SIL-RRT*: Learning Sampling Distribution through Self Imitation Learning

TL;DR

SIL-RRT* is a novel learning-based motion planning algorithm that uses neural networks to predict sampling distributions, improving efficiency and scalability in high-dimensional robotic motion planning tasks.

Contribution

It introduces SIL-RRT*, which extends RRT* with learned sampling distributions via deep neural networks, enhancing performance in complex environments.

Findings

Reduces number of samples needed compared to traditional methods

Successfully scales to high-dimensional and complex environments

Demonstrates efficiency in 2D and 3D motion planning tasks

Abstract

Efficiently finding safe and feasible trajectories for mobile objects is a critical field in robotics and computer science. In this paper, we propose SIL-RRT*, a novel learning-based motion planning algorithm that extends the RRT* algorithm by using a deep neural network to predict a distribution for sampling at each iteration. We evaluate SIL-RRT* on various 2D and 3D environments and establish that it can efficiently solve high-dimensional motion planning problems with fewer samples than traditional sampling-based algorithms. Moreover, SIL-RRT* is able to scale to more complex environments, making it a promising approach for solving challenging robotic motion planning problems.