RT Journal Article SR Electronic T1 Multi-expert learning of adaptive legged locomotion JF Science Robotics JO Sci. Robotics FD American Association for the Advancement of Science SP eabb2174 DO 10.1126/scirobotics.abb2174 VO 5 IS 49 A1 Yang, Chuanyu A1 Yuan, Kai A1 Zhu, Qiuguo A1 Yu, Wanming A1 Li, Zhibin YR 2020 UL http://robotics.sciencemag.org/content/5/49/eabb2174.abstract AB 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.