With the challenge of great growing of transport diversity for the automobile enterprises, the het-erogeneous vehicle routing problem with multiple depots, multiple types of finished vehicles and multiple types of transport vehicles in finished vehicle logistics ( HVRPMD) is modelled and solved. A multi-objective optimization model for HVRPMD is presented considering loading constraints to minimize the total cost and minimize the number of transport vehicles. Then a hybrid heuristic algo-rithm based on genetic algorithm and particle swarm optimization ( GA-PSO) is developed. Moreo-ver, a case study is used to evaluate the effectiveness of this algorithm. By comparing the GA-PSO algorithm with the traditional GA algorithm, the simulation results demonstrate the proposed GA-PSO algorithm is able to better support the HVRPMD problem in practice. Contributions of the paper are the modelling and solving of a complex HVRPMD in logistics industry.