000173661 001__ 173661
000173661 005__ 20180317093332.0
000173661 037__ $$aCONF
000173661 245__ $$aIntegration of Online Learning into HTN Planning for Robotic Tasks
000173661 269__ $$a2012
000173661 260__ $$c2012
000173661 336__ $$aConference Papers
000173661 520__ $$aThis paper extends hierarchical task network (HTN) planning with lightweight learning, considering that in robotics, actions have a non-zero probability of failing. Our work applies to A*-based HTN planners with lifting. We prove that the planner finds the plan of maximal expected utility, while retaining its lifting capability and efficient heuristic-based search. We show how to learn the probabilities online, which allows a robot to adapt by replanning on execution failures. The idea behind this work is to use the HTN domain to constrain the space of possibilities, and then to learn on the constrained space in a way requiring few training samples, rendering the method applicable to autonomous mobile robots.
000173661 6531_ $$aHTN Planning
000173661 6531_ $$aRobot
000173661 6531_ $$alearning
000173661 700__ $$0240744$$aMagnenat, Stéphane$$g118595
000173661 700__ $$0240964$$aChappelier, Jean-Cédric$$g112547
000173661 700__ $$0240589$$aMondada, Francesco$$g102717
000173661 7112_ $$aDesigning Intelligent Robots: Reintegrating AI, AAAI Spring Symposium 2012$$cStanford$$dMarch 26th-28th, 2012
000173661 773__ $$tProceedings of the AAAI Spring Symposium 2012: Designing Intelligent Robots, Reintegrating AI
000173661 8564_ $$s266079$$uhttps://infoscience.epfl.ch/record/173661/files/Integration%20of%20Online%20Learning%20into%20HTN%20Planning%20for%20Robotic%20Tasks%20-%20Ste%CC%81phane%20Magnenat%20Jean-Ce%CC%81dric%20Chappelier%20and%20Francesco%20Mondada%20-%20AAAI%20-%202012.pdf$$yn/a$$zn/a
000173661 909CO $$ooai:infoscience.tind.io:173661$$pconf$$pSTI$$pIC
000173661 909C0 $$0252016$$pLSRO
000173661 909C0 $$0252184$$pLIA$$xU10406
000173661 917Z8 $$x102717
000173661 917Z8 $$x102717
000173661 937__ $$aEPFL-CONF-173661
000173661 973__ $$aEPFL$$rREVIEWED$$sACCEPTED
000173661 980__ $$aCONF