Platoon optimal tracking control: An adaptive critic programming approach

Engineering notes

Key topics: autonomous driving, control. See the paper for implementation details and experimental results.

Chinese explanation / 中文解读

中文解读待补充：本站会优先为端到端自动驾驶、BEV感知、3D目标检测、轨迹预测、路径规划、LiDAR感知等高价值论文补充中文说明。

Original abstract

This paper addresses the optimal tracking control of nonlinear vehicle platoon systems under safety constraints using a single-critic-network adaptive dynamic programming (ADP) method. By integrating tracking errors and reference trajectory dynamics into an augmented system and embedding platoon safety distance constraints into the performance function, an optimization criterion balancing tracking accuracy and safety is established. A single critic neural network approximates the performance index, combined with policy iteration to solve the Hamilton-Jacobi-Bellman (HJB) equation, reducing computational complexity. Lyapunov theory proves the uniformly ultimately bounded stability of the closed-loop system and inter-vehicle spacing error constraints are analytically derived to ensure vehicle platoon stability. Simulations show that for a five-vehicle platoon converging from <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" overflow="scroll"> <mml:mrow> <mml:mn>2</mml:mn> <mml:mi mathvariant="normal">m</mml:mi> </mml:mrow> </mml:math> to <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" overflow="scroll"> <mml:mrow> <mml:mn>1</mml:mn> <mml:mi mathvariant="normal">m</mml:mi> </mml:mrow> </mml:math> spacing, inter-vehicle spacing errors remain within <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" overflow="scroll"> <mml:mrow> <mml:mo>±</mml:mo> <mml:mn>0</mml:mn> <mml:mo>.</mml:mo> <mml:mn>1</mml:mn> <mml:mi mathvariant="normal">m</mml:mi> </mml:mrow> </mml:math> , while longitudinal, lateral, and heading angle errors asymptotically converge.

Links and sources

• PDF from original source

Comments