A Two-Phase Safe Vehicle Routing and Scheduling Problem: Formulations and Solution Algorithms

TL;DR

This paper introduces a two-phase vehicle routing and scheduling model prioritizing safety over traditional metrics, using mixed-integer programming and simulated annealing to optimize routes and departure times considering congestion and crash risks.

Contribution

The paper presents a novel two-phase model that explicitly incorporates safety considerations into vehicle routing and scheduling, with a tailored solution algorithm for complex, dynamic networks.

Findings

The proposed model effectively identifies safer routes compared to traditional shortest-distance methods.

The modified simulated annealing algorithm provides solutions efficiently within short computation times.

Results demonstrate improved safety metrics and congestion avoidance in dynamic roadway networks.

Abstract

We propose a two phase time dependent vehicle routing and scheduling optimization model that identifies the safest routes, as a substitute for the classical objectives given in the literature such as shortest distance or travel time, through (1) avoiding recurring congestions, and (2) selecting routes that have a lower probability of crash occurrences and non-recurring congestion caused by those crashes. In the first phase, we solve a mixed-integer programming model which takes the dynamic speed variations into account on a graph of roadway networks according to the time of day, and identify the routing of a fleet and sequence of nodes on the safest feasible paths. Second phase considers each route as an independent transit path (fixed route with fixed node sequences), and tries to avoid congestion by rescheduling the departure times of each vehicle from each node, and by adjusting the sub-optimal speed on each arc. A modified simulated annealing (SA) algorithm is formulated to solve both complex models iteratively, which is found to be capable of providing solutions in a considerably short amount of time.