Prediction of Bottleneck Points for Manipulation Planning in Cluttered Environment using a 3D Convolutional Neural Network

TL;DR

This paper introduces a 3D CNN-based method to identify bottleneck regions in cluttered environments, guiding RRT* planning to improve efficiency and generalize to new problems in industrial robotics.

Contribution

It proposes a novel bottleneck detection technique using 3D CNNs to enhance sampling-based motion planning in unstructured environments.

Findings

Significant reduction in planning time and memory usage.

Effective generalization to unseen problem instances.

Improved convergence of RRT* in cluttered environments.

Abstract

Latest research in industrial robotics is aimed at making human robot collaboration possible seamlessly. For this purpose, industrial robots are expected to work on the fly in unstructured and cluttered environments and hence the subject of perception driven motion planning plays a vital role. Sampling based motion planners are proven to be the most effective for such high dimensional planning problems with real time constraints. Unluckily random stochastic samplers suffer from the phenomenon of 'narrow passages' or bottleneck regions which need targeted sampling to improve their convergence rate. Also identifying these bottleneck regions in a diverse set of planning problems is a challenge. In this paper an attempt has been made to address these two problems by designing an intelligent 'bottleneck guided' heuristic for a Rapidly Exploring Random Tree Star (RRT*) planner which is based on relevant context extracted from the planning scenario using a 3D Convolutional Neural Network and it is also proven that the proposed technique generalises to unseen problem instances. This paper benchmarks the technique (bottleneck guided RRT*) against a 10% Goal biased RRT star planner, shows significant improvement in planning time and memory requirement and uses ABB 1410 industrial manipulator as a platform for implantation and validation of the results.