{"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/efficient-hierarchical-robot-motion-planning","title":"Efficient Hierarchical Robot Motion Planning Under Uncertainty and Hybrid Dynamics","arxiv_id":"1802.04205","date":"2018-02-12","proceeding":null,"authors":["Ajinkya Jain","Scott Niekum"],"abstract":"Noisy observations coupled with nonlinear dynamics pose one of the biggest\nchallenges in robot motion planning. By decomposing nonlinear dynamics into a\ndiscrete set of local dynamics models, hybrid dynamics provide a natural way to\nmodel nonlinear dynamics, especially in systems with sudden discontinuities in\ndynamics due to factors such as contacts. We propose a hierarchical POMDP\nplanner that develops cost-optimized motion plans for hybrid dynamics models.\nThe hierarchical planner first develops a high-level motion plan to sequence\nthe local dynamics models to be visited and then converts it into a detailed\ncontinuous state plan. This hierarchical planning approach results in a\ndecomposition of the POMDP planning problem into smaller sub-parts that can be\nsolved with significantly lower computational costs. The ability to sequence\nthe visitation of local dynamics models also provides a powerful way to\nleverage the hybrid dynamics to reduce state uncertainty. We evaluate the\nproposed planner on a navigation task in the simulated domain and on an\nassembly task with a robotic manipulator, showing that our approach can solve\ntasks having high observation noise and nonlinear dynamics effectively with\nsignificantly lower computational costs compared to direct planning approaches.","url_abs":"http://arxiv.org/abs/1802.04205v4","url_pdf":"http://arxiv.org/pdf/1802.04205v4.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":"efficient-hierarchical-robot-motion-planning","repo_url":"https://github.com/Pearl-UTexas/POMDP-HD","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"motion-planning","task_name":"Motion Planning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}