Learning and Intelligent Systems Group
Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology
32 Vassar Street, Cambridge MA 02139

Home | People | Research | Publications | Alumni

Members of the LIS group work in a broad set of research areas, here are some publications in areas of recent interest; for a full list click on Publications.

Integrated Task and Motion Planning

Project page: click for more details (including videos)

2013
[6]	Manipulation-based Active Search for Occluded Objects (Lawson L. S. Wong, Leslie Pack Kaelbling, Tomas Lozano-Perez), In IEEE Conference on Robotics and Automation (ICRA), 2013. (movie) [bib] [pdf]
[5]	Integrated Task and Motion Planning in Belief Space (Leslie Pack Kaelbling, Tomas Lozano-Perez), In International Journal of Robotics Research, 2013. [bib] [pdf]
[4]	Optimization in the Now: Dynamic Peephole Optimization for Hierarchical Planning (Dylan Hadfield-Menell, Leslie Pack Kaelbling, Tomas Lozano-Perez), In IEEE Conference on Robotics and Automation (ICRA), 2013. [bib] [pdf]
2012
[3]	Unifying Perception, Estimation and Action for Mobile Manipulation via Belief Space Planning (Leslie Pack Kaelbling, Tomas Lozano-Perez), In IEEE Conference on Robotics and Automation (ICRA), 2012. [bib] [pdf]
2011
[2]	Pre-image backchaining in belief space for mobile manipulation (Leslie Pack Kaelbling, Tomás Lozano-Pérez), In International Symposium on Robotics Research (ISRR), 2011. [bib] [pdf]
[1]	Hierarchical Planning in the Now (Leslie Pack Kaelbling, Tomas Lozano-Perez), In IEEE Conference on Robotics and Automation (ICRA), 2011. (Finalist, Best Manipulation Paper Award) [bib] [pdf]

Belief Space Planning

2013
[7]	Optimal Sampling-Based Planning for Linear-Quadratic Kinodynamic Systems (G. Goretkin, A. Perez, R. Platt, G.D. Konidaris), In IEEE Conference on Robotics and Automation (ICRA), 2013. [bib] [pdf]
2012
[6]	LQR-RRT*: Optimal Sampling-Based Motion Planning with Automatically Derived Extension Heuristics (A. Perez, R. Platt, G.D. Konidaris, L.P. Kaelbling, T. Lozano-Perez), In Proceedings of the IEEE International Conference on Robotics and Automation, 2012. [bib] [pdf]
[5]	Non-Gaussian Belief Space Planning: Correctness and Complexity (Robert Platt, Leslie Kaelbling, Tomas Lozano-Perez, Russ Tedrake), In IEEE Conference on Robotics and Automation (ICRA), 2012. [bib] [pdf]
[4]	Unifying Perception, Estimation and Action for Mobile Manipulation via Belief Space Planning (Leslie Pack Kaelbling, Tomas Lozano-Perez), In IEEE Conference on Robotics and Automation (ICRA), 2012. [bib] [pdf]
2011
[3]	Simultaneous Localization and Grasping as a Belief Space Control Problem (Robert Platt, Leslie Pack Kaelbling, Tomas Lozano-Perez, Russ Tedrake), In International Symposium on Robotics Research (ISRR), 2011. [bib] [pdf]
[2]	Pre-image backchaining in belief space for mobile manipulation (Leslie Pack Kaelbling, Tomás Lozano-Pérez), In International Symposium on Robotics Research (ISRR), 2011. [bib] [pdf]
2010
[1]	Belief space planning assuming maximum likelihood observations (Robert Platt, Russell Tedrake, Leslie Kaelbling, Tomas Lozano-Perez), In Robotics Science and Systems Conference (RSS), 2010. [bib] [pdf]

Reinforcement Learning

2012
[9]	Transfer Learning by Discovering Latent Task Parametrizations (F. Doshi-Velez, G.D. Konidaris), In NIPS 2012 Workshop on Bayesian Nonparametric Models for Reliable Planning And Decision-Making Under Uncertainty, 2012. [bib] [pdf]
[8]	Learning and Generalization of Complex Tasks from Unstructured Demonstrations (S. Niekum, S. Osentoski, G.D. Konidaris, A.G. Barto), In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2012. [bib] [pdf]
[7]	Learning Parameterized Skills (B.C. da Silva, G.D. Konidaris, A.G. Barto), In Proceedings of the Twenty Ninth International Conference on Machine Learning, 2012. [bib] [pdf]
[6]	Transfer in Reinforcement Learning via Shared Features (G.D. Konidaris, I. Scheidwasser, A.G. Barto), In Journal of Machine Learning Research, volume 13, 2012. [bib] [pdf]
[5]	Robot Learning from Demonstration by Constructing Skill Trees (G.D. Konidaris, S.R. Kuindersma, R.A. Grupen, A.G. Barto), In International Journal of Robotics Research, volume 31, 2012. [bib] [pdf]
2011
[4]	TD_γ: Re-evaluating Complex Backups in Temporal Difference Learning (G.D. Konidaris, S. Niekum, P.S. Thomas), In Advances in Neural Information Processing Systems 24, 2011. [bib] [pdf]
[3]	Value Function Approximation in Reinforcement Learning using the Fourier Basis (G.D. Konidaris, S. Osentoski, P.S. Thomas), In Proceedings of the Twenty-Fifth Conference on Artificial Intelligence, 2011. [bib] [pdf]
[2]	Autonomous Skill Acquisition on a Mobile Manipulator (G.D. Konidaris, S.R. Kuindersma, R.A. Grupen, A.G. Barto), In Proceedings of the Twenty-Fifth Conference on Artificial Intelligence, 2011. [bib] [pdf]
2000
[1]	Practical Reinforcement Learning (William D. Smart, Leslie Pack Kaelbling), In International Conference on Machine Learning (ICML), 2000. [bib] [pdf]

