2021/10/04 by Roshan Vijay, Vijay, Roshan, Jim Cherian +7 · 1 citation
Engineering · Environmental Science · #Artificial Intelligence (cs.AI) #Autonomous Vehicle Technology and Safety #C.2.1 #FOS: Computer and information sciences #FOS: Electrical engineering #I.6 #Networking and Internet Architecture (cs.NI) #Remote Sensing and LiDAR Applications #Robotics (cs.RO) #Systems and Control (eess.SY) #Vehicular Ad Hoc Networks (VANETs) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2110.01251
openalex publication_date 2021/10/04 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
Vehicles with driving automation are increasingly being developed for\ndeployment across the world. However, the onboard sensing and perception\ncapabilities of such automated or autonomous vehicles (AV) may not be\nsufficient to ensure safety under all scenarios and contexts.\nInfrastructure-augmented environment perception using roadside infrastructure\nsensors can be considered as an effective solution, at least for selected\nregions of interest such as urban road intersections or curved roads that\npresent occlusions to the AV. However, they incur significant costs for\nprocurement, installation and maintenance. Therefore these sensors must be\nplaced strategically and optimally to yield maximum benefits in terms of the\noverall safety of road users. In this paper, we propose a novel methodology\ntowards obtaining an optimal placement of V2X (Vehicle-to-everything)\ninfrastructure sensors, which is particularly attractive to urban AV\ndeployments, with various considerations including costs, coverage and\nredundancy. We combine the latest advances made in raycasting and linear\noptimization literature to deliver a tool for urban city planners, traffic\nanalysis and AV deployment operators. Through experimental evaluation in\nrepresentative environments, we prove the benefits and practicality of our\napproach.\n