{"type":"ScholarlyArticle","title":"Online, Interactive User Guidance for High-dimensional, Constrained Motion Planning","authors":[{"name":"Fahad Islam","slug":"fahad-islam","given":"Fahad","family":"Islam","affiliation":"The Robotics Institute , Carnegie Mellon University"},{"name":"Oren Salzman","slug":"oren-salzman","given":"Oren","family":"Salzman","affiliation":"The Robotics Institute , Carnegie Mellon University"},{"name":"Maxim Likhachev","slug":"maxim-likhachev","given":"Maxim","family":"Likhachev","affiliation":"The Robotics Institute , Carnegie Mellon University"}],"abstract":"We consider the problem of planning a collision-free path for a high-dimensional robot. Specifically, we suggest a planning framework where a motion-planning algorithm can obtain guidance from a user. In contrast to existing approaches that try to speed up planning by incorporating experiences or demonstrations ahead of planning, we suggest to seek user guidance only when the planner identifies that it ceases to make significant progress towards the goal. Guidance is provided in the form of an intermediate configuration q^, which is used to bias the planner to go through q^. We demonstrate our approach for the case where the planning algorithm is Multi-Heuristic A* (MHA*) and the robot is a 34-DOF humanoid. We show that our approach allows to compute highly-constrained paths with little domain knowledge. Without our approach, solving such problems requires carefully-crafted domain-dependent heuristics.","doi":"10.24963/ijcai.2018/683","url":"https://ijcai.org/proceedings/2018/683","pdf":"https://ijcai.org/proceedings/2018/0683.pdf","markdown":"https://ijcai.org/proceedings/2018/683.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/683","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Robotics","track":"Main track","number":683,"pages":{"first":4921,"last":4928},"keywords":["Robotics: Robotics","Robotics: Motion and Path Planning","Heuristic Search and Game Playing: Heuristic Search"],"videos":[],"references":[{"position":1,"raw":"[Aine et al., 2016] Sandip Aine, Siddharth Swaminathan, Venkatraman Narayanan, Victor Hwang, and Maxim Likhachev. Multi-heuristic A*. IJRR, 35(1-3):224-243, 2016.","title":"Multi-heuristic A*","authors":"Siddharth Sandip Aine, Venkatraman Swaminathan, Victor Narayanan, Maxim Hwang, Likhachev","year":"2016","venue":"IJRR","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Argall et al., 2009] Brenna Argall, Sonia Chernova, Manuela M. Veloso, and Brett Browning. A survey of robot learning from demonstration. Robotics and Autonomous Systems, 57(5):469-483, 2009.","title":"A survey of robot learning from demonstration","authors":"Brenna Argall, Sonia Chernova, Manuela M Veloso, Brett Browning","year":"2009","venue":"Robotics and Autonomous Systems","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Blin et al., 2016] Nassime Blin, Michel Taïx, Philippe Filla- treau, and Jean-Yves Fourquet. I-RRT-C: interactive mo- tion planning with contact. In IROS, pages 4244-4249, 2016.","title":"I-RRT-C: interactive motion planning with contact","authors":"Blin","year":"2016","venue":"IROS","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Burns et al., 2013] Ethan Burns, Wheeler Ruml, and Minh Binh Do. Heuristic search when time matters. J. Artif. Intell. Res, 47:697-740, 2013.","title":"Heuristic search when time matters","authors":"Ethan Burns, Wheeler Ruml, Minh Binh Do","year":"2013","venue":"J. Artif. Intell. Res","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chakrabarti et al., 1986] PP Chakrabarti, Sujoy Ghose, and SC Desarkar. Heuristic search through islands. J. AI, 29(3):339-347, 1986.","title":"Heuristic search through islands","authors":"Chakrabarti","year":"1986","venue":"J. AI","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chestnutt et al., 2005] Joel E. Chestnutt, Manfred Lau, Ger- man K. M. Cheung, James Kuffner, Jessica K. Hodgins, and Takeo Kanade. Footstep planning for the honda ASIMO humanoid. In ICRA, pages 629-634, 