{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/hallucinating-robots-inferring-obstacle","title":"Hallucinating robots: Inferring Obstacle Distances from Partial Laser Measurements","arxiv_id":"1805.12338","date":"2018-05-31","proceeding":null,"authors":["Jens Lundell","Francesco Verdoja","Ville Kyrki"],"abstract":"Many mobile robots rely on 2D laser scanners for localization, mapping, and\nnavigation. However, those sensors are unable to correctly provide distance to\nobstacles such as glass panels and tables whose actual occupancy is invisible\nat the height the sensor is measuring. In this work, instead of estimating the\ndistance to obstacles from richer sensor readings such as 3D lasers or RGBD\nsensors, we present a method to estimate the distance directly from raw 2D\nlaser data. To learn a mapping from raw 2D laser distances to obstacle\ndistances we frame the problem as a learning task and train a neural network\nformed as an autoencoder. A novel configuration of network hyperparameters is\nproposed for the task at hand and is quantitatively validated on a test set.\nFinally, we qualitatively demonstrate in real time on a Care-O-bot 4 that the\ntrained network can successfully infer obstacle distances from partial 2D laser\nreadings.","url_abs":"http://arxiv.org/abs/1805.12338v2","url_pdf":"http://arxiv.org/pdf/1805.12338v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"hallucinating-robots-inferring-obstacle","repo_url":"https://github.com/jsll/IROS2018-Hallucinating-Robots","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}