Deep Neural Networks for Swept Volume Prediction Between Configurations

TL;DR

This paper introduces a deep neural network approach to rapidly estimate swept volume sizes for robotic configurations, significantly reducing computation time while maintaining accuracy, thus enhancing motion planning efficiency.

Contribution

The authors develop a DNN-based method to predict swept volume sizes for specific robots, achieving over 1500 times faster estimates than traditional algorithms.

Findings

DNN estimates closely match true swept volume sizes.

Method is over 1500 times faster than existing algorithms.

Applicable to different robot geometries, including 6 and 7 DOF robots.

Abstract

Swept Volume (SV), the volume displaced by an object when it is moving along a trajectory, is considered a useful metric for motion planning. First, SV has been used to identify collisions along a trajectory, because it directly measures the amount of space required for an object to move. Second, in sampling-based motion planning, SV is an ideal distance metric, because it correlates to the likelihood of success of the expensive local planning step between two sampled configurations. However, in both of these applications, traditional SV algorithms are too computationally expensive for efficient motion planning. In this work, we train Deep Neural Networks (DNNs) to learn the size of SV for specific robot geometries. Results for two robots, a 6 degree of freedom (DOF) rigid body and a 7 DOF fixed-based manipulator, indicate that the network estimations are very close to the true size of SV and is more than 1500 times faster than a state of the art SV estimation algorithm.