Visual CPG-RL: Learning Central Pattern Generators for Visually-Guided Quadruped Locomotion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bellegarda, Guillaume, Shafiee, Milad, Ijspeert, Auke
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913260975947776
author Bellegarda, Guillaume
Shafiee, Milad
Ijspeert, Auke
author_facet Bellegarda, Guillaume
Shafiee, Milad
Ijspeert, Auke
contents We present a framework for learning visually-guided quadruped locomotion by integrating exteroceptive sensing and central pattern generators (CPGs), i.e. systems of coupled oscillators, into the deep reinforcement learning (DRL) framework. Through both exteroceptive and proprioceptive sensing, the agent learns to coordinate rhythmic behavior among different oscillators to track velocity commands, while at the same time override these commands to avoid collisions with the environment. We investigate several open robotics and neuroscience questions: 1) What is the role of explicit interoscillator couplings between oscillators, and can such coupling improve sim-to-real transfer for navigation robustness? 2) What are the effects of using a memory-enabled vs. a memory-free policy network with respect to robustness, energy-efficiency, and tracking performance in sim-to-real navigation tasks? 3) How do animals manage to tolerate high sensorimotor delays, yet still produce smooth and robust gaits? To answer these questions, we train our perceptive locomotion policies in simulation and perform sim-to-real transfers to the Unitree Go1 quadruped, where we observe robust navigation in a variety of scenarios. Our results show that the CPG, explicit interoscillator couplings, and memory-enabled policy representations are all beneficial for energy efficiency, robustness to noise and sensory delays of 90 ms, and tracking performance for successful sim-to-real transfer for navigation tasks. Video results can be found at https://youtu.be/wpsbSMzIwgM.
format Preprint
id arxiv_https___arxiv_org_abs_2212_14400
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Visual CPG-RL: Learning Central Pattern Generators for Visually-Guided Quadruped Locomotion
Bellegarda, Guillaume
Shafiee, Milad
Ijspeert, Auke
Robotics
Artificial Intelligence
Machine Learning
Systems and Control
We present a framework for learning visually-guided quadruped locomotion by integrating exteroceptive sensing and central pattern generators (CPGs), i.e. systems of coupled oscillators, into the deep reinforcement learning (DRL) framework. Through both exteroceptive and proprioceptive sensing, the agent learns to coordinate rhythmic behavior among different oscillators to track velocity commands, while at the same time override these commands to avoid collisions with the environment. We investigate several open robotics and neuroscience questions: 1) What is the role of explicit interoscillator couplings between oscillators, and can such coupling improve sim-to-real transfer for navigation robustness? 2) What are the effects of using a memory-enabled vs. a memory-free policy network with respect to robustness, energy-efficiency, and tracking performance in sim-to-real navigation tasks? 3) How do animals manage to tolerate high sensorimotor delays, yet still produce smooth and robust gaits? To answer these questions, we train our perceptive locomotion policies in simulation and perform sim-to-real transfers to the Unitree Go1 quadruped, where we observe robust navigation in a variety of scenarios. Our results show that the CPG, explicit interoscillator couplings, and memory-enabled policy representations are all beneficial for energy efficiency, robustness to noise and sensory delays of 90 ms, and tracking performance for successful sim-to-real transfer for navigation tasks. Video results can be found at https://youtu.be/wpsbSMzIwgM.
title Visual CPG-RL: Learning Central Pattern Generators for Visually-Guided Quadruped Locomotion
topic Robotics
Artificial Intelligence
Machine Learning
Systems and Control
url https://arxiv.org/abs/2212.14400