{"type":"ScholarlyArticle","title":"Interactive Robot Transition Repair With SMT","authors":[{"name":"Jarrett Holtz","slug":"jarrett-holtz","given":"Jarrett","family":"Holtz","affiliation":"University of Massachusetts Amherst"},{"name":"Arjun Guha","slug":"arjun-guha","given":"Arjun","family":"Guha","affiliation":"University of Massachusetts Amherst"},{"name":"Joydeep Biswas","slug":"joydeep-biswas","given":"Joydeep","family":"Biswas","affiliation":"University of Massachusetts Amherst"}],"abstract":"Complex robot behaviors are often structured as\r\nstate machines, where states encapsulate actions\r\nand a transition function switches between states.\r\nSince transitions depend on physical parameters,\r\nwhen the environment changes, a roboticist has to\r\npainstakingly readjust the parameters to work in\r\nthe new environment. We present interactive SMT-\r\nbased Robot Transition Repair (SRTR): instead of\r\nmanually adjusting parameters, we ask the roboticist to identify a few instances where the robot is\r\nin a wrong state and what the right state should\r\nbe. An automated analysis of the transition function 1) identifies adjustable parameters, 2) converts the transition function into a system of logical constraints, and 3) formulates the constraints\r\nand user-supplied corrections as a MaxSMT problem that yields new parameter values. We show\r\nthat SRTR finds new parameters 1) quickly, 2)\r\nwith few corrections, and 3) that the parameters\r\ngeneralize to new scenarios. We also show that\r\na SRTR-corrected state machine can outperform a\r\nmore complex, expert-tuned state machine.","doi":"10.24963/ijcai.2018/681","url":"https://ijcai.org/proceedings/2018/681","pdf":"https://ijcai.org/proceedings/2018/0681.pdf","markdown":"https://ijcai.org/proceedings/2018/681.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/681","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":681,"pages":{"first":4905,"last":4911},"keywords":["Robotics: Dependable Robots","Constraints and SAT: MaxSAT, MinSAT","Robotics: Robotics","Constraints and SAT: SAT: Applications"],"videos":[],"references":[{"position":1,"raw":"[Abbeel and Ng, 2011] Pieter Abbeel and Andrew Y Ng. In- verse reinforcement learning. In Encyclopedia of machine learning, pages 554-558. Springer, 2011.","title":"Inverse reinforcement learning","authors":"Ng Abbeel, Pieter Abbeel, Andrew Y Ng","year":"2011","venue":"Encyclopedia of machine learning","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Argall et al., 2009] Brenna D. Argall, Sonia Chernova, Manuela Veloso, and Brett Browning. A Survey of Robot Learning From Demonstration. Robotics and Autonomous Systems, pages 469 -483, 2009.","title":"A Survey of Robot Learning From Demonstration","authors":"Brenna D Argall, Sonia Chernova, Manuela Veloso, Brett Browning","year":"2009","venue":"Robotics and Autonomous Systems","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bai and Russell, 2017] Aijun Bai and Stuart Russell. Ef- ficient Reinforcement Learning with Hierarchies of Ma- chines by Leveraging Internal Transitions. In ICRA, 2017.","title":"Efficient Reinforcement Learning with Hierarchies of Machines by Leveraging Internal Transitions","authors":"Russell ; ] Aijun Bai, Stuart Bai, Russell","year":"2017","venue":"ICRA","doi":null,"url":null,"internal_url":"/proceedings/2017/196"},{"position":4,"raw":"[Biswas et al., 2014] Biswas, Mendoza, Zhu, Choi, Klee, and Veloso. Opponent-driven planning and execution for pass, attack, and defense in a multi-robot soccer team. In AAMAS, pages 493-500, 2014.","title":"Opponent-driven planning and execution for pass, attack, and defense in a multi-robot soccer team","authors":"Biswas, Mendoza, Zhu, Klee Choi, Veloso","year":"2014","venue":"AAMAS","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Bjørner