Multi-Loco：通过强化学习增强的扩散模型统一多具身腿式运动
Multi-Loco: Unifying Multi-Embodiment Legged Locomotion via Reinforcement Learning Augmented Diffusion
AI总结：
针对不同形态腿式机器人运动策略难泛化的问题，提出结合形态无关扩散模型与RL优化残差策略的Multi-Loco框架，在仿真和真机实验中较标准PPO框架平均回报提升10.35%，验证了跨具身数据与复合生成架构的优势。
摘要：
由于观测/动作维度以及系统动力学的差异，在具有不同形态的多种腿式机器人之间泛化运动策略是一项关键挑战。在本研究中，我们提出了Multi-Loco，这是一种新颖的统一框架，将形态无关的生成式扩散模型与通过强化学习（RL）优化的轻量级残差策略相结合。扩散模型从多样的跨具身数据集中捕捉形态不变的运动模式，提升了泛化性和鲁棒性。残差策略在所有具身之间共享，对扩散模型生成的动作进行细化，增强了任务感知性能和实际部署的鲁棒性。我们在仿真和真实世界实验中，利用包含四种腿式机器人的丰富库评估了我们的方法。与采用PPO的标准RL框架相比，我们的方法——用扩散模型和残差项替换高斯策略——实现了10.35%的平均回报提升，在轮式双足运动任务中的增益最高可达13.57%。这些结果凸显了跨具身数据和复合生成架构在学习鲁棒、通用的运动技能方面的优势。
英文摘要：
Generalizing locomotion policies across diverse legged robots with varying morphologies is a key challenge due to differences in observation/action dimensions and system dynamics. In this work, we propose Multi-Loco, a novel unified framework combining a morphology-agnostic generative diffusion model with a lightweight residual policy optimized via reinforcement learning (RL). The diffusion model captures morphology-invariant locomotion patterns from diverse cross-embodiment datasets, improving generalization and robustness. The residual policy is shared across all embodiments and refines the actions generated by the diffusion model, enhancing task-aware performance and robustness for real-world deployment. We evaluated our method with a rich library of four legged robots in both simulation and real-world experiments. Compared to a standard RL framework with PPO, our approach -- replacing the Gaussian policy with a diffusion model and residual term -- achieves a 10.35% average return improvement, with gains up to 13.57% in wheeled-biped locomotion tasks. These results highlight the benefits of cross-embodiment data and composite generative architectures in learning robust, generalized locomotion skills.
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。
