Pedestrian-aware supervisory control system interactive optimization of connected hybrid electric vehicles via fuzzy adaptive cost map and Bees Algorithm

Electrified vehicles are increasingly being seen as a means of mitigating the pressing concerns of traffic-related pollution. Due to the nature of engine-assisted vehicle exhaust systems, pedestrians in close proximity to these vehicles may experience events where specific emission concentrations are high enough to cause health effects. To minimize pedestrians’ exposure to vehicle emissions and pollutants nearby, we present a pedestrian-aware supervisory control system for connected hybrid electric vehicles by proposing an interactive optimization methodology. This optimization methodology combines a novel fuzzy adaptive cost map and the Bees Algorithm to optimize power-split control parameters. It enables the self-regulation of inter-objective weights of fuel and exhaust emissions based on the real-time pedestrian density information during the optimization process. The evaluation of the vehicle performance by using the proposed methodology is conducted on the realistic trip map involving pedestrian density information collected from the University College Dublin campus. Moreover, two bootstrap sampling techniques and effect of communication quality are both investigated in order to examine the robustness of the improved vehicle system. The results demonstrate that 14.42% mass of exhaust emissions can be reduced for the involved pedestrians, by using the developed fuzzy adaptive cost map.