Learning Agile Robotic Locomotion Skills by Imitating Animals
This addresses the problem of time-consuming manual controller design for roboticists, offering a more automated approach, though it appears incremental by building on existing imitation and domain adaptation techniques.
The paper tackles the challenge of automating the development of agile locomotion controllers for legged robots by introducing an imitation learning system that uses real-world animal motion data to synthesize diverse behaviors, achieving successful deployment on an 18-DoF quadruped robot for tasks like dynamic hops and turns.
Reproducing the diverse and agile locomotion skills of animals has been a longstanding challenge in robotics. While manually-designed controllers have been able to emulate many complex behaviors, building such controllers involves a time-consuming and difficult development process, often requiring substantial expertise of the nuances of each skill. Reinforcement learning provides an appealing alternative for automating the manual effort involved in the development of controllers. However, designing learning objectives that elicit the desired behaviors from an agent can also require a great deal of skill-specific expertise. In this work, we present an imitation learning system that enables legged robots to learn agile locomotion skills by imitating real-world animals. We show that by leveraging reference motion data, a single learning-based approach is able to automatically synthesize controllers for a diverse repertoire behaviors for legged robots. By incorporating sample efficient domain adaptation techniques into the training process, our system is able to learn adaptive policies in simulation that can then be quickly adapted for real-world deployment. To demonstrate the effectiveness of our system, we train an 18-DoF quadruped robot to perform a variety of agile behaviors ranging from different locomotion gaits to dynamic hops and turns.