Learning Agile Paths from Optimal Control

TL;DR

This paper introduces a machine learning approach trained on optimal control outputs to improve motion planning efficiency for agile robots, balancing optimality and computational feasibility.

Contribution

It presents a novel method that leverages optimal control solutions to train models for faster, more efficient motion planning in complex robotic environments.

Findings

Improved planning speed for agile robots

Maintains near-optimal motion solutions

Balances complexity and computational efficiency

Abstract

Efficient motion planning algorithms are of central importance for deploying robots in the real world. Unfortunately, these algorithms often drastically reduce the dimensionality of the problem for the sake of feasibility, thereby foregoing optimal solutions. This limitation is most readily observed in agile robots, where the solution space can have multiple additional dimensions. Optimal control approaches partially solve this problem by finding optimal solutions without sacrificing the complexity of the environment, but do not meet the efficiency demands of real-world applications. This work proposes an approach to resolve these issues simultaneously by training a machine learning model on the outputs of an optimal control approach.