Meta-Reinforcement Learning for Adaptive Motor Control in Changing Robot Dynamics and Environments

01/19/2021
by   Timothée Anne, et al.
21

This work developed a meta-learning approach that adapts the control policy on the fly to different changing conditions for robust locomotion. The proposed method constantly updates the interaction model, samples feasible sequences of actions of estimated the state-action trajectories, and then applies the optimal actions to maximize the reward. To achieve online model adaptation, our proposed method learns different latent vectors of each training condition, which are selected online given the newly collected data. Our work designs appropriate state space and reward functions, and optimizes feasible actions in an MPC fashion which are then sampled directly in the joint space considering constraints, hence requiring no prior design of specific walking gaits. We further demonstrate the robot's capability of detecting unexpected changes during interaction and adapting control policies quickly. The extensive validation on the SpotMicro robot in a physics simulation shows adaptive and robust locomotion skills under varying ground friction, external pushes, and different robot models including hardware faults and changes.

READ FULL TEXT

page 1

page 5

page 6

page 7

research
09/26/2020

Complementary Meta-Reinforcement Learning for Fault-Adaptive Control

Faults are endemic to all systems. Adaptive fault-tolerant control maint...
research
03/22/2019

Iterative Reinforcement Learning Based Design of Dynamic Locomotion Skills for Cassie

Deep reinforcement learning (DRL) is a promising approach for developing...
research
11/09/2020

Learning Task Space Actions for Bipedal Locomotion

Recent work has demonstrated the success of reinforcement learning (RL) ...
research
09/16/2022

Value Summation: A Novel Scoring Function for MPC-based Model-based Reinforcement Learning

This paper proposes a novel scoring function for the planning module of ...
research
10/23/2020

Robust Planning and Control for Dynamic Quadrupedal Locomotion with Adaptive Feet

In this paper, we aim to improve the robustness of dynamic quadrupedal l...
research
07/16/2019

Adaptive Prior Selection for Repertoire-based Online Learning in Robotics

Among the data-efficient approaches for online adaptation in robotics (m...
research
08/31/2023

A Policy Adaptation Method for Implicit Multitask Reinforcement Learning Problems

In dynamic motion generation tasks, including contact and collisions, sm...

Please sign up or login with your details

Forgot password? Click here to reset