Energy-Efficient Slithering Gait Exploration for a Snake-like Robot based on Reinforcement Learning

04/16/2019
by   Zhenshan Bing, et al.
0

Similar to their counterparts in nature, the flexible bodies of snake-like robots enhance their movement capability and adaptability in diverse environments. However, this flexibility corresponds to a complex control task involving highly redundant degrees of freedom, where traditional model-based methods usually fail to propel the robots energy-efficiently. In this work, we present a novel approach for designing an energy-efficient slithering gait for a snake-like robot using a model-free reinforcement learning (RL) algorithm. Specifically, we present an RL-based controller for generating locomotion gaits at a wide range of velocities, which is trained using the proximal policy optimization (PPO) algorithm. Meanwhile, a traditional parameterized gait controller is presented and the parameter sets are optimized using the grid search and Bayesian optimization algorithms for the purposes of reasonable comparisons. Based on the analysis of the simulation results, we demonstrate that this RL-based controller exhibits very natural and adaptive movements, which are also substantially more energy-efficient than the gaits generated by the parameterized controller. Videos are shown at bluehttps://videoviewsite.wixsite.com/rlsnakehttps://videoviewsite.wixsite.com/rlsnake.

READ FULL TEXT

page 5

page 6

research
03/08/2021

An Energy-Saving Snake Locomotion Gait Policy Using Deep Reinforcement Learning

Snake robots, comprised of sequentially connected joint actuators, have ...
research
03/08/2023

Energetic Analysis on the Optimal Bounding Gaits of Quadrupedal Robots

It is often overlooked by roboticists when designing locomotion controll...
research
08/31/2020

Control of a Nature-inspired Scorpion using Reinforcement Learning

A terrestrial robot that can maneuver rough terrain and scout places is ...
research
06/12/2023

Tuning Legged Locomotion Controllers via Safe Bayesian Optimization

In this paper, we present a data-driven strategy to simplify the deploym...
research
02/27/2020

Exploiting Variable Impedance for Energy Efficient Sequential Movements

Compliant robotics have seen successful applications in energy efficient...
research
11/01/2020

Bound Controller for a Quadruped Robot using Pre-Fitting Deep Reinforcement Learning

The bound gait is an important gait in quadruped robot locomotion. It ca...
research
03/29/2021

Mechanical design and fabrication of a kinetic sculpture with application to bioinspired drone design

Biologically-inspired robots are a very interesting and difficult branch...

Please sign up or login with your details

Forgot password? Click here to reset