MARCH: 模型辅助强化学习实现人形机器人稀疏立足点的感知控制
MARCH: Model-Assisted Reinforcement Learning for the Perceptive Control of Humanoids over Sparse Footholds
AI总结：
提出模型辅助强化学习框架，结合简化模型生成安全参考轨迹、基于控制李雅普诺夫函数的奖励引导教师策略训练以及视觉学生策略蒸馏，实现人形机器人在稀疏立足点上的稳健感知行走。
摘要：
在稀疏地形上的感知双足行走仍然是一个困难的挑战：基于模型的方法精确但对不确定性脆弱，而基于无模型的方法鲁棒但难以发现安全关键型行走所需的精确、受约束的运动，其中小错误可能导致灾难性故障。我们提出了一个模型辅助强化学习（RL）框架，通过三个步骤结合两种视角：（1）使用简化模型生成安全参考轨迹；（2）训练一个特权教师策略，该策略由围绕安全参考轨迹构建的控制李雅普诺夫函数（CLF）奖励引导；（3）将教师策略蒸馏为基于视觉的学生策略。我们表明，这种模型辅助过程产生了物理基础的运动，提高了样本效率，减少了对复杂学习课程的需求，并实现了更平滑的行走行为，同时在与无模型基线相当的踏脚石性能上。我们在仿真中验证了我们的方法，并展示了在Unitree G1人形机器人上成功部署，该机器人导航具有横向约束的稀疏立足点。
英文摘要：
Perceptive bipedal locomotion over sparse terrain remains a difficult challenge: model-based methods are precise but brittle to uncertainty, while model-free methods are robust but struggle to discover the precise, constrained motions required for safety-critical locomotion where small errors can cause catastrophic failures. We propose a model-assisted reinforcement learning (RL) framework that combines both perspectives in three steps: (1) generate a safe reference trajectory using simplified models; (2) train a privileged teacher policy guided by a control Lyapunov function (CLF) reward built around the safe reference trajectory; and (3) distill the teacher into a vision-based student policy. We show that this model-assistance procedure produces physically grounded locomotion, improving sample efficiency, reducing the need for a complex learning curriculum, and achieving smoother locomotion behavior alongside stepping stone performance comparable to model-free baselines. We validate our approach in simulation and demonstrate successful deployment on a Unitree G1 humanoid robot navigating sparse footholds with lateral constraints.
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。
