Sim-to-Real: Learning Agile Locomotion For Quadruped Robots

Citations Over TimeTop 1% of 2018 papers

Abstract

Designing agile locomotion for quadruped robots often requires extensive expertise and tedious manual tuning. In this paper, we present a system to automate this process by leveraging deep reinforcement learning techniques. Our system can learn quadruped locomotion from scratch using simple reward signals. In addition, users can provide an open loop reference to guide the learning process when more control over the learned gait is needed. The control policies are learned in a physics simulator and then deployed on real robots. In robotics, policies trained in simulation often do not transfer to the real world. We narrow this reality gap by improving the physics simulator and learning robust policies. We improve the simulation using system identification, developing an accurate actuator model and simulating latency. We learn robust controllers by randomizing the physical environments, adding perturbations and designing a compact observation space. We evaluate our system on two agile locomotion gaits: trotting and galloping. After learning in simulation, a quadruped robot can successfully perform both gaits in the real world.

Related Papers

• → Adopting SAFe to Scale Agile in a Globally Distributed Organization(2017)104 cited
• → A Deep Reinforcement Learning Strategy for UAV Autonomous Landing on a Platform(2022)15 cited
• → Performance of distributed multi-agent multi-state reinforcement spectrum management using different exploration schemes(2013)13 cited
• → Cost-Efficient Reinforcement Learning for Optimal Trade Execution on Dynamic Market Environment(2022)2 cited
• → Classification without gradients: multi-agent reinforcement learning approach to optimization (Conference Presentation)(2023)