Manipulation Planning

Project page (DARRTH): click for more details (including videos)
Project page (Handey): click for more details (including videos)

2013
[4]	Object Placement as Inverse Motion Planning (Anne Holladay, Jennifer Barry, Leslie Pack Kaelbling, Tomas Lozano-Perez), In IEEE Conference on Robotics and Automation (ICRA), 2013. (movie) [bib] [pdf]
[3]	A Hierarchical Approach to Manipulation with Diverse Actions (Jennifer Barry, Leslie Pack Kaelbling, Tomas Lozano-Perez), In IEEE Conference on Robotics and Automation (ICRA), 2013. [bib] [pdf]
2012
[2]	Manipulation with Multiple Action Types (J. Barry, K. Hsiao, L. P. Kaelbling, T. Lozano-Pérez), In International Symposium on Experimental Robotics, 2012. [bib] [pdf]
1992
[1]	HANDEY: A Robot Task Planner (Tomas Lozano-Perez, Joseph L. Jones, Emanuel Mazer, Patrick A. O'Donnell), MIT Press, 1992. [bib] [pdf]

Grasping

Project page (WRT Grasping): click for more details (including videos)
Project page (Grasping POMDPs): click for more details (including videos)

2011
[6]	Simultaneous Localization and Grasping as a Belief Space Control Problem (Robert Platt, Leslie Pack Kaelbling, Tomas Lozano-Perez, Russ Tedrake), In International Symposium on Robotics Research (ISRR), 2011. [bib] [pdf]
[5]	Robust grasping under object pose uncertainty (Kaijen Hsiao, Leslie Pack Kaelbling, Tomas Lozano-Perez), In Autonomous Robots, volume 31, 2011. [bib] [pdf]
2010
[4]	Task-driven Tactile Exploration (Kaijen Hsiao, Leslie Pack Kaelbling, Tomas Lozano-Perez), In Robotics Science and Systems (RSS), 2010. [bib] [pdf]
2008
[3]	Robust Belief-Based Execution of Manipulation Programs (Kaijen Hsiao, Tomas Lozano-Perez, Leslie Pack Kaelbling), In Eighth International Workshop on the Algorithmic Foundations of Robotics (WAFR), 2008. [bib] [pdf]
2007
[2]	Grasping POMDPs (Kaijen Hsiao, Leslie Pack Kaelbling, Tomas Lozano-Perez), In IEEE International Conference on Robotics and Automation, 2007. [bib] [pdf]
2006
[1]	Imitation Learning of Whole-Body Grasps (Kaijen Hsiao, Tomas Lozano-Perez), In IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS), 2006. [bib] [pdf]

Multiagent Planning

2013
[8]	Producing Efficient Error-bounded Solutions for Transition Independent Decentralized MDPs (Jilles S. Dibangoye, Christopher Amato, Arnaud Doniec, François Charpillet), In Proceedings of the Twelfth International Conference on Autonomous Agents and Multiagent Systems, 2013. [bib] [pdf]
2012
[7]	Scaling Up Decentralized MDPs Through Heuristic Search (Jilles S. Dibangoye, Christopher Amato, Arnaud Doniec), In Proceedings of the Twenty-Eighth Conference on Uncertainty in Artificial Intelligence, 2012. [bib] [pdf]
[6]	Influence-Based Abstraction for Multiagent Systems (Frans A. Oliehoek, Stefan Witwicki, Leslie P. Kaelbling), In Proceedings of the National Conference on Artificial Intelligence, 2012. [bib] [pdf]
[5]	Tree-Based Solution Methods for Multiagent POMDPs with Delayed Communication (Frans A. Oliehoek, Matthijs T. J. Spaan), In Proceedings of the National Conference on Artificial Intelligence, 2012. [bib] [pdf]
[4]	Heuristic Search of Multiagent Influence Space (Stefan Witwicki, Frans A. Oliehoek, Leslie P. Kaelbling), In Proceedings of The International Joint Conference on Autonomous Agents and Multi Agent Systems, 2012. [bib] [pdf]
2011
[3]	Scaling Up Optimal Heuristic Search in Dec-POMDPs via Incremental Expansion (Matthijs T. J. Spaan, Frans A. Oliehoek, Christopher Amato), In Proceedings of the International Joint Conference on Artificial Intelligence, 2011. (A version appeared in AAMAS Workshop on Multi-agent Sequential Decision Making in Uncertain Domains and as extended abstract in Proc. of 23rd Benelux Conference on Artificial Intelligence) [bib] [pdf]
2