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

by   Maurice Rahme, et al.

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.


page 1

page 4

page 6


Dynamics Randomization Revisited:A Case Study for Quadrupedal Locomotion

Understanding the gap between simulation andreality is critical for rein...

Snake Robot Gait Decomposition and Gait Parameter Optimization

This paper proposes Gait Decomposition (G.D), a method of mathematically...

Gait Library Synthesis for Quadruped Robots via Augmented Random Search

In this paper, with a view toward fast deployment of learned locomotion ...

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...

Cyclic Policy Distillation: Sample-Efficient Sim-to-Real Reinforcement Learning with Domain Randomization

Deep reinforcement learning with domain randomization learns a control p...

Learning Semantics-Aware Locomotion Skills from Human Demonstration

The semantics of the environment, such as the terrain type and property,...

Online vs. Offline Adaptive Domain Randomization Benchmark

Physics simulators have shown great promise for conveniently learning re...

Please sign up or login with your details

Forgot password? Click here to reset