{"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/intention-net-integrating-planning-and-deep","title":"Intention-Net: Integrating Planning and Deep Learning for Goal-Directed Autonomous Navigation","arxiv_id":"1710.05627","date":"2017-10-16","proceeding":null,"authors":["Wei Gao","David Hsu","Wee Sun Lee","ShengMei Shen","Karthikk Subramanian"],"abstract":"How can a delivery robot navigate reliably to a destination in a new office\nbuilding, with minimal prior information? To tackle this challenge, this paper\nintroduces a two-level hierarchical approach, which integrates model-free deep\nlearning and model-based path planning. At the low level, a neural-network\nmotion controller, called the intention-net, is trained end-to-end to provide\nrobust local navigation. The intention-net maps images from a single monocular\ncamera and \"intentions\" directly to robot controls. At the high level, a path\nplanner uses a crude map, e.g., a 2-D floor plan, to compute a path from the\nrobot's current location to the goal. The planned path provides intentions to\nthe intention-net. Preliminary experiments suggest that the learned motion\ncontroller is robust against perceptual uncertainty and by integrating with a\npath planner, it generalizes effectively to new environments and goals.","url_abs":"http://arxiv.org/abs/1710.05627v2","url_pdf":"http://arxiv.org/pdf/1710.05627v2.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":"intention-net-integrating-planning-and-deep","repo_url":"https://github.com/ayusefi/Localization-Papers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"intention-net-integrating-planning-and-deep","repo_url":"https://github.com/xiexiexiaoxiexie/Udacity-self-driving-car-engineer-P7-Highway-Driving","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"autonomous-navigation","task_name":"Autonomous Navigation"},{"task_slug":"navigate","task_name":"Navigate"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1710.05627","atlas_url":"https://app.syntology.ai/?focus=1710.05627","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}