et al., 2015] Nikolaj Bjørner, Anh-Dung Phan, and Lars Fleckenstein. νZ-an optimizing SMT solver. In Inter- national Conference on Tools and Algorithms for the Con- struction and Analysis of Systems, pages 194-199, 2015.","title":"νZ-an optimizing SMT solver","authors":"Nikolaj Bjørner, Anh-Dung Phan, Lars Fleckenstein","year":"2015","venue":"International Conference on Tools and Algorithms for the Construction and Analysis of Systems","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Bruce et al., 2008] James Bruce, Stefan Zickler, Mike Lici- tra, and Manuela Veloso. CMDragons: Dynamic Passing and Strategy on a Champion Robot Soccer Team. In ICRA, pages 4074-4079, 2008.","title":"CMDragons: Dynamic Passing and Strategy on a Champion Robot Soccer Team","authors":"James Bruce, Stefan Zickler, Mike Licitra, Manuela Veloso","year":"2008","venue":"ICRA","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Cano et al., 2016] José Cano, Alejandro Bordallo, Vijay Nagarajan, Subramanian Ramamoorthy, and Sethu Vi- jayakumar. Automatic Configuration of ROS Applications for Near-Optimal Performance. In IROS, pages 2217- 2223, 2016.","title":"Automatic Configuration of ROS Applications for Near-Optimal Performance","authors":"José Cano, Alejandro Bordallo, Vijay Nagarajan, Subramanian Ramamoorthy, Sethu Vijayakumar","year":"2016","venue":"IROS","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Dantam et al., 2013] Neil Dantam, Ayonga Hereid, Aaron Ames, and Mike Stilman. Correct Software Synthesis for Stable Speed-Controlled Robotic Walking. In RSS, 2013.","title":"Correct Software Synthesis for Stable Speed-Controlled Robotic Walking","authors":"Neil Dantam, Ayonga Hereid, Aaron Ames, Mike Stilman","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Devlin et al., 2017] Jacob Devlin, Jonathan Uesato, Surya Bhupatiraju, Rishabh Singh, Abdelrahman Mohammad, and Pushmeet Kohli. RobustFill: Neural program learn- ing under noisy I/O. In ICML, 2017.","title":"RobustFill: Neural program learning under noisy I/O","authors":"Devlin","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Gulwani, 2011] Sumit Gulwani. Automating string process- ing in spreadsheets using input-output examples. In ACM SIGPLAN Notices, pages 317-330. ACM, 2011.","title":"Automating string processing in spreadsheets using input-output examples","authors":"Sumit Gulwani","year":"2011","venue":"ACM SIGPLAN Notices","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Holtz and Biswas, 2017] Jarrett Holtz and Joydeep Biswas. Automatic Extrinsic Calibration of Depth Sensors with Ambiguous Environments and Restricted Motion. In IROS, pages 2235-2240, 2017.","title":"Automatic Extrinsic Calibration of Depth Sensors with Ambiguous Environments and Restricted Motion","authors":"Jarrett Holtz, Joydeep Biswas","year":"2017","venue":"IROS","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Jones et al., 1993] Neil D. Jones, Carsten K. Gomad, and Peter Sestoft. Partial Evaluation and Automatic Program Generation. Prentice-Hall, Inc., 1993.","title":"Partial Evaluation and Automatic Program Generation","authors":"D Neil, Carsten K Jones, Peter Gomad, Sestoft","year":"1993","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Kalmár-Nagy et al., 2004] Tamás Kalmár-Nagy, Raffaello D'Andrea, and Pritam Ganguly. Near-Optimal Dynamic Trajectory Generation and Control of an Omnidirectional Vehicle. Robotics and Autonomous Systems, pages 47-64, 2004.","title":"Near-Optimal Dynamic Trajectory Generation and Control of an Omnidirectional Vehicle","authors":"Tamás Kalmár-Nagy, D' Raffaello, Pritam Andrea, Ganguly","year":"2004","venue":"Robotics and Autonomous Systems","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kamar, 