An Adaptable Approach to Learn Realistic Legged Locomotion without Examples

Abstract

Learning controllers that reproduce legged locomotion in nature has been a long-time goal in robotics and computer graphics. While yielding promising results, recent approaches are not yet flexible enough to be applicable to legged systems of different morphologies. This is partly because they often rely on precise motion capture references or elaborate learning environments that ensure the naturality of the emergent locomotion gaits but prevent generalization. This work proposes a generic approach for ensuring realism in locomotion by guiding the learning process with the spring-loaded inverted pendulum model as a reference. Leveraging on the exploration capacities of Reinforcement Learning (RL), we learn a control policy that fills in the information gap between the template model and full-body dynamics required to maintain stable and periodic locomotion. The proposed approach can be applied to robots of different sizes and morphologies and adapted to any RL technique and control architecture. We present experimental results showing that even in a model-free setup and with a simple reactive control architecture, the learned policies can generate realistic and energy-efficient locomotion gaits for a bipedal and a quadrupedal robot. And most importantly, this is achieved without using motion capture, strong constraints in the dynamics or kinematics of the robot, nor prescribing limb coordination. We provide supplemental videos for qualitative analysis of the naturality of the learned gaits.

arXiv commentAccepted to ICRA 2022

References in corpus (11)

• Soft Actor-Critic Algorithms and Applications
• Learning Quadrupedal Locomotion over Challenging Terrain
• Benchmarking Deep Reinforcement Learning for Continuous Control
• DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
• An Open Torque-Controlled Modular Robot Architecture for Legged Locomotion Research
• Learning Symmetric and Low-energy Locomotion
• Synthesis of Biologically Realistic Human Motion Using Joint Torque Actuation
• CARL: Controllable Agent with Reinforcement Learning for Quadruped Locomotion
• GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Model
• Towards General and Autonomous Learning of Core Skills: A Case Study in Locomotion
• Generalized Maximum Causal Entropy for Inverse Reinforcement Learning

Cited by in corpus (3)

• Leveraging Symmetry in RL-based Legged Locomotion Control
• On discrete symmetries of robotics systems: A group-theoretic and data-driven analysis
• Morphological Symmetries in Robotics