1. NCCU Academic Hub
  2. 學術產出
  3. College of Informatics
  4. Periodical Articles
  5. Item

學術產出-Periodical Articles

Article View/Open

Publication Export

Google ScholarTM

政大圖書館

Citation Infomation

題名 An Incremental Learning Approach to Motion Planning with Roadmap Management
作者 Li, Tsai-yen;SHIE, YANG-CHUAN
李蔡彥
貢獻者 資科系
關鍵詞 incremental learning; motion planning; probabilistic roadmap management; reconfigurable random forest; planning for dynamic environments
日期 2007
上傳時間 8-May-2015 16:07:38 (UTC+8)
摘要 Traditional approaches to the motion-planning problem can be classified into solutions for single-query and multiple-query problems with the tradeoffs on run-time computation cost and adaptability to environment changes. In this paper, we propose a novel approach to the problem that can learn incrementally on every planning query and effectively manage the learned road-map as the process goes on. This planner is based on previous work on probabilistic roadmaps and uses a data structure called Reconfigurable Random Forest (RRF), which extends the Rapidly-exploring Random Tree (RRT) structure proposed in the literature. The planner can account for environmental changes while keeping the size of the roadmap small. The planner removes invalid nodes in the roadmap as the obstacle configurations change. It also uses a tree-pruning algorithm to trim RRF into a more concise representation. Our experiments show that the resulting roadmap has good coverage of freespace as the original one. We have also successful incorporated the planner into the application of intelligent navigation control.
關聯 JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 23, 525-538
資料類型 article
DOI http://dx.doi.org/10.1109/ROBOT.2002.1014238
dc.contributor 資科系
dc.creator (作者) Li, Tsai-yen;SHIE, YANG-CHUAN
dc.creator (作者) 李蔡彥zh_TW
dc.date (日期) 2007
dc.date.accessioned 8-May-2015 16:07:38 (UTC+8)-
dc.date.available 8-May-2015 16:07:38 (UTC+8)-
dc.date.issued (上傳時間) 8-May-2015 16:07:38 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/75057-
dc.description.abstract (摘要) Traditional approaches to the motion-planning problem can be classified into solutions for single-query and multiple-query problems with the tradeoffs on run-time computation cost and adaptability to environment changes. In this paper, we propose a novel approach to the problem that can learn incrementally on every planning query and effectively manage the learned road-map as the process goes on. This planner is based on previous work on probabilistic roadmaps and uses a data structure called Reconfigurable Random Forest (RRF), which extends the Rapidly-exploring Random Tree (RRT) structure proposed in the literature. The planner can account for environmental changes while keeping the size of the roadmap small. The planner removes invalid nodes in the roadmap as the obstacle configurations change. It also uses a tree-pruning algorithm to trim RRF into a more concise representation. Our experiments show that the resulting roadmap has good coverage of freespace as the original one. We have also successful incorporated the planner into the application of intelligent navigation control.
dc.format.extent 1384858 bytes-
dc.format.mimetype application/pdf-
dc.relation (關聯) JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 23, 525-538
dc.subject (關鍵詞) incremental learning; motion planning; probabilistic roadmap management; reconfigurable random forest; planning for dynamic environments
dc.title (題名) An Incremental Learning Approach to Motion Planning with Roadmap Management
dc.type (資料類型) articleen
dc.identifier.doi (DOI) 10.1109/ROBOT.2002.1014238
dc.doi.uri (DOI) http://dx.doi.org/10.1109/ROBOT.2002.1014238