Achieving versatile robot locomotion requires motor skills that can adapt to previously unseen situations. We propose a multi-expert learning architecture (MELA) that learns to generate adaptive skills from a group of representative expert skills. During training, MELA is first initialized by a distinct set of pretrained experts, each in a separate deep neural network (DNN). Then, by learning the combination of these DNNs using a gating neural network (GNN), MELA can acquire more specialized experts and transitional skills across various locomotion modes. During runtime, MELA constantly blends multiple DNNs and dynamically synthesizes a new DNN to produce adaptive behaviors in response to changing situations. This approach leverages the advantages of trained expert skills and the fast online synthesis of adaptive policies to generate responsive motor skills during the changing tasks. Using one unified MELA framework, we demonstrated successful multiskill locomotion on a real quadruped robot that performed coherent trotting, steering, and fall recovery autonomously and showed the merit of multi-expert learning generating behaviors that can adapt to unseen scenarios.

实现多功能的机器人运动需要能够适应以前未见过的情况的运动技能。我们提出了一种多专家学习体系结构（MELA），该体系结构学会从一组具有代表性的专家技能中培养适应性技能。在训练过程中，首先由一组不同的经过预训练的专家来初始化MELA，每个专家都在单独的深度神经网络（DNN）中。然后，通过使用门控神经网络（GNN）学习这些DNN的组合，MELA可以在各种运动模式下获得更多的专业专家和过渡技能。在运行时，MELA不断混合多个DNN，并动态合成新的DNN，以响应不断变化的情况而产生自适应行为。这种方法利用了训练有素的专家技能的优势以及自适应策略的快速在线综合优势，可以在不断变化的任务中产生响应性的运动技能。使用一个统一的MELA框架，我们在一个真正的四足机器人上演示了成功的多技能运动，该四足机器人自动执行了连贯的小跑，转向和跌倒恢复，并展示了多专家学习生成行为的优点，这些行为可以适应看不见的情况。