A. P. D. Silva, Imane Horiya Brahmi, S. Leirens, B. Denis
{"title":"System-level Simulation of Cooperative Sensor Data Fusion Strategies for Improved Vulnerable Road Users Safety","authors":"A. P. D. Silva, Imane Horiya Brahmi, S. Leirens, B. Denis","doi":"10.1109/WPNC47567.2019.8970187","DOIUrl":null,"url":null,"abstract":"Cooperation between vehicles and/or with static elements of the road infrastructure enables a wide number of applications and services, such as traffic monitoring and prediction, localization and mapping, or novel safety approaches for vulnerable road users. For instance, relying on on-board sensors, on conventional navigation systems, and on V2X wireless connectivity, vehicles can represent geo-tagged measurements (e.g., LiDAR) in the form of local occupancy grid maps accounting for the presence of obstacles. The latter maps can be subsequently shared, either directly (e.g., with other fellow vehicles around) or via a centralized entity (e.g., edge cloud…). Through cooperative fusion, equipped vehicles thus contribute to elaborate a global view of the physical environment.In this paper, we first describe a flexible end-to-end system simulator that can evaluate such cooperative mapping strategies in complex road driving environments. The overall simulation flow spans from sensor and V2X connectivity abstractions up to fusion algorithms running at the application level. We then present a few illustrating simulation results in a smart intersection scenario, confirming the importance of V2X-aided cooperation to enhance the physical perception of standalone vehicles in terms of both coverage and detection performances.","PeriodicalId":284815,"journal":{"name":"2019 16th Workshop on Positioning, Navigation and Communications (WPNC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 16th Workshop on Positioning, Navigation and Communications (WPNC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/WPNC47567.2019.8970187","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7
Abstract
Cooperation between vehicles and/or with static elements of the road infrastructure enables a wide number of applications and services, such as traffic monitoring and prediction, localization and mapping, or novel safety approaches for vulnerable road users. For instance, relying on on-board sensors, on conventional navigation systems, and on V2X wireless connectivity, vehicles can represent geo-tagged measurements (e.g., LiDAR) in the form of local occupancy grid maps accounting for the presence of obstacles. The latter maps can be subsequently shared, either directly (e.g., with other fellow vehicles around) or via a centralized entity (e.g., edge cloud…). Through cooperative fusion, equipped vehicles thus contribute to elaborate a global view of the physical environment.In this paper, we first describe a flexible end-to-end system simulator that can evaluate such cooperative mapping strategies in complex road driving environments. The overall simulation flow spans from sensor and V2X connectivity abstractions up to fusion algorithms running at the application level. We then present a few illustrating simulation results in a smart intersection scenario, confirming the importance of V2X-aided cooperation to enhance the physical perception of standalone vehicles in terms of both coverage and detection performances.