Robot Parkour Learning
Authors:
- Jianren WangJWJianren Wang
- Christopher AtkesonCAChristopher Atkeson
- Hang ZhaoHZHang Zhao
Preprint
Abstract
Parkour is a grand challenge for legged locomotion that requires robots to overcome various obstacles rapidly in complex environments. Existing methods can generate either diverse but blind locomotion skills or vision-based but specialized skills by using reference animal data or complex rewards. However, autonomous parkour requires robots to learn generalizable skills that are both vision-based and diverse to perceive and react to various scenarios. In this work, we propose a system for learning a single end-to-end vision-based parkour policy of diverse parkour skills using a simple reward without any reference motion data. We develop a reinforcement learning method inspired by direct collocation to generate parkour skills, including climbing over high obstacles, leaping over large gaps, crawling beneath low barriers, squeezing through thin slits, and running. We distill these skills into a single vision-based parkour policy and transfer it to a quadrupedal robot using its egocentric depth camera. We demonstrate that our system can empower two different low-cost robots to autonomously select and execute appropriate parkour skills to traverse challenging real-world environments.Keywords
All Related Versions
This publication has 59 references indexed in Scilit:
- Neural Volumetric Memory for Visual Locomotion Control2023
- Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real World2022
- Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots2021
- Trajectory and foothold optimization using low-dimensional models for rough terrain locomotion2017
- Human‐in‐the‐loop Control of a Humanoid Robot for Disaster Response: A Report from the DARPA Robotics Challenge TrialsJournal of Field Robotics, 2015
- Design and architecture of the unified modular snake robot2012
- Real‐time localization and elevation mapping within urban search and rescue scenariosJournal of Field Robotics, 2007
- The effects of distant and on-line visual information on the control of approach phase and step over an obstacle during locomotionExperimental Brain Research, 2004
- Understanding the roles of vision in the control of human locomotionGait & Posture, 1997
- High-resolution terrain map from multiple sensor dataIEEE Transactions on Pattern Analysis and Machine Intelligence, 1992