S. Nayak, Guoyuan Wu, M. Barth, Yongkang Liu, E. A. Sisbot, K. Oguchi
{"title":"基于不同运动模型的基础设施辅助车辆协同跟踪评价","authors":"S. Nayak, Guoyuan Wu, M. Barth, Yongkang Liu, E. A. Sisbot, K. Oguchi","doi":"10.1109/PLANS53410.2023.10139968","DOIUrl":null,"url":null,"abstract":"Vehicle positioning and tracking is a key component of Intelligent Transportation Systems (ITS). Cooperative positioning techniques through vehicle-to-vehicle (V2V) or vehicle-to-infrastructure (V2I) information sharing can improve the existing proprioceptive based positioning systems such as Global Navigation Satellite System (GNSS) which are prone to errors due to urban canyons, signal jamming, etc. V2V-based positioning might not fulfill all positioning needs, given the low Connected and Automated Vehicle (CAV) penetration in today's traffic. In these scenarios, infrastructure sensors can assist the vehicles in estimating the state of the traffic through I2V communication. The state estimation requires fusion between the infrastructure and the on-board sensor measurements which are often multi-rate and asynchronous in nature. Moreover, the measurements from the infrastructure might be delayed and not time-synchronized with other sensors. Hence, it is imperative to address the practical problems while designing a sensor fusion framework for fusing multiple sensor measurements in a real world scenario. This paper aims at evaluating the improvement in vehicle tracking by fusing roadside LiDAR measurements with the on-board GPS position measurements. Various motion models for the vehicle are studied and implemented with a sequential Kalman filter for estimating the vehicle states.","PeriodicalId":344794,"journal":{"name":"2023 IEEE/ION Position, Location and Navigation Symposium (PLANS)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Evaluation of Infrastructure-Assisted Cooperative Tracking of Vehicles Using Various Motion Models\",\"authors\":\"S. Nayak, Guoyuan Wu, M. Barth, Yongkang Liu, E. A. Sisbot, K. Oguchi\",\"doi\":\"10.1109/PLANS53410.2023.10139968\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Vehicle positioning and tracking is a key component of Intelligent Transportation Systems (ITS). Cooperative positioning techniques through vehicle-to-vehicle (V2V) or vehicle-to-infrastructure (V2I) information sharing can improve the existing proprioceptive based positioning systems such as Global Navigation Satellite System (GNSS) which are prone to errors due to urban canyons, signal jamming, etc. V2V-based positioning might not fulfill all positioning needs, given the low Connected and Automated Vehicle (CAV) penetration in today's traffic. In these scenarios, infrastructure sensors can assist the vehicles in estimating the state of the traffic through I2V communication. The state estimation requires fusion between the infrastructure and the on-board sensor measurements which are often multi-rate and asynchronous in nature. Moreover, the measurements from the infrastructure might be delayed and not time-synchronized with other sensors. Hence, it is imperative to address the practical problems while designing a sensor fusion framework for fusing multiple sensor measurements in a real world scenario. This paper aims at evaluating the improvement in vehicle tracking by fusing roadside LiDAR measurements with the on-board GPS position measurements. Various motion models for the vehicle are studied and implemented with a sequential Kalman filter for estimating the vehicle states.\",\"PeriodicalId\":344794,\"journal\":{\"name\":\"2023 IEEE/ION Position, Location and Navigation Symposium (PLANS)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-04-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 IEEE/ION Position, Location and Navigation Symposium (PLANS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/PLANS53410.2023.10139968\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IEEE/ION Position, Location and Navigation Symposium (PLANS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/PLANS53410.2023.10139968","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Evaluation of Infrastructure-Assisted Cooperative Tracking of Vehicles Using Various Motion Models
Vehicle positioning and tracking is a key component of Intelligent Transportation Systems (ITS). Cooperative positioning techniques through vehicle-to-vehicle (V2V) or vehicle-to-infrastructure (V2I) information sharing can improve the existing proprioceptive based positioning systems such as Global Navigation Satellite System (GNSS) which are prone to errors due to urban canyons, signal jamming, etc. V2V-based positioning might not fulfill all positioning needs, given the low Connected and Automated Vehicle (CAV) penetration in today's traffic. In these scenarios, infrastructure sensors can assist the vehicles in estimating the state of the traffic through I2V communication. The state estimation requires fusion between the infrastructure and the on-board sensor measurements which are often multi-rate and asynchronous in nature. Moreover, the measurements from the infrastructure might be delayed and not time-synchronized with other sensors. Hence, it is imperative to address the practical problems while designing a sensor fusion framework for fusing multiple sensor measurements in a real world scenario. This paper aims at evaluating the improvement in vehicle tracking by fusing roadside LiDAR measurements with the on-board GPS position measurements. Various motion models for the vehicle are studied and implemented with a sequential Kalman filter for estimating the vehicle states.