Comparison of Data-Driven Approaches to Configuration Space Approximation

05/24/2023
by   Gabriel Guo, et al.
0

Configuration spaces (C-spaces) are an essential component of many robot path-planning algorithms, yet calculating them is a time-consuming task, especially in spaces involving a large number of degrees of freedom (DoF). Here we explore a two-step data-driven approach to C-space approximation: (1) sample (i.e., explicitly calculate) a few configurations; (2) train a machine learning (ML) model on these configurations to predict the collision status of other points in the C-space. We studied multiple factors that impact this approximation process, including model representation, number of DoF (up to 42), collision density, sample size, training set distribution, and desired confidence of predictions. We conclude that XGBoost offers a significant time improvement over other methods, while maintaining low error rates, even in C-Spaces with over 14 DoF.

READ FULL TEXT

page 4

page 6

research
01/22/2019

Learning Configuration Space Belief Model from Collision Checks for Motion Planning

For motion planning in high dimensional configuration spaces, a signific...
research
01/22/2019

Estimating Configuration Space Belief from Collision Checks for Motion Planning

For motion planning in high dimensional configuration spaces, a signific...
research
10/14/2019

Neural Collision Clearance Estimator for Fast Robot Motion Planning

Collision checking is a well known bottleneck in sampling-based motion p...
research
04/10/2021

Efficient Path Planning in Narrow Passages via Closed-Form Minkowski Operations

Path planning has long been one of the major research areas in robotics,...
research
08/08/2022

Efficient Distance-Optimal Tethered Path Planning in Planar Environments: The Workspace Convexity

The main contribution of this paper is the proof of the convexity of the...
research
02/07/2020

Free Space of Rigid Objects: Caging, Path Non-Existence, and Narrow Passage Detection

In this work we propose algorithms to explicitly construct a conservativ...
research
09/10/2019

Inverse Ising inference from high-temperature re-weighting of observations

Maximum Likelihood Estimation (MLE) is the bread and butter of system in...

Please sign up or login with your details

Forgot password? Click here to reset