2021 · 200 citations · 33 references
EngineeringComputer ScienceRobotics EngineeringHumanoid RoboticsRobot ControlRoboticsBipedal LocomotionLegged LocomotionLegged RoboticsPolicy LearningReinforcement LearningSim-to-real TransferDomain RandomizationLocomotion Policy LearningModel-free Locomotion LearningModel-free Reinforcement LearningReinforcement Learning For LocomotionReinforcement Learning TransferRobust LocomotionTransfer Learning For Locomotion
Developing robust walking controllers for bipedal robots is a challenging endeavor. Traditional model-based locomotion controllers require simplifying assumptions and careful modelling; any small errors can result in unstable control. To address these challenges for bipedal locomotion, we present a model-free reinforcement learning framework for training robust locomotion policies in simulation, which can then be transferred to a real bipedal Cassie robot. To facilitate sim-to-real transfer, domain randomization is used to encourage the policies to learn behaviors that are robust across variations in system dynamics. The learned policies enable Cassie to perform a set of diverse and dynamic behaviors, while also being more robust than traditional controllers and prior learning-based methods that use residual control. We demonstrate this on versatile walking behaviors such as tracking a target walking velocity, walking height, and turning yaw. (Video <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> )
33
MuJoCo: A physics engine for model-based control
Emanuel Todorov, Tom Erez, Yuval Tassa · 2012 · 4.4K citations
Engineering, Mechanical Engineering, Robotics Engineering +17
Domain randomization for transferring deep neural networks from simulation to the real world
Josh Tobin, Rachel Fong, Alex Ray et al. · 2017 · 2.8K citations
Learning agile and dynamic motor skills for legged robots
Jemin Hwangbo, Joonho Lee, Alexey Dosovitskiy et al. · Science Robotics · 2019 · 1.4K citations · Full text