Dynamics and Domain Randomized Gait Modulation with Bezier Curves for Sim-to-Real Legged Locomotion

10/22/2020
by   Maurice Rahme, et al.
0

We present a sim-to-real framework that uses dynamics and domain randomized offline reinforcement learning to enhance open-loop gaits for legged robots, allowing them to traverse uneven terrain without sensing foot impacts. Our approach, D^2-Randomized Gait Modulation with Bezier Curves (D^2-GMBC), uses augmented random search with randomized dynamics and terrain to train, in simulation, a policy that modifies the parameters and output of an open-loop Bezier curve gait generator for quadrupedal robots. The policy, using only inertial measurements, enables the robot to traverse unknown rough terrain, even when the robot's physical parameters do not match the open-loop model. We compare the resulting policy to hand-tuned Bezier Curve gaits and to policies trained without randomization, both in simulation and on a real quadrupedal robot. With D^2-GMBC, across a variety of experiments on unobserved and unknown uneven terrain, the robot walks significantly farther than with either hand-tuned gaits or gaits learned without domain randomization. Additionally, using D^2-GMBC, the robot can walk laterally and rotate while on the rough terrain, even though it was trained only for forward walking.

READ FULL TEXT

Authors

page 1

page 4

page 6

11/04/2020

Dynamics Randomization Revisited:A Case Study for Quadrupedal Locomotion

Understanding the gap between simulation andreality is critical for rein...
12/30/2019

Gait Library Synthesis for Quadruped Robots via Augmented Random Search

In this paper, with a view toward fast deployment of learned locomotion ...
03/29/2021

Rough-Terrain Locomotion and Unilateral Contact Force Regulations With a Multi-Modal Legged Robot

Despite many accomplishments by legged robot designers, state-of-the-art...
06/27/2022

Learning Semantics-Aware Locomotion Skills from Human Demonstration

The semantics of the environment, such as the terrain type and property,...
12/13/2021

Teaching a Robot to Walk Using Reinforcement Learning

Classical control techniques such as PID and LQR have been used effectiv...
11/03/2020

Policy Transfer via Kinematic Domain Randomization and Adaptation

Transferring reinforcement learning policies trained in physics simulati...
06/29/2022

Online vs. Offline Adaptive Domain Randomization Benchmark

Physics simulators have shown great promise for conveniently learning re...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.