2016] Ece Kamar. Directions in Hybrid Intelli- gence: Complementing AI Systems with Human Intelli- gence. In ICRA, 2016.","title":"Directions in Hybrid Intelligence: Complementing AI Systems with Human Intelligence","authors":"Ece Kamar, Kamar","year":"2016","venue":null,"doi":null,"url":null,"internal_url":"/proceedings/2016/603"},{"position":15,"raw":"[Mechtaev et al., 2015] Sergey Mechtaev, Jooyong Yi, and Abhik Roychoudhury. DirectFix: Looking for Simple Pro- gram Repairs. In ICSE, pages 448-458, 2015.","title":"DirectFix: Looking for Simple Program Repairs","authors":"Sergey Mechtaev, Jooyong Yi, Abhik Roychoudhury","year":"2015","venue":"ICSE","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Meric ¸li et al., 2012] C ¸etin Meric ¸li, Manuela Veloso, and H Levent Akın. Multi-resolution corrective demonstration for efficient task execution and refinement. International Journal of Social Robotics, pages 423-435, 2012.","title":"Multi-resolution corrective demonstration for efficient task execution and refinement","authors":"Manuela C ¸etin Meric ¸li, H Veloso, Levent Akın","year":"2012","venue":"International Journal of Social Robotics","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Mericli et al., 2014] Cetin Mericli, Steven D. Klee, Jack Pa- parian, and Manuela Veloso. An Interactive Approach for Situated Task Specification Through Verbal Instructions. In AAMAS, pages 1069-1076, 2014.","title":"An Interactive Approach for Situated Task Specification Through Verbal Instructions","authors":"Cetin Mericli, Steven D Klee, Jack Paparian, Manuela Veloso","year":"2014","venue":"AAMAS","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Miyazawa et al., 2017] Alvaro Miyazawa, Pedro Ribeiro, Wei Li, Ana Cavalcanti, and Jon Timmis. Automatic property checking of robotic applications. In IROS, pages 3869-3876, 2017.","title":"Automatic property checking of robotic applications","authors":"Alvaro Miyazawa, Pedro Ribeiro, Wei Li, Ana Cavalcanti, Jon Timmis","year":"2017","venue":"IROS","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Nashed and Biswas, 2018] Samer Nashed and Joydeep Biswas. Human-in-the-Loop SLAM. In AAAI, 2018.","title":"Human-in-the-Loop SLAM","authors":"Samer Nashed, Joydeep Biswas","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Nedunuri et al., 2014] Srinivas Nedunuri, Sailesh Prabhu, Mark Moll, Swarat Chaudhuri, and Lydia E. Kavraki. SMT-based synthesis of integrated task and motion plans from plan outlines. In ICRA, pages 655-662, 2014.","title":"SMT-based synthesis of integrated task and motion plans from plan outlines","authors":"Srinivas Nedunuri, Sailesh Prabhu, Mark Moll, Swarat Chaudhuri, Lydia E Kavraki","year":"2014","venue":"ICRA","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Reiter, 1987] Raymond Reiter. A Theory of Diagnosis from First Principles. Artificial Intelligence, pages 57-95, 1987.","title":"A Theory of Diagnosis from First Principles","authors":"Raymond Reiter","year":"1987","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Weiss et al., 2017] Aaron Weiss, Arjun Guha, and Yuriy Brun. Tortoise: Interactive System Configuration Repair. In ASE, pages 625-636, 2017.","title":"Tortoise: Interactive System Configuration Repair","authors":"Aaron Weiss, Arjun Guha, Yuriy Brun","year":"2017","venue":"ASE","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wong et al., 2014] Kai Weng Wong, Rädiger Ehlers, and Hadas Kress-Gazit. Correct High-level Robot Behavior in Environments with Unexpected Events. In RSS, 2014.","title":"Correct High-level Robot Behavior in Environments with Unexpected Events","authors":"Kai Weng Wong, Rädiger Ehlers, Hadas Kress-Gazit","year":"2014","venue":"RSS","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}