{"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/underwater-multi-robot-convoying-using-visual","title":"Underwater Multi-Robot Convoying using Visual Tracking by Detection","arxiv_id":"1709.08292","date":"2017-09-25","proceeding":null,"authors":["Florian Shkurti","Wei-Di Chang","Peter Henderson","Md Jahidul Islam","Juan Camilo Gamboa Higuera","Jimmy Li","Travis Manderson","Anqi Xu","Gregory Dudek","Junaed Sattar"],"abstract":"We present a robust multi-robot convoying approach that relies on visual\ndetection of the leading agent, thus enabling target following in unstructured\n3-D environments. Our method is based on the idea of tracking-by-detection,\nwhich interleaves efficient model-based object detection with temporal\nfiltering of image-based bounding box estimation. This approach has the\nimportant advantage of mitigating tracking drift (i.e. drifting away from the\ntarget object), which is a common symptom of model-free trackers and is\ndetrimental to sustained convoying in practice. To illustrate our solution, we\ncollected extensive footage of an underwater robot in ocean settings, and\nhand-annotated its location in each frame. Based on this dataset, we present an\nempirical comparison of multiple tracker variants, including the use of several\nconvolutional neural networks, both with and without recurrent connections, as\nwell as frequency-based model-free trackers. We also demonstrate the\npracticality of this tracking-by-detection strategy in real-world scenarios by\nsuccessfully controlling a legged underwater robot in five degrees of freedom\nto follow another robot's independent motion.","url_abs":"http://arxiv.org/abs/1709.08292v1","url_pdf":"http://arxiv.org/pdf/1709.08292v1.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":"underwater-multi-robot-convoying-using-visual","repo_url":"https://github.com/Breakend/TemporalYolo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"visual-tracking","task_name":"Visual Tracking"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}