自动驾驶汽车换道决策优化  

Lane-changing decision optimization of autonomous vehicles

在线阅读下载全文

作  者:张茂盛 林国庆[2] 贺伟星 吕文静 ZHANG Maosheng;LIN Guoqing;HE Weixing;LYU Wenjing(School of Automobile,Chang’an University,Xi’an 710064,China;School of Energy and Electerical Engineering,Chang’an University,Xi’an 710064,China)

机构地区:[1]长安大学汽车学院,西安710064 [2]长安大学能源与电气工程学院,西安710064

出  处:《交通科技与经济》2025年第2期74-80,共7页Technology & Economy in Areas of Communications

基  金:陕西省重点研发计划项目(2021LLRH-04-02-02),陕西省创新能力支撑计划项目(2019PT-16)。

摘  要:传统换道策略仅考虑前车慢行和制动安全问题,这在复杂的交通环境中具有局限性。基于此,在速度不满意度中引入车辆类型因素和道路拥堵程度因数,在空间不满意度中引入制动距离和道路特性等因素,以实现类人换道意图的产生。根据模型计算出换道意图后,结合实际驾驶情况和综合成本函数进行最优车道选择,并利用仿真软件对模型进行仿真验证。结果表明:换道决策算法可根据当前车道环境以及驾驶状况,通过不满意度的积累做出合理的换道决策,根据综合成本函数对目标车道的优劣进行判断,规划控制模块仿真结果显示换道轨迹平稳,无侧滑失稳现象发生。提出的模型能够较好地优化自动驾驶汽车的换道决策。Traditional lane-changing strategies primarily address issues of slow-moving lead vehicles and braking safety,which prove limited in complex traffic environments.To address this,the factors of vehicle type and road congestion level are introduced into speed dissatisfaction,while braking distance and road characteristics are incorporated into spatial dissatisfaction,to emulate human-like lane-changing intentions.Upon calculating the lane-changing intention via the proposed model,the optimal lane is selected based on actual driving conditions and a comprehensive cost function.The model was validated through simulation software.Results indicate that the lane-changing decision algorithm can reasonably determine lane changes by accumulating dissatisfaction based on the current lane environment and driving conditions.It evaluates the suitability of target lanes using a comprehensive cost function.The planning control module’s simulation results demonstrate smooth lane-changing trajectories without incidents of side slip or instability.The study concludes that the proposed model effectively optimizes lane-changing decisions for autonomous vehicles.

关 键 词:交通工程 自动驾驶汽车 仿真分析 换道决策 运动控制 

分 类 号:U495[交通运输工程—交通运输规划与管理]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象