State Estimation of Preceding Target Vehicle Using Radar and V2X
Minsu Kim, Changsun Ahn
Pusan National University
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
With the advancement of automotive technologies and the widespread adoption of Advanced Driver Assistance Systems (ADAS), the need for accurate and real-time information regarding not only the ego vehicle but also surrounding vehicles—such as their positions and velocities—has become critical. However, sensors used to measure the states of surrounding vehicles are inherently limited by issues such as blind spots, occlusions, and signal delays, which can hinder the reliable operation of assistance systems. To address this challenge, this study proposes a sensor fusion estimator based on an Unscented Kalman Filter (UKF) with delay compensation, aimed at improving the accuracy and continuity of preceding vehicle tracking. The proposed estimator integrates data from GPS, vehicle-to-vehicle (V2V) communication, Radar, and IMU by utilizing a kinematic sensor dynamics model that does not require detailed vehicle-specific characteristics. This approach compensates for the weaknesses of individual sensors and ensures robust state estimation. To cope with various signal update rates and signal loss, a measurement model switching method is employed. Additionally, delay compensation enables the estimation of the current states of surrounding vehicles. The proposed estimator is validated using sensor data collected from real vehicles in diverse scenarios and environment, demonstrating improved accuracy, robustness, and real-time performance.
逐年被引趋势
暂无年度引用数据
关键指标
同类平均 = 1
同领域 · 同年份 · 同类型
Google Scholar 与 OpenAlex 的被引统计范围不同,数值存在差异属正常。
AI 辅助阅读
依据:摘要
可就本文提问;依据不足时会说明。
学术脉络
学科主题
计算机 / AITarget Tracking and Data Fusion in Sensor Networks
Autonomous Vehicle Technology and Safety · Inertial Sensor and Navigation