基于融合感知的自动驾驶汽车AEB控制研究

打开文本图片集

中图分类号：U461.91 文献标识码：A DOI：10.3969/j.issn.1674-8484.2025.04.013

Abstract：To address the limitations of existing automatic emergency braking （AEB） systems—such as the susceptibilitytoobstacle misidentification in complex scenarios，theinsuficient considerationof the preceding vehicle'sacceleration，and the lack of control precision—this paperproposedanobstacledetectionapproach that integrated visual and LiDAR perception.A hierarchicalAEB control strategy based on model predictive control（MPC）wasdesigned todetermine thedesired brakingdeceleration，andaproportional-integral-derivative （PID）controller was employed to regulate the vehicle's brake mastercylinder pressure.The results show that the proposed obstacle detection method canaccurately identify obstacles incomplexscenarios.Furthermore， the controller enables the vehicle toachievea 100% deceleration rate across various AEB test scenarios，with brakingacceleration being outputas intended.The proposed methodology effectively enhances both safetyand ride comfort during the automatic emergency braking process.

Key words：vehicle safety; Inteligent vehicle;autonomousemergency break （AEB）;obstructiondetection; model predictive control （MPC）

根据公安部统计，截至2024年全国机动车保有量达 4.53亿辆，其中汽车3.53亿辆[。（剩余14136字）