2005.","title":"Footstep planning for the honda ASIMO humanoid","authors":"Joel E Chestnutt, Manfred Lau, K M German, James Cheung, Jessica K Kuffner, Takeo Hodgins, Kanade","year":"2005","venue":"ICRA","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Choset et al., 2005] Howie Choset, Kevin M. Lynch, Seth Hutchinson, George Kantor, Wolfram Burgard, Lydia E. Kavraki, and Sebastian Thrun. Principles of Robot Mo- tion: Theory, Algorithms, and Implementation. MIT Press, June 2005.","title":"Principles of Robot Motion: Theory, Algorithms, and Implementation","authors":"Howie Choset, Kevin M Lynch, Seth Hutchinson, George Kantor, Wolfram Burgard, Lydia E Kavraki, Sebastian Thrun","year":"2005","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Cohen et al., 2014] Benjamin J. Cohen, Sachin Chitta, and Maxim Likhachev. Single-and dual-arm motion planning with heuristic search. IJRR, 33(2):305-320, 2014.","title":"Single-and dual-arm motion planning with heuristic search","authors":"Benjamin J Cohen, Sachin Chitta, Maxim Likhachev","year":"2014","venue":"IJRR","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[DeDonato et al., 2017] Mathew DeDonato, Felipe Polido, Kevin Knoedler, Benzun PW Babu, Nandan Banerjee, Christoper P Bove, Xiongyi Cui, Ruixiang Du, Perry Franklin, Joshua P Graff, et al. Team WPI-CMU: Achiev- ing reliable humanoid behavior in the DARPA robotics challenge. J. Field Robotics, 34(2):381-399, 2017.","title":"Team WPI-CMU: Achieving reliable humanoid behavior in the DARPA robotics challenge","authors":"Mathew Dedonato, Felipe Polido, Kevin Knoedler, P W Benzun, Nandan Babu, Christoper P Banerjee, Xiongyi Bove, Ruixiang Cui, Perry Du, Joshua P Franklin, Graff","year":"2017","venue":"J. Field Robotics","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Denny et al., 2014] Jory Denny, Read Sandström, Nicole Julian, and Nancy M. Amato. A region-based strategy for collaborative roadmap construction. In WAFR, pages 125- 141, 2014.","title":"A region-based strategy for collaborative roadmap construction","authors":"Jory Denny, Read Sandström, Nicole Julian, Nancy M Amato","year":"2014","venue":"WAFR","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Dionne et al., 2011] Austin J. Dionne, Jordan Tyler Thayer, and Wheeler Ruml. Deadline-aware search using on-line measures of behavior. In SoCS, pages 39-46, 2011.","title":"Deadline-aware search using on-line measures of behavior","authors":"Austin J Dionne, Jordan Tyler Thayer, Wheeler Ruml","year":"2011","venue":"SoCS","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Dornbush et al., 2018] Andrew Dornbush, Karthik Vi- jayakumar, Sameer Bardapurkar, Fahad Islam, and Maxim Likhachev. A single-planner approach to multi-modal hu- manoid mobility. CoRR, abs/1801.10225, 2018.","title":"A single-planner approach to multi-modal humanoid mobility","authors":"Andrew Dornbush, Karthik Vijayakumar, Sameer Bardapurkar, Fahad Islam, Maxim Likhachev","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Flavigne et al., 2009] David Flavigne, Michel Taïx, and Eti- enne Ferre. Interactive motion planning for assembly tasks. In RO-MAN, pages 430-435, 2009.","title":"Interactive motion planning for assembly tasks","authors":"David Flavigne, Michel Taïx, Etienne Ferre","year":"2009","venue":"RO-MAN","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Gochev et al., 2011] Kalin Gochev, Benjamin J. Cohen, Jonathan Butzke, Alla Safonova, and Maxim Likhachev. Path planning with adaptive dimensionality. In SoCS, pages 52-59, 2011.","title":"Path planning with adaptive dimensionality","authors":"Kalin Gochev, Benjamin J Cohen, Jonathan Butzke, Alla Safonova, Maxim Likhachev","year":"2011","venue":"SoCS","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Gochev et al., 2012] Kalin Gochev, Alla Safonova, and Maxim Likhachev. Planning with adaptive dimensional- ity for mobile manipulation. In ICRA, pages 2944-2951, 2012.","title":"Planning with adaptive dimensionality for mobile manipulation","authors":"Kalin Gochev, Alla