Optimal Eco-Driving for Heavy Vehicle Platooning: An Iterative Learning-Based Integrated Speed Planning and Control Method

Eco-driving for vehicle platoons has attracted significant research interest due to its potential to improve traffic efficiency and reduce energy consumption by optimizing vehicle speed trajectories and inter-vehicle spacing. This paper presents a Data-Efficient Iterative Learning-based (DEIL) method for integrated speed planning and control, specifically designed for heavy-duty vehicle platoons. The proposed approach formulates the problem as a finite-horizon constrained optimization, that incorporates both a terminal energy cost and a time-domain-guided terminal safe constraint set. Unlike conventional optimization methods that rely on a one-time pre-planned reference speed, the DEIL leverages historical vehicle states and energy consumption data from previous iterations to approximate the terminal cost and constraint set, enabling closed-loop, data-efficient iterative learning. The approximated terminal energy cost decreases monotonically and converges, facilitating the derivation of an energy-optimal control strategy within a limited number of iterations. Moreover, the method integrates trajectory planning and tracking control without requiring predefined reference profiles. To improve computational efficiency, a dynamic programming (DP) strategy is employed to generate the initial feasible trajectory. Comparative analysis validates the proposed approach, demonstrating its effectiveness in producing energy-optimal trajectories and control strategies for heavy vehicle platooning.