Learning-based Preference Prediction for Constrained Multi-Criteria Path-Planning

TL;DR

This paper presents a learning-based approach that uses neural networks to predict uncertain criteria in multi-criteria path planning for autonomous ground vehicles, improving operational efficiency in off-road rescue scenarios.

Contribution

It introduces a novel framework combining offline simulation-trained neural networks with online path planning for multi-criteria optimization in AGV applications.

Findings

Reduces human intervention in AGV path planning

Achieves near-optimal paths with limited distance increase

Demonstrates effectiveness in realistic rescue scenarios

Abstract

Learning-based methods are increasingly popular for search algorithms in single-criterion optimization problems. In contrast, for multiple-criteria optimization there are significantly fewer approaches despite the existence of numerous applications. Constrained path-planning for Autonomous Ground Vehicles (AGV) is one such application, where an AGV is typically deployed in disaster relief or search and rescue applications in off-road environments. The agent can be faced with the following dilemma : optimize a source-destination path according to a known criterion and an uncertain criterion under operational constraints. The known criterion is associated to the cost of the path, representing the distance. The uncertain criterion represents the feasibility of driving through the path without requiring human intervention. It depends on various external parameters such as the physics of the vehicle, the state of the explored terrains or weather conditions. In this work, we leverage knowledge acquired through offline simulations by training a neural network model to predict the uncertain criterion. We integrate this model inside a path-planner which can solve problems online. Finally, we conduct experiments on realistic AGV scenarios which illustrate that the proposed framework requires human intervention less frequently, trading for a limited increase in the path distance.