Teleoperated or remote-controlled driving complements automated driving and acts as transitional technology toward full automation. An economic advantage of teleoperated driving in logistics operations lies in managing fleets with fewer teleoperators compared to vehicles with in-vehicle drivers. This alleviates growing truck driver shortage problems in the logistics industry and saves costs. However, a trade-off exists between the teleoperator-to-vehicle ratio and the service level of teleoperation. This study designs a simulation framework to explore this trade-off generating multiple performance indicators as proxies for teleoperation service level. By applying the framework, we identify factors influencing the trade-off and optimal teleoperator-to-vehicle ratios under different scenarios. Our case study on road freight tours in The Netherlands reveals that for any operational setting, a teleoperation-to-vehicle ratio below one can manage all freight truck tours without delay, while one represents the current situation. The minimum teleoperator-to-vehicle ratio for zero-delay operations is never above 0.6, implying a minimum of 40% teleoperation labor cost saving. For operations where a small delay is allowed, teleoperator-to-vehicle ratios as low as 0.4 are shown to be feasible, which indicates potential savings of up to 60%. This confirms great promise for a positive business case for the teleoperated driving as a service.

This study proposes a hybrid deep-learning-metaheuristic framework with a bi-level architecture for road network design problems (NDPs). We train a graph neural network (GNN) to approximate the solution of the user equilibrium (UE) traffic assignment problem and use inferences made by the trained model to calculate fitness function evaluations of a genetic algorithm (GA) to approximate solutions for NDPs. Using three test networks, two NDP variants and an exact solver as benchmark, we show that on average, our proposed framework can provide solutions within 1.5% gap of the best results in less than 0.5% of the time used by the exact solution procedure. Our framework can be utilized within an expert system for infrastructure planning to determine the best infrastructure planning and management decisions under different scenarios. Given the flexibility of the framework, it can easily be adapted to many other decision problems that can be modeled as bi-level problems on graphs. Moreover, we foreseen interesting future research directions, thus we also put forward a brief research agenda for this topic. The key observation from our research that can shape future research is that the fitness function evaluation time using the inferences made by the GNN model was in the order of milliseconds, which points to an opportunity and a need for novel heuristics that 1) can cope well with noisy fitness function values provided by deep learning models, and 2) can use the significantly enlarged efficiency of the evaluation step to explore the search space effectively (rather than efficiently). This opens a new avenue for a modern class of metaheuristics that are crafted for use with AI-powered predictors.