Optimization of a Robotaxi Dispatch Problem in Pandemic Era

Autonomous driving has been successfully realized in particular areas such as logistics distribution centers, container terminals, and university campuses. Robotaxi could be another potential application in the near future. This work studies a robotaxi dispatch problem during the pandemic time. It proposes a multi-objective optimization model to minimize the number, waiting time, and driving distance of the robotaxis. Besides, a dispatch strategy is innovatively designed according to a defined severity degree of the pandemic. A virus infection rate can be decreased by reducing contact among passengers. A two-stage nondominated sorting genetic algorithm (NSGA-TS) is proposed to solve the problem. Three operations are used to generate offspring solutions, which can ensure the diversity of the population and speed up the convergence of the algorithm. The effectiveness of NSGA-TS is verified compared with two popular multi-objective optimization algorithms, i.e., multi-objective evolutionary algorithm based on decomposition (MOEA/D) and nondominated sorting genetic algorithm II (NSGA-II). Experimental results show that the proposed model performs well on the studied problem. It can reduce the virus infection rate by decreasing contact among passengers at different risk levels of the pandemic while accomplishing passenger orders. This work is conducive to society building intelligent transportation in the post-pandemic era.