用专家混合模型让机器人一脑多用，稳跨各种地形
MoE-Loco: Mixture of Experts for Multitask Locomotion
- 用专家混合机制解决多任务训练时的梯度冲突
- 不同专家自动专攻特定运动行为，支持技能组合与迁移
- 在仿真和真实机器人上均表现稳定，适应性强
我们提出 MoE-Loco，一种用于足式机器人多任务行走的专家混合（MoE）框架。该方法使单一策略能应对多种地形，包括横杆、坑洞、台阶、斜坡和障碍物，并支持四足与双足步态。通过引入 MoE，有效缓解了多任务强化学习中的梯度冲突，提升训练效率与性能。实验表明，不同专家自然专注于特定行走行为，可用于任务迁移与技能组合。我们在仿真和真实机器人部署中验证了该方法的鲁棒性与适应性。
原文摘要 · Abstract (English)
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.
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。