A Configuration-Space Decomposition Scheme for Learning-based Collision Checking

11/17/2019
by   Yiheng Han, et al.
0

Motion planning for robots of high degrees-of-freedom (DOFs) is an important problem in robotics with sampling-based methods in configuration space C as one popular solution. Recently, machine learning methods have been introduced into sampling-based motion planning methods, which train a classifier to distinguish collision free subspace from in-collision subspace in C. In this paper, we propose a novel configuration space decomposition method and show two nice properties resulted from this decomposition. Using these two properties, we build a composite classifier that works compatibly with previous machine learning methods by using them as the elementary classifiers. Experimental results are presented, showing that our composite classifier outperforms state-of-the-art single classifier methods by a large margin. A real application of motion planning in a multi-robot system in plant phenotyping using three UR5 robotic arms is also presented.

READ FULL TEXT

page 2

page 4

page 6

research
07/25/2018

Quotient-Space Motion Planning

A motion planning algorithm computes the motion of a robot by computing ...
research
01/30/2018

Analysis of Motion Planning by Sampling in Subspaces of Progressively Increasing Dimension

Despite the performance advantages of modern sampling-based motion plann...
research
11/15/2022

A Survey on the Integration of Machine Learning with Sampling-based Motion Planning

Sampling-based methods are widely adopted solutions for robot motion pla...
research
07/02/2021

A Levy Flight based Narrow Passage Sampling Method for Probabilistic Roadmap Planners

Sampling based probabilistic roadmap planners (PRM) have been successful...
research
03/03/2019

dRRT*: Scalable and Informed Asymptotically-Optimal Multi-Robot Motion Planning

Many exciting robotic applications require multiple robots with many deg...
research
03/18/2022

Comparing SONN Types for Efficient Robot Motion Planning in the Configuration Space

Motion planning in the configuration space (C-space) induces benefits, s...
research
11/19/2018

Predictive and Semantic Layout Estimation for Robotic Applications in Manhattan Worlds

This paper describes an approach to automatically extracting floor plans...

Please sign up or login with your details

Forgot password? Click here to reset