{"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/neural-path-planning-fixed-time-near-optimal","title":"Neural Path Planning: Fixed Time, Near-Optimal Path Generation via Oracle Imitation","arxiv_id":"1904.11102","date":"2019-04-25","proceeding":null,"authors":["Mayur J. Bency","Ahmed H. Qureshi","Michael C. Yip"],"abstract":"Fast and efficient path generation is critical for robots operating in\ncomplex environments. This motion planning problem is often performed in a\nrobot's actuation or configuration space, where popular pathfinding methods\nsuch as A*, RRT*, get exponentially more computationally expensive to execute\nas the dimensionality increases or the spaces become more cluttered and\ncomplex. On the other hand, if one were to save the entire set of paths\nconnecting all pair of locations in the configuration space a priori, one would\nrun out of memory very quickly. In this work, we introduce a novel way of\nproducing fast and optimal motion plans for static environments by using a\nstepping neural network approach, called OracleNet. OracleNet uses Recurrent\nNeural Networks to determine end-to-end trajectories in an iterative manner\nthat implicitly generates optimal motion plans with minimal loss in performance\nin a compact form. The algorithm is straightforward in implementation while\nconsistently generating near-optimal paths in a single, iterative, end-to-end\nroll-out. In practice, OracleNet generally has fixed-time execution regardless\nof the configuration space complexity while outperforming popular pathfinding\nalgorithms in complex environments and higher dimensions","url_abs":"http://arxiv.org/abs/1904.11102v1","url_pdf":"http://arxiv.org/pdf/1904.11102v1.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":"neural-path-planning-fixed-time-near-optimal","repo_url":"https://github.com/our-projects-github/Safe-Deep-Learning-Based-Global-Path-Planning-Using-a-Fast-Collision-Free-Path-Generator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"motion-planning","task_name":"Motion Planning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.11102","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}