Authors:
Fei Peng
1
;
Amy M. Cohn
1
;
Oleg Gusikhin
2
and
David Perner
2
Affiliations:
1
University of Michigan, United States
;
2
Ford Motor Company, United States
Keyword(s):
Vehicle Routing Problem, Heterogeneous Feet, Heuristics.
Abstract:
In the classical Vehicle Routing Problem (VRP) literature, as well as in most VRP commercial software
packages, it is commonly assumed that all vehicles are identical in their characteristics. In real-world problems
however, this is often not true. In many cases, fleets are made up of different vehicle types, which may vary by
size, engine/fuel type, and other performance-impacting factors. Even in a homogeneous fleet, vehicles often
differ by age and condition, which can greatly impact performance. Our research was specifically motivated
by cases where the fleet contains vehicles that not only vary in performance, but this variation is a function of
the arc type, such that a given vehicle might have lower cost on some arcs but higher cost on others. We refer
to this as the Hybrid Fleet Vehicle Routing Problem (HFVRP). We propose two heuristic methods that take
into account the vehicle-specific cost structures. We provide computational results to demonstrate the quality
of our soluti
ons, as well as a comparison with a Genetic Algorithm (GA) based method seen in the literature.
(More)