20.500.12556/RUL-161054 Zaznavanje ljudi v okolici mobilnega robota Detecting people around a mobile robot V diplomski nalogi smo sme posvetili glavni problematiki gibanja robotov v okolici človeka - sposobnosti zaznavanja ljudi in posledično varno gibanje robota za vse udeležence v prostoru. Preizkusili smo odprtokoden algoritem v okviru projekta Spencer in s primerno senzorsko opremo preizkusili njegovo učinkovitost v realnem okolju. Največ pozornosti smo posvetili zaznavanju okolice z RGB-D kamero, kateri smo določili njeno vidno polje ter ovrednotili natančnost zaznavanja oseb. Ko smo prenesli naš ROS-paket, smo na računalnik namestili ustrezne gonilnike za RGB-D kamero ter ustrezno dopolnili kodo (natančneje našo datoteko, ki odpre okolje Rviz, v katerem prikazuje podatke kamere v realnem času). V naslednjem koraku smo posneli podatke, ki jih je zajela RGB-D kamera in jih shranili. Pridobljene podatke pa smo nato analizirali in prikazali v okolju Matlab. Spreminjali smo višino kamere in postopek ponovili. Analiza je bila uspešna - uspelo nam je določiti območje s praktično 100% zanesljivostjo delovanja, analizirali pa smo tudi uspešnost v območju, kjer zanesljivost ni bila popolna. In the thesis, we addressed the main issues of robot movement in the vicinity of humans - the ability to detect people and consequently the safe movement of the robot for all participants in the area. We tested an open-source algorithm developed under the European project Spencer and evaluated its effectiveness in a real environment with appropriate sensor equipment. We focused most of our attention on environment detection with an RGB-D camera, defining its field of view and evaluating the accuracy of person detection. After downloading our ROS package, we installed the appropriate drivers for the RGB-D camera on the computer and the necessary supplementary code (specifically our launch file, which opens the Rviz environment, displaying the camera data in real-time). In the next step, we recorded the data captured by the RGB-D camera and saved it (in a rosbag file). The obtained data was then analyzed and presented in the Matlab environment. We varied the height of the camera and repeated the process. The analysis was successful and allowed us to determine the area with practically 100\% reliability of operation and partial reliability. Zaznavanje ljudi ROS RGB-D kamera Rviz rosbag linux launch datoteka Detecting people ROS RGB-D kamera Rviz rosbag linux launch file true false false Slovenski jezik Angleški jezik Diplomsko delo/naloga 2024-09-06 11:40:20 2024-09-06 11:40:25 2025-08-08 13:33:36 0000-00-00 00:00:00 2024 0 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 62592 206848003 Cerovsek_Karel_-_Zaznavanje_ljudi_v_okolici_mobilnega_robota.pdf Cerovsek_Karel_-_Zaznavanje_ljudi_v_okolici_mobilnega_robota.pdf 1 097D458EE7D2AEA2ED4644A645425A42 a8159abbe4f2e206de229823175fe885c4022643dbe50cfd0e6c682ed443cfba 067bd17b-6c34-11ef-b232-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=189913 Fakulteta za elektrotehniko 0 0 0