{"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/detection-localisation-and-tracking-of","title":"Detection, localisation and tracking of pallets using machine learning techniques and 2D range data","arxiv_id":"1803.11254","date":"2018-03-29","proceeding":null,"authors":["Ihab S. Mohamed","Alessio Capitanelli","Fulvio Mastrogiovanni","Stefano Rovetta","Renato Zaccaria"],"abstract":"The problem of autonomous transportation in industrial scenarios is receiving\na renewed interest due to the way it can revolutionise internal logistics,\nespecially in unstructured environments. This paper presents a novel\narchitecture allowing a robot to detect, localise, and track (possibly\nmultiple) pallets using machine learning techniques based on an on-board 2D\nlaser rangefinder only. The architecture is composed of two main components:\nthe first stage is a pallet detector employing a Faster Region-based\nConvolutional Neural Network (Faster R-CNN) detector cascaded with a CNN-based\nclassifier; the second stage is a Kalman filter for localising and tracking\ndetected pallets, which we also use to defer commitment to a pallet detected in\nthe first stage until sufficient confidence has been acquired via a sequential\ndata acquisition process. For fine-tuning the CNNs, the architecture has been\nsystematically evaluated using a real-world dataset containing 340 labeled 2D\nscans, which have been made freely available in an online repository. Detection\nperformance has been assessed on the basis of the average accuracy over k-fold\ncross-validation, and it scored 99.58% in our tests. Concerning pallet\nlocalisation and tracking, experiments have been performed in a scenario where\nthe robot is approaching the pallet to fork. Although data have been originally\nacquired by considering only one pallet as per specification of the use case we\nconsider, artificial data have been generated as well to mimic the presence of\nmultiple pallets in the robot workspace. Our experimental results confirm that\nthe system is capable of identifying, localising and tracking pallets with a\nhigh success rate while being robust to false positives.","url_abs":"http://arxiv.org/abs/1803.11254v3","url_pdf":"http://arxiv.org/pdf/1803.11254v3.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":"detection-localisation-and-tracking-of","repo_url":"https://github.com/EMAROLab/PDT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}