Adaptive Optimal Multi‐Lane Fusion Control for a Two‐Dimensional Plane Vehicle Platoon With Prescribed Performance and Angle Constraints

We investigate adaptive optimal and non‐optimal multi‐lane fusion control for a two‐dimensional (2‐D) plane vehicle platoon under angle constraints and prescribed performance. Most existing optimal control methods are restricted to optimization criteria and lack flexibility in adjusting control structures. In contrast, the proposed strategy enables both optimal and non‐optimal control by employing a layered controller design. One part uses sliding mode control to achieve the desired prescribed performance while adhering to angle constraints. The other part incorporates optimal control, utilizing an adaptive dynamic programming (ADP) method with the actor‐critic (AC) strategy to minimize the performance index function related to sliding‐mode surfaces and control signals. The sliding mode component alone achieves non‐optimal control, ensuring multi‐lane fusion and vehicle platoon stability. When combined with the optimal control component, the vehicle platoon minimizes the performance index function, thus achieving optimal multi‐lane fusion control. Besides, the unmodeled dynamics in the follower vehicle model are approximated by the radial basis function neural networks (RBFNNs) with the updating laws derived from the gradient descent method. Finally, the effectiveness of the proposed strategy is verified through simulations and comparisons.