An Evolutionary Multiobjective Carpool Algorithm Using Set-Based Operator Based on Simulated Binary Crossover

Sharing vehicle journeys with other passengers can provide many benefits, such as reducing traffic congestion and making urban transportation more environmentally friendly. For the procedure of sharing empty seats, we need to consider increased ridership and driving distances incurred by carpool detours resulting from matching passengers to drivers, as well as maximizing the number of simultaneous matches. In accordance with these goals, this paper proposes and defines the multiobjective optimization carpool service problem (MOCSP). Previous studies have used evolutionary algorithms by combining multiple objectives into a single objective through a weighted linear or/and nonlinear combination of different objectives, thus turning to a single-objective optimization problem. These single-objective problems are optimized, but there is no guarantee of the performance of the respective objectives. By improving the individual representation and genetic operation, we developed a set-based simulated binary and multiobjective carpool matching algorithm that can more effectively solve MOCSP. Furthermore, the proposed algorithm can provide better driver-passenger matching results than can the binary-coded and set-based nondominated sorting genetic algorithms.