Real-time decision-making for autonomous vehicles under faults

TL;DR

This paper presents real-time decision-making strategies for autonomous vehicles facing faults, optimizing routing and maintenance to minimize mission completion time using mixed integer programming and Dijkstra's algorithm.

Contribution

It introduces a novel optimization framework for fault management in autonomous vehicle routing, combining two computational methods for improved efficiency.

Findings

Both methods demonstrate high computational efficiency.

The approaches are feasible for highway and urban scenarios.

Optimization reduces total mission time.

Abstract

This paper addresses the challenges of decision-making for autonomous vehicles under faults during a transport mission. A real-time decision-making problem of vehicle routing planning considering maintenance management is formulated as an optimization problem. The goal is to minimize the total time to finish the transport mission by selecting the optimal workshop to conduct the maintenance and the corresponding routes. Two methods are proposed to solve the optimization problem based on two methods of fundamental solutions: (1) Mixed Integer Programming; (2) Dijkstra's algorithm. We adapt these methods to solve the optimization problem and consider improving the computation efficiency. Numerical studies of test cases of highway and urban scenarios are presented to demonstrate the proposed methods, which show the feasibility and high computational efficiency of both methods.