用自动调参技术提升机器人走路控制，显著缩小仿真与现实差距
Autotuning Bipedal Locomotion MPC with GRFM-Net for Efficient Sim-to-Real Transfer
- 通过可微编程自动优化行走控制参数，避免人工调参
- 结合地面反力网络补偿仿真误差，使真实机器人行走损失降低40.5%
- 适合研究机器人控制、仿真到现实迁移的工程师和研究员
双足行走控制对人形机器人在复杂人机环境中的导航至关重要。尽管基于优化的控制设计能整合复杂的机器人模型，但通常需要大量手动调参。本文提出DiffTune，一种基于模型的自动调参方法，利用可微编程实现高效参数学习。主要挑战在于模型保真度与可微性之间的平衡。我们采用低保真模型保证可微性，并引入地面反力与力矩网络（GRFM-Net）捕捉MPC指令与实际控制效果之间的差异。在硬件实验中验证了DiffTune+GRFM-Net学习的参数，在多目标设定下优于基线参数，总损失相比专家调参减少高达40.5%。结果证实GRFM-Net有效缓解了仿真到现实的差距，提升了仿真学习参数在真实硬件上的迁移能力。
原文摘要 · Abstract (English)
Bipedal locomotion control is essential for humanoid robots to navigate complex, human-centric environments. While optimization-based control designs are popular for integrating sophisticated models of humanoid robots, they often require labor-intensive manual tuning. In this work, we address the challenges of parameter selection in bipedal locomotion control using DiffTune, a model-based autotuning method that leverages differential programming for efficient parameter learning. A major difficulty lies in balancing model fidelity with differentiability. We address this difficulty using a low-fidelity model for differentiability, enhanced by a Ground Reaction Force-and-Moment Network (GRFM-Net) to capture discrepancies between MPC commands and actual control effects. We validate the parameters learned by DiffTune with GRFM-Net in hardware experiments, which demonstrates the parameters' optimality in a multi-objective setting compared with baseline parameters, reducing the total loss by up to 40.5$\%$ compared with the expert-tuned parameters. The results confirm the GRFM-Net's effectiveness in mitigating the sim-to-real gap, improving the transferability of simulation-learned parameters to real hardware.
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。