{"title":"Automatic Generation of Waypoint Graphs from Distributed Ceiling-Mounted Smart Cameras for Decentralized Multi-Robot Indoor Navigation","authors":"Andrew Felder, Dillon Van Buskirk, C. Bobda","doi":"10.1145/3349801.3349814","DOIUrl":null,"url":null,"abstract":"This work addresses decentralized coordination of autonomous robots with assistance from overhead map-building and path planning cameras. We propose our solution, Decentralized Indoor Smart Mapping and Hierarchical Navigation (DISCMAHN). We propose an algorithm to generate a waypoint map for each overhead camera's region in real time. Furthermore, we propose a modified A* to perform fully-decentralized path planning. Waypoint generation was simulated to ensure it is both effective and efficient. Path planning was simulated on various, randomized environments to show effectiveness. Our method efficiently handles the cases where other robot navigation methods are otherwise weak and ineffective.","PeriodicalId":299138,"journal":{"name":"Proceedings of the 13th International Conference on Distributed Smart Cameras","volume":"7 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 13th International Conference on Distributed Smart Cameras","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3349801.3349814","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
This work addresses decentralized coordination of autonomous robots with assistance from overhead map-building and path planning cameras. We propose our solution, Decentralized Indoor Smart Mapping and Hierarchical Navigation (DISCMAHN). We propose an algorithm to generate a waypoint map for each overhead camera's region in real time. Furthermore, we propose a modified A* to perform fully-decentralized path planning. Waypoint generation was simulated to ensure it is both effective and efficient. Path planning was simulated on various, randomized environments to show effectiveness. Our method efficiently handles the cases where other robot navigation methods are otherwise weak and ineffective.