Mining truck platooning patterns through massive trajectory data

Truck platooning refers to a series of trucks driving in close proximity via communication technologies, and it is considered one the most implementable systems connected automated vehicles, bringing huge energy savings safety improvements. Properly planning platoons evaluating potential truck are crucial trucking companies transportation authorities. This study proposes data mining approaches learn spontaneous patterns from massive trajectories. An enhanced map matching algorithm developed identify headings by using digital data, followed an adaptive spatial clustering detect trucks’ instantaneous co-moving sets. These sets then aggregated find network-wide maximum platoon duration size through frequent itemset for computational efficiency. The GPS were collected fleeting Liaoning Province, China performance measures spatiotemporal distribution visualization. Results show that approximately 36% can be coordinated speed adjustment without changing routes schedules. average distance ratios these platooned 9.6% 9.9%, respectively, leading 2.8% reduction total fuel consumption. also distinguishes optimal periods space headways national freeways trunk roads, prioritize road segments with high possibilities platooning. derived results reproducible, providing useful policy implications operational strategies large-scale roadside infrastructure construction.