构建数据驱动流程，让机器人走路更自然且可直接部署。
Booster Lab: A Data-Centric Pipeline for Learning Deployable Humanoid Locomotion Policies
- 整合数据清洗、仿真适配与强化学习，提升动作可行性
- 在Booster T1上实现可部署的类人行走策略
- 适合机器人研发与仿生运动算法研究者
类人机器人运动学习不仅需要任务导向的控制策略，还需物理可行且自然的动作行为，以实现在真实机器人上的部署。然而，机器人可用的运动数据往往稀缺：原始人类示范可能不适用于机器人结构，开源动作片段质量参差，仿真生成的轨迹仍需验证可行性。为此，我们提出一种以数据为中心的训练与部署流程，集成动作数据清洗、真实到仿真模型适配、基于AMP的强化学习以及仿真到现实的部署。我们在Booster T1机器人上验证了该框架，并在Booster K1上进行了初步的跨平台验证。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。