An Adaptable Approach to Learn Realistic Legged Locomotion without Examples

10/28/2021
by   Daniel Ordonez-Apraez, et al.
0

Learning controllers that reproduce legged locomotion in nature has been a long-time goal in robotics and computer graphics. While yielding promising results, recent approaches are not yet flexible enough to be applicable to legged systems of different morphologies. This is partly because they often rely on precise motion capture references or elaborate learning environments that ensure the naturality of the emergent locomotion gaits but prevent generalization. This work proposes a generic approach for ensuring realism in locomotion by guiding the learning process with the spring-loaded inverted pendulum model as a reference. Leveraging on the exploration capacities of Reinforcement Learning (RL), we learn a control policy that fills in the information gap between the template model and full-body dynamics required to maintain stable and periodic locomotion. The proposed approach can be applied to robots of different sizes and morphologies and adapted to any RL technique and control architecture. We present experimental results showing that even in a model-free setup and with a simple reactive control architecture, the learned policies can generate realistic and energy-efficient locomotion gaits for a bipedal and a quadrupedal robot. And most importantly, this is achieved without using motion capture, strong constraints in the dynamics or kinematics of the robot, nor prescribing limb coordination. We provide supplemental videos for qualitative analysis of the naturality of the learned gaits.

READ FULL TEXT
research
04/20/2021

GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Model

Model-free reinforcement learning (RL) for legged locomotion commonly re...
research
12/11/2021

OstrichRL: A Musculoskeletal Ostrich Simulation to Study Bio-mechanical Locomotion

Muscle-actuated control is a research topic of interest spanning differe...
research
10/30/2021

Learning Coordinated Terrain-Adaptive Locomotion by Imitating a Centroidal Dynamics Planner

Dynamic quadruped locomotion over challenging terrains with precise foot...
research
01/24/2019

Distributed Learning of Decentralized Control Policies for Articulated Mobile Robots

State-of-the-art distributed algorithms for reinforcement learning rely ...
research
09/27/2018

Adaptive Tensegrity Locomotion on Rough Terrain via Reinforcement Learning

The dynamical properties of tensegrity robots give them appealing rugged...
research
05/15/2023

AcroMonk: A Minimalist Underactuated Brachiating Robot

Brachiation is a dynamic, coordinated swinging maneuver of body and arms...

Please sign up or login with your details

Forgot password? Click here to reset