. We further characterize why such a small real-time sampling budget is sufficient, finding that temporal persistence of sampled actions and exploration scale strongly govern success, while CEM provides the widest operating region over planning rate and model mismatch. These results establish a real-world baseline for online, contact-rich humanoid manipulation. Code, videos, and full hardware details are available at https://h12leaner.github.io/
作者:Allen Devaraj, William Xie, Nikolaus Correll
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)