【作者】 杨明亮； 寇胜杰； 芦勇； 于春磊； 江昆； 杨殿阁；

【Author】 Yang Mingliang;Kou Shengjie;Lu Yong;Yu Chunlei;Jiang Kun;Yang Diange;Tsinghua University;Lianchang Automotive Electronics Co.,Ltd;

【机构】 清华大学； 联创汽车电子有限公司；

【摘要】 基于单一传感器换道预警模型准确性和可靠性不足,且换道过程中自车加速度的确定未考虑真实场景因素,本文提出了基于多传感器融合的换道预警模型,并在模型自车加速度的确定中充分考虑了自车车速、他车相对距离、相对速度因素,优化了原有的换道预警模型,并采用碰撞时间和安全换道距离为评价指标制定换道决策规则。仿真和实车试验结果表明基于多传感器融合的换道预警模型预警更加灵敏高效,符合道路使用和驾驶员操作要求,验证了多传感器在环境感知中的优势,证明了换道预警模型的有效性。更多还原

【Abstract】 The accuracy and reliability of lane-changing warning model based on single sensor are insufficient,and the detennination of self-driving acceleration in lane-changing process does not take into account the real scene factors.In this paper,a lane change warning model based on multi-sensor fusion was proposed.In the determination of the acceleration of the model,the factors of the speed of the car,the relative distance between other cars and the relative speed were fully considered.The original lane-changing early warning model was optimized,and the decision rules of lane-changing were formulated with time to collision and safe lane-changing distance as the evaluation indexes.The simulation and real vehicle test results show that the lane-changing early warning model based on multi-sensor fusion is more sensitive and efficient,which met the requirements of road use and driver operation,verified the advantages of multisensor in environmental perception and proved the validity of lane change warning model.更多还原