基于ACT-R的智能车动态优化方法  

ACT-R based dynamic trajectory optimization method for intelligent vehicles

作　　者：李爱娟[1,2] 李舜酩[2] 沈峘[2] 缪小冬[2] 

机构地区：[1]山东交通学院汽车工程学院,济南250023 [2]南京航空航天大学能源与动力学院,南京210016

出　　处：《吉林大学学报（工学版）》2013年第5期1184-1189,共6页Journal of Jilin University:Engineering and Technology Edition

基　　金：中国博士后科学基金项目(2011M500917);江苏省博士后科研计划项目(1101153C);江苏省普通高校研究生科研创新计划项目(CXLX11_0180)

摘　　要：为了使智能车辆在不同道路环境中能够顺利沿规划轨迹行驶,提出一种新的基于认知结构ACT-R的动态轨迹优化方法。该方法将数学工具最优控制方法和ACT-R模型联系起来,以ACT-R模型为核心,用最优控制方法生成轨迹,由ACT-R模型对评价函数的权重进行动态调整优化,通过智能优化多个权重的方法动态生成最优轨迹。避障行驶仿真实验结果表明,所提出的方法有效可行,可以动态地生成最优参考轨迹。In order to enable the intelligent vehicle to travel following planned trajectory smoothly under different road conditions, a new cognitive architecture Adaptive Control of Thought-Rational （ACT-R） based dynamic optimal trajectory planning method was introduced. The new method combines the mathematical tool for optimal control problem and the ACT-R model. The ACT-R model is the core of the new method and the trajectory is generated by the optimal control method. The multi-weights of the cost function are adjusted dynamically by intelligent optimization and the optimized trajectory is generated. The simulation results of obstacle avoidance show that the method is effective and feasible, and the optimal reference trajectory can be generated dynamically.

关 键 词：车辆工程 智能车 ACT-R模型 最优控制 动态轨迹优化 

分 类 号：U471.15[机械工程—车辆工程]