Semi-autonomous Intersection Collision Avoidance through Job-shop Scheduling

TL;DR

This paper presents a supervisory system for intersection collision avoidance that models the problem as a job-shop scheduling task, enabling verification of potential collisions and intervention to prevent accidents.

Contribution

It introduces a novel approach translating intersection collision verification into a job-shop scheduling problem solvable by mixed-integer linear programming.

Findings

The supervisor effectively detects potential collisions in real-time.

The approach can be implemented using existing commercial solvers.

It provides a systematic method for collision avoidance at intersections.

Abstract

In this paper, we design a supervisor to prevent vehicle collisions at intersections. An intersection is modeled as an area containing multiple conflict points where vehicle paths cross in the future. At every time step, the supervisor determines whether there will be more than one vehicle in the vicinity of a conflict point at the same time. If there is, then an impending collision is detected, and the supervisor overrides the drivers to avoid collision. A major challenge in the design of a supervisor as opposed to an autonomous vehicle controller is to verify whether future collisions will occur based on the current drivers choices. This verification problem is particularly hard due to the large number of vehicles often involved in intersection collision, to the multitude of conflict points, and to the vehicles dynamics. In order to solve the verification problem, we translate the problem to a job-shop scheduling problem that yields equivalent answers. The job-shop scheduling problem can, in turn, be transformed into a mixed-integer linear program when the vehicle dynamics are first-order dynamics, and can thus be solved by using a commercial solver.