Booster Lab: 一种用于学习可部署人形机器人运动策略的数据中心化流水线
Booster Lab: A Data-Centric Pipeline for Learning Deployable Humanoid Locomotion Policies
AI总结:
提出一种数据中心化流水线,通过运动数据筛选、真实到仿真模型适配、基于AMP的强化学习和仿真到现实部署,解决人形机器人运动数据稀缺问题,并在Booster T1和K1机器人上验证。
摘要:
人形机器人运动学习不仅需要面向任务的控制策略,还需要能够转移到真实机器人的物理可行且自然的行为。然而,机器人可行的运动数据通常稀缺:原始的人类演示可能与机器人形态不兼容,开源片段质量参差不齐,仿真收集的机器人轨迹仍需可行性检查。为应对这些挑战,我们提出了一种数据中心化的训练和部署流水线,该流水线整合了运动数据筛选、真实到仿真模型适配、基于对抗运动先验(AMP)的强化学习以及仿真到现实部署。我们在Booster T1机器人上验证了该框架,并进一步在Booster K1上提供了初步的跨平台验证。
英文摘要:
Humanoid robot motion learning requires not only task-oriented control policies but also physically feasible and natural behaviors that can be transferred to real robots. However, robot-feasible motion data are often scarce: raw human demonstrations may be incompatible with the robot morphology, open-source clips vary in quality, and simulation-collected robot trajectories still require feasibility checking. To address these challenges, we propose a data-centric training and deployment pipeline that integrates motion data curation, real-to-sim model adaptation, AMP-based reinforcement learning, and sim-to-real deployment. We validate the framework on the Booster T1 robot and further provide preliminary cross-platform validation on Booster K1.
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。