Highway On-Ramp Truck Platooning Based on Deep Reinforcement Learning

The advancement of connected and automated trucks (CATs) offers a novel avenue for the freight industry to optimize fuel efficiency, enhance traffic flow, and bolster safety through platooning. Particularly at highway on-ramps, how to effectively form CAT platoons is a key research topic. Previous studies have not addressed the issue of platooning at on-ramps. Within mixed traffic conditions, the interference from human driven vehicle (HDV) notably complicates the platooning operation. In this process, the position, timing, and speed of CAT merging significantly affect energy consumption and traffic safety. Thus, this work introduces a hierarchical merging strategy with a dynamic mechanism for selecting optimal merging points. Its objective is to facilitate efficient autonomous CAT platooning at highway on-ramps while considering the interference of HDVs. Specifically, it uses a model-free deep reinforcement learning method that guides the platooning process by exploring optimal driving behaviors. It ensures the safety and efficiency of the CAT merging process. Furthermore, we incorporate a realistic vehicle dynamics model within our simulations. The proposed strategy can handle the variation of the CATs' initial positions and speeds at on-ramps, as well as interference caused by HDVs at highway mainline. The efficacy of the proposed strategy has been verified through a series of simulation experiments. The findings indicate that our strategy is capable of effectively orchestrating CAT platooning maneuvers at the highway on-ramps.