电子测量与仪器学报

李海青,李永福,郑太雄,李洪丞,蔡小雨.智能汽车拟人驾驶风险量化方法研究[J].电子测量与仪器学报,2023,37(8):120-127

智能汽车拟人驾驶风险量化方法研究

Research on human-like driving risk quantification method for intelligent vehicles

DOI：

英文关键词:human-like driving dynamic risk field quantification method intelligent vehicles

基金项目:国家自然科学基金(62273067)、重庆市创新发展联合基金(CSTB2022NSCQ-LZX0025)、重庆市教委青年项目(KJQN202100644)、重庆市自然科学基金面上项目(cstc2020jcyj-msxmX0915)资助

作者	单位
李海青	1. 重庆邮电大学先进制造工程学院
李永福	2. 重庆邮电大学智能空地协同控制重庆市高校重点实验室
郑太雄	1. 重庆邮电大学先进制造工程学院
李洪丞	1. 重庆邮电大学先进制造工程学院
蔡小雨	1. 重庆邮电大学先进制造工程学院

Author	Institution
Li Haiqing	1. Advanced Manufacturing Engineering School, Chongqing University of Posts and Telecommunications
Li Yongfu	2. Key Laboratory of Intelligent Air-Ground Cooperative Control for Universities in Chongqing, Chongqing University of Posts and Telecommunications
Zheng Taixiong	1. Advanced Manufacturing Engineering School, Chongqing University of Posts and Telecommunications
Li Hongcheng	1. Advanced Manufacturing Engineering School, Chongqing University of Posts and Telecommunications
Cai Xiaoyu	1. Advanced Manufacturing Engineering School, Chongqing University of Posts and Telecommunications

摘要点击次数: 464

全文下载次数: 549

中文摘要:

驾驶风险量化评估对智能汽车拟人驾驶决策至关重要,针对复杂多任务场景下的驾驶风险量化问题,提出了一种基于人类风险感知机理的智能汽车驾驶风险量化方法。首先,利用传感器获取驾驶场景周围环境信息与行驶状态信息,并根据人类驾驶经验对潜在冲突因素赋值代价,生成驾驶场景代价地图;其次,根据车辆运动状态与拟人驾驶的基本原则,利用高斯函数建立动态风险模型;最后,结合驾驶场景代价图与动态风险模型实时计算拟人驾驶风险量化值。仿真结果表明,提出的方法能够基于人类驾驶经验,计算出动态变化的驾驶风险量化值,应用于智能汽车自动驾驶决策,可产生拟人驾驶行为。

英文摘要:

Conducting a quantize value of driving risk is crucial for the human-like driving decision of intelligent vehicles (IV). Aiming at the challenge of quantifying driving risks in complex multi-task scenarios, a method of driving risk quantification of IV based on human risk perceived mechanism is proposed. By utilizing vehicle or road sensors, measurements of the surrounding environment and state information have been obtained. And a cost map of the driving scene is created by assigning costs to potential collision factors such as roads, plants, and obstacles that the driver believes may occur in the first stage. Based on the fundamental principles of human driving and vehicle motion states, a dynamic risk model is established utilizing Gaussian functions. The real-time computation of driving risk with human-like characteristics is accomplished through the integration of the cost map for the driving environment and a dynamic risk model. The simulation results demonstrate the effectiveness of the proposed method in quantifying dynamic driving risk based on human driving experience, which is applicable to autonomous driving decision-making for IV and capable of generating human-like driving behavior.

查看全文查看/发表评论下载PDF阅读器