Dynamic lane-changing strategy for autonomous articulated heavy vehicles considering vehicles stability in complex environments

Articulated heavy vehicles is the mainstay of inter-city freight transportation, and is the one of the most likely fields for the earliest practical applications of intelligent driving. Trajectory planning and tracking of lane change are critical technologies for Autonomous Articulated Heavy Vehicles (AAHVs). Characteristics of the AAHVs susceptible to stability problems resulting from the high height, long lengths, heavy load, and mutual coupling of tractor and trailer, combined the complex environments with the dynamic changes in the states of adjacent vehicles and road adhesion coefficient, pose a significant challenge in dynamic lane change for AAHVs. To address the above challenges, a framework is proposed to achieve the trajectory planning and tracking of dynamic lane change for AAHVs. For trajectory planning approach, the trajectory planning and replanning is optimized in the real-time safe range of the longitudinal length of the lane-changing trajectory to obtain the real-time reference trajectory, considering vehicle stability and lane-changing efficiency. The minimum longitudinal length of lane-changing trajectory is determined by the predictive model of AAHVs stability including swing-out, jack-knifing, and rollover, utilizing the Long Short-Term Memory (LSTM) neural network. The minimum longitudinal length, combined with the maximum length formed by the adjacent vehicles with dynamic states, forms the real-time safe range for lane-changing trajectory planning. For trajectory tracking approach, a tracking approach using model predictive control based on multipoint preview is proposed to achieve the real-time planned trajectory tracking. The effectiveness of the proposed strategy is evaluated by simulating an experimentally validated Trucksim model in complex environments to demonstrate the capability of the strategy in trajectory planning and tracking.