Zero-Shot Terrain Generalization for Visual Locomotion Policies

Legged robots have unparalleled mobility on unstructured terrains. However, it remains an open challenge to design locomotion controllers that can operate in a large variety of environments. In this paper, we address this challenge of automatically learning locomotion controllers that can generalize to a diverse collection of terrains often encountered in the real world. We frame this challenge as a multi-task reinforcement learning problem and define each task as a type of terrain that the robot needs to traverse. We propose an end-to-end learning approach that makes direct use of the raw exteroceptive inputs gathered from a simulated 3D LiDAR sensor, thus circumventing the need for ground-truth heightmaps or preprocessing of perception information. As a result, the learned controller demonstrates excellent zero-shot generalization capabilities and can navigate 13 different environments, including stairs, rugged land, cluttered offices, and indoor spaces with humans.

[1]  Marcin Andrychowicz,et al.  What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study , 2020, ArXiv.

[2]  Glen Berseth,et al.  DeepLoco , 2017, ACM Trans. Graph..

[3]  Atil Iscen,et al.  Policies Modulating Trajectory Generators , 2018, CoRL.

[4]  Marco Hutter,et al.  Gait and Trajectory Optimization for Legged Systems Through Phase-Based End-Effector Parameterization , 2018, IEEE Robotics and Automation Letters.

[5]  Lorenz Wellhausen,et al.  Learning quadrupedal locomotion over challenging terrain , 2020, Science Robotics.

[6]  Wojciech Czarnecki,et al.  Multi-task Deep Reinforcement Learning with PopArt , 2018, AAAI.

[7]  Alec Radford,et al.  Proximal Policy Optimization Algorithms , 2017, ArXiv.

[8]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[9]  Rich Caruana,et al.  Multitask Learning: A Knowledge-Based Source of Inductive Bias , 1993, ICML.

[10]  Sergey Levine,et al.  Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning , 2019, CoRL.

[11]  Sangbae Kim,et al.  MIT Cheetah 3: Design and Control of a Robust, Dynamic Quadruped Robot , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[12]  Yuval Tassa,et al.  Emergence of Locomotion Behaviours in Rich Environments , 2017, ArXiv.

[13]  Vladlen Koltun,et al.  Learning by Cheating , 2019, CoRL.

[14]  Jitendra Malik,et al.  Gibson Env: Real-World Perception for Embodied Agents , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[15]  Joonho Lee,et al.  DeepGait: Planning and Control of Quadrupedal Gaits Using Deep Reinforcement Learning , 2020, IEEE Robotics and Automation Letters.

[16]  Brett R Fajen,et al.  Visual control of foot placement when walking over complex terrain , 2014, Journal of experimental psychology. Human perception and performance.

[17]  Sergey Levine,et al.  High-Dimensional Continuous Control Using Generalized Advantage Estimation , 2015, ICLR.

[18]  Michael McCloskey,et al.  Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem , 1989 .

[19]  Sergey Levine,et al.  Learning to Walk in the Real World with Minimal Human Effort , 2020, CoRL.

[20]  Sergey Levine,et al.  Learning to Walk via Deep Reinforcement Learning , 2018, Robotics: Science and Systems.

[21]  Ruben Grandia,et al.  Feedback MPC for Torque-Controlled Legged Robots , 2019, 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[22]  Ye Zhao,et al.  Stabilizing Series-Elastic Point-Foot Bipeds Using Whole-Body Operational Space Control , 2016, IEEE Transactions on Robotics.

[23]  Atil Iscen,et al.  Sim-to-Real: Learning Agile Locomotion For Quadruped Robots , 2018, Robotics: Science and Systems.

[24]  Joonho Lee,et al.  Learning agile and dynamic motor skills for legged robots , 2019, Science Robotics.

[25]  Mary M. Hayhoe,et al.  Gaze and the Control of Foot Placement When Walking in Natural Terrain , 2018, Current Biology.

[26]  Keenan Albee,et al.  Real-time Motion Planning in Unknown Environments for Legged Robotic Planetary Exploration , 2020, 2020 IEEE Aerospace Conference.

[27]  Peter Fankhauser,et al.  Advances in real‐world applications for legged robots , 2018, J. Field Robotics.