Collision-Backpropagation based Obstacle Avoidance Method for a Legged Robot Expressed as a Simplified Dynamics Model

Simplified dynamics models have been widely adopted to reduce the computational complexity of motion planning for legged robots. However, not much research has been conducted on the collision avoidance for a simplified dynamics model. To contribute to this problem, we present the collision-backpropa...

Full description

Saved in:
Bibliographic Details
Main Authors: Kim, Jinwon, Shin, Heechan, Yoon, Sung-Eui
Format: Conference Proceeding
Language:English
Subjects:
Collision avoidance
Computational modeling
Costs
Dynamics
End effectors
Learning systems
Legged locomotion
Planning
Simplified dynamics
Trajectory optimization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Simplified dynamics models have been widely adopted to reduce the computational complexity of motion planning for legged robots. However, not much research has been conducted on the collision avoidance for a simplified dynamics model. To contribute to this problem, we present the collision-backpropagation based obstacle avoidance method (CBOA), in which we employ the gradient flow of the collision cost to optimize the trajectory, thus avoiding collisions with obstacles. Our experiment shows that the CBOA reduces the collision rate of planned trajectories by up to 15.89 times compared to a previous implicit collision avoidance method.
ISSN:2642-3901
DOI:10.23919/ICCAS55662.2022.10003733