Safonova, Maxim Likhachev","year":"2012","venue":"ICRA","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Gochev et al., 2013] Kalin Gochev, Alla Safonova, and Maxim Likhachev. Incremental planning with adaptive di- mensionality. In ICAPS, pages 82-90, 2013.","title":"Incremental planning with adaptive dimensionality","authors":"Kalin Gochev, Alla Safonova, Maxim Likhachev","year":"2013","venue":"ICAPS","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Gray et al., 2017] Steven Gray, Robert Chevalier, David Kotfis, Benjamin Caimano, Kenneth Chaney, Aron Rubin, and Todd Danko. An architecture for human-guided auton- omy: Team TROOPER at the DARPA robotics challenge finals. J. Field Robotics, 34(5):852-873, 2017.","title":"An architecture for human-guided autonomy: Team TROOPER at the DARPA robotics challenge finals","authors":"Steven Gray, Robert Chevalier, David Kotfis, Benjamin Caimano, Kenneth Chaney, Aron Rubin, Todd Danko","year":"2017","venue":"J. Field Robotics","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Halperin et al., 2017] Dan Halperin, Oren Salzman, and Micha Sharir. Algorithmic motion planning. In Handbook of Discrete and Computational Geometry, Third Edition., pages 1311-1342. 2017.","title":"Algorithmic motion planning","authors":"Dan Halperin, Oren Salzman, Micha Sharir","year":"2017","venue":"Handbook of Discrete and Computational Geometry","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Hauser et al., 2008] Kris K. Hauser, Timothy Bretl, Jean- Claude Latombe, Kensuke Harada, and Brian Wilcox. Mo- tion planning for legged robots on varied terrain. IJRR, 27(11-12):1325-1349, 2008.","title":"Motion planning for legged robots on varied terrain","authors":"Kris K Hauser, Timothy Bretl, Jean-Claude Latombe, Kensuke Harada, Brian Wilcox","year":"2008","venue":"IJRR","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Hernández and Baier, 2012] Carlos Hernández and Jorge A Baier. Avoiding and escaping depressions in real-time heuristic search. J. Artif. Intell. Res, 43:523-570, 2012.","title":"Avoiding and escaping depressions in real-time heuristic search","authors":"Carlos Hernández, Jorge A Baier","year":"2012","venue":"J. Artif. Intell. Res","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Ishida, 1992] Toru Ishida. Moving target search with intel- ligence. In AAAI, pages 525-532, 1992.","title":"Moving target search with intelligence","authors":"Toru Ishida, Ishida","year":"1992","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Islam et al., 2015] Fahad Islam, Venkatraman Narayanan, and Maxim Likhachev. Dynamic multi-heuristic A*. In ICRA, pages 2376-2382, 2015.","title":"Dynamic multi-heuristic A","authors":"Fahad Islam, Venkatraman Narayanan, Maxim Likhachev","year":"2015","venue":"ICRA","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Kaneko et al., 2004] Kenji Kaneko, Fumio Kanehiro, Shu- uji Kajita, Hirohisa Hirukawa, T. Kawasaki, Masaru Hi- rata, Kazuhiko Akachi, and Takakatsu Isozumi. Humanoid robot HRP-2. In ICRA, pages 1083-1090, 2004.","title":"Humanoid robot HRP-2","authors":"Kenji Kaneko, Fumio Kanehiro, Shuuji Kajita, Hirohisa Hirukawa, T Kawasaki, Masaru Hirata, Kazuhiko Akachi, Takakatsu Isozumi","year":"2004","venue":"ICRA","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Koenig and Sun, 2009] Sven Koenig and Xiaoxun Sun. Comparing real-time and incremental heuristic search for real-time situated agents. AAMS, 18(3):313-341, 2009.","title":"Comparing real-time and incremental heuristic search for real-time situated agents","authors":"Sven Koenig, Xiaoxun Sun","year":"2009","venue":"AAMS","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Korf, 1990] Richard E Korf. Real-time heuristic search. J. AI, 42(2-3):189-211, 1990.","title":"Real-time heuristic search","authors":"Richard E Korf","year":"1990","venue":"J. AI","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Kuffner et al., 2001] James Kuffner, Koichi Nishiwaki, Satoshi Kagami, Masayuki Inaba, and Hirochika Inoue. Footstep planning among obstacles for biped robots. In IROS, pages 500-505, 2001.","title":"Footstep planning among obstacles for biped robots","authors":"James Kuffner, Koichi Nishiwaki, Satoshi Kagami, Masayuki Inaba, Hirochika Inoue","year":"2001","venue":"IROS","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[LaValle, 2006] Steven M. LaValle. Planning algorithms. Cambridge University Press, 2006.","title":"Planning algorithms","authors":"M Steven, Lavalle","year":"2006","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Marion et al., 2017] Pat Marion, Maurice Fallon, Robin Deits, Andrés Valenzuela, Claudia Pérez D'Arpino, Greg Izatt, Lucas Manuelli, Matt Antone, Hongkai Dai, Twan Koolen, et al. Director: A user interface designed for robot operation with shared autonomy. J. Field Robotics, 34(2):262-280, 2017.","title":"Director: A user interface designed for robot operation with shared autonomy","authors":"Pat Marion, Maurice Fallon, Robin Deits, Andrés Valenzuela, Claudia Pérez D'arpino, Greg Izatt, Lucas Manuelli, Matt Antone, Hongkai Dai, Twan Koolen","year":"2017","venue":"J. Field Robotics","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Matsuzawa et al., 2015] Takashi Matsuzawa, Kenji Hashimoto, Xiao Sun, Kazuhiro Uryu, Ayanori Koizumi, Shinya Hamamoto, Tomotaka Teramachi, and Atsuo Takanishi. Development of disaster response robot with commonly structured limbs and experiment in climbing vertical ladder. In ICAM, pages 142-143, 2015.","title":"Development of disaster response robot with commonly structured limbs and experiment in climbing vertical ladder","authors":"Takashi Matsuzawa, Kenji Hashimoto, Xiao Sun, Kazuhiro Uryu, Ayanori Koizumi, Shinya Hamamoto, Tomotaka Teramachi, Atsuo Takanishi","year":"2015","venue":"ICAM","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[McGill et al., 2017] Stephen G McGill, Seung-Joon Yi, Hak Yi, Min Sung Ahn, Sanghyun Cho, Kevin Liu, Daniel Sun, Bhoram Lee, Heejin Jeong, Jinwook Huh, et al. Team THOR's entry in the DARPA Robotics Challenge Finals 2015. J. Field Robotics, 4(34):775-801, 2017.","title":"Team THOR's entry in the DARPA Robotics Challenge Finals 2015","authors":"Seung-Joon Stephen G Mcgill, Hak Yi, Min Yi, Sanghyun Sung Ahn, Kevin Cho, Daniel Liu, Bhoram Sun, Heejin Lee, Jinwook Jeong, Huh","year":"2017","venue":"J. Field Robotics","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Mehta et al., 2015] Siddhartha S Mehta, Chau Ton, Michael J McCourt, Z Kan, Emily A Doucette, and W Curtis. Human-assisted RRT for path planning in urban environments. In Systems, Man, and Cybernetics (SMC), pages 941-946, 2015.","title":"Human-assisted RRT for path planning in urban environments","authors":"Siddhartha S Mehta, Chau Ton, J Michael, Z Mccourt, Emily A Kan, Doucette, Curtis","year":"2015","venue":"Systems, Man, and Cybernetics (SMC)","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Narayanan et al., 2015] Venkatraman Narayanan, Sandip Aine, and Maxim Likhachev. Improved multi-heuristic A* for searching with uncalibrated heuristics. In SoCS, pages 78-86, 2015.","title":"Improved multi-heuristic A* for searching with uncalibrated heuristics","authors":"Venkatraman Narayanan, Sandip Aine, Maxim Likhachev","year":"2015","venue":"SoCS","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Perrin et al., 2012] Nicolas Perrin, Olivier Stasse, Leo Bau- douin, Florent Lamiraux, and Eiichi Yoshida. Fast hu- manoid robot collision-free footstep planning using swept volume approximations. Trans. Robotics, 28(2):427-439, 2012.","title":"Fast humanoid robot collision-free footstep planning using swept volume approximations","authors":"Nicolas Perrin, Olivier Stasse, Leo Baudouin, Florent Lamiraux, Eiichi Yoshida","year":"2012","venue":"Trans. Robotics","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Phillips et al., 2015] Mike Phillips, Venkatraman Narayanan, Sandip Aine, and Maxim Likhachev. Efficient search with an ensemble of heuristics. In IJCAI, pages 784-791, 2015.","title":"Efficient search with an ensemble of heuristics","authors":"Mike Phillips, Venkatraman Narayanan, Sandip Aine, Maxim Likhachev","year":"2015","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2015/116"},{"position":35,"raw":"[Phillips et al., 2016] Mike Phillips, Victor Hwang, Sachin Chitta, and Maxim Likhachev. Learning to plan for con- strained manipulation from demonstrations. Autonomous Robots, 40(1):109-124, 2016.","title":"Learning to plan for constrained manipulation from demonstrations","authors":"Mike Phillips, Victor Hwang, Sachin Chitta, Maxim Likhachev","year":"2016","venue":"Autonomous Robots","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Pohl, 1970] Ira Pohl. First results on the effect of error in heuristic search. Machine Intelligence, 5:219-236, 1970.","title":"First results on the effect of error in heuristic search","authors":"Ira Pohl","year":"1970","venue":"Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Ranganeni et al., 2017] Vinitha Ranganeni, Oren Salzman, and Maxim Likhachev. Effective footstep planning for humanoids using homotopy-class guidance. CoRR, abs/1712.00531, 2017.","title":"Effective footstep planning for humanoids using homotopy-class guidance","authors":"Vinitha Ranganeni, Oren Salzman, Maxim Likhachev","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Schulman et al., 2016] John Schulman, Jonathan Ho, Cameron Lee, and Pieter Abbeel. Learning from demon- strations through the use of non-rigid registration. In Robotics Research, pages 339-354. 2016.","title":"Learning from demonstrations through the use of non-rigid registration","authors":"John Schulman, Jonathan Ho, Cameron Lee, Pieter Abbeel","year":"2016","venue":"Robotics Research","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Spenko et al., 2018] Matthew Spenko, Stephen Buerger, and Karl Iagnemma. The Darpa Robotics Challenge Fi- nals: Humanoid Robots To The Rescue, volume 121 of Springer Tracts in Advanced Robotics. 2018.","title":"The Darpa Robotics Challenge Finals: Humanoid Robots To The Rescue","authors":"Matthew Spenko, Stephen Buerger, Karl Iagnemma","year":"2018","venue":"Springer Tracts in Advanced Robotics","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Taïx et al., 2012] Michel Taïx, David Flavigné, and Etienne Ferré. Human interaction with motion planning algorithm. J. Intell. Robot. Syst., 67(3):285-306, 2012.","title":"Human interaction with motion planning algorithm","authors":"Michel Taïx, David Flavigné, Etienne Ferré","year":"2012","venue":"J. Intell. Robot. Syst","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Vijayakumar, 2017] Karthik Vijayakumar. A multi- heuristic framework for humanoid planning. Master's the- sis, Robotics Institute, Carnegie Mellon University, 2017.","title":"A multiheuristic framework for humanoid planning","authors":"Karthik Vijayakumar","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Xia et al., 2009] Zeyang Xia, Guodong Chen, Jing Xiong, Qunfei Zhao, and Ken Chen. A random sampling-based approach to goal-directed footstep planning for humanoid robots. In AIM, pages 168-173, 2009.","title":"A random sampling-based approach to goal-directed footstep planning for humanoid robots","authors":"Zeyang Xia, Guodong Chen, Jing Xiong, Qunfei Zhao, Ken Chen","year":"2009","venue":"AIM","doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Yan et al., 2015] Yu Yan, Emilie Poirson, and Fouad Ben- nis. An interactive motion planning framework that can learn from experience. CAD, 59:23-38, 2015.","title":"An interactive motion planning framework that can learn from experience","authors":"Yu Yan, Emilie Poirson, Fouad Bennis","year":"2015","venue":"CAD","doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Ye and Alterovitz, 2017] Gu Ye and Ron Alterovitz. Demonstration-guided motion planning. In Robotics Research, pages 291-307. 2017.","title":"Demonstration-guided motion planning","authors":"Gu Ye, Ron Alterovitz","year":"2017","venue":"Robotics Research","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}