ZSL-RPPO: Zero-Shot Learning for Quadrupedal Locomotion in Challenging Terrains using Recurrent Proximal Policy Optimization
Authors:
- Yao ZhaoYZYao Zhao
- Tao WuTWTao Wu
- Yijie ZhuYZYijie Zhu
- Xiang LuXLXiang Lu
- Jun WangJWJun Wang
- Haitham Bou-AmmarHBHaitham Bou-Ammar
- Xinyu ZhangXZXinyu Zhang
- Peng DuPDPeng Du
Preprint
Abstract
We present ZSL-RPPO, an improved zero-shot learning architecture that overcomes the limitations of teacher-student neural networks and enables generating robust, reliable, and versatile locomotion for quadrupedal robots in challenging terrains. We propose a new algorithm RPPO (Recurrent Proximal Policy Optimization) that directly trains recurrent neural network in partially observable environments and results in more robust training using domain randomization. Our locomotion controller supports extensive perturbation across simulation-to-reality transfer for both intrinsic and extrinsic physical parameters without further fine-tuning. This can avoid the significant decline of student's performance during simulation-to-reality transfer and therefore enhance the robustness and generalization of the locomotion controller. We deployed our controller on the Unitree A1 and Aliengo robots in real environment and exteroceptive perception is provided by either a solid-state Lidar or a depth camera. Our locomotion controller was tested in various challenging terrains like slippery surfaces, Grassy Terrain, and stairs. Our experiment results and comparison show that our approach significantly outperforms the state-of-the-art.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Learning-Based Design and Control for Quadrupedal Robots With Parallel-Elastic ActuatorsIEEE Robotics and Automation Letters, 2023
- Transferring policy of deep reinforcement learning from simulation to reality for roboticsNature Machine Intelligence, 2022
- Learning robust perceptive locomotion for quadrupedal robots in the wildScience Robotics, 2022
- Reinforcement Learning versus Conventional Control for Controlling a Planar Bi-rotor Platform with Tail AppendageJournal of Intelligent & Robotic Systems, 2021
- Sim2Real in Robotics and Automation: Applications and ChallengesIEEE Transactions on Automation Science and Engineering, 2021
- Learning quadrupedal locomotion over challenging terrainScience Robotics, 2020
- Learning agile and dynamic motor skills for legged robotsScience Robotics, 2019
- Advances in real‐world applications for legged robotsJournal of Field Robotics, 2018
- Survey of Model-Based Reinforcement Learning: Applications on RoboticsJournal of Intelligent & Robotic Systems, 2017
- Optimal control of Markov processes with incomplete state informationJournal of Mathematical Analysis and Applications, 1965