MoE-Loco: 面向多任务运动的专家混合模型
MoE-Loco: Mixture of Experts for Multitask Locomotion
AI总结：
本研究提出足式机器人多任务运动框架MoE-Loco，通过专家混合模型缓解多任务强化学习梯度冲突，支持多地形与双/四足步态，经仿真与实机验证具备鲁棒性与适应性，可实现任务迁移与技能组合。
摘要：
我们提出了MoE-Loco，一种用于足式机器人多任务运动的专家混合（Mixture of Experts，MoE）框架。该方法使单个策略能够应对包括横杆、凹坑、楼梯、斜坡和挡板在内的多种地形，同时支持四足和双足步态。借助MoE，我们缓解了多任务强化学习中常见的梯度冲突问题，提升了训练效率与性能。实验表明，不同专家会自然形成不同运动行为的专长，可用于任务迁移和技能组合。我们还在仿真和真实部署中验证了该方法，展现了其鲁棒性与适应性。
英文摘要：
We present MoE-Loco, a Mixture of Experts (MoE) framework for multitask locomotion for legged robots. Our method enables a single policy to handle diverse terrains, including bars, pits, stairs, slopes, and baffles, while supporting quadrupedal and bipedal gaits. Using MoE, we mitigate the gradient conflicts that typically arise in multitask reinforcement learning, improving both training efficiency and performance. Our experiments demonstrate that different experts naturally specialize in distinct locomotion behaviors, which can be leveraged for task migration and skill composition. We further validate our approach in both simulation and real-world deployment, showcasing its robustness and adaptability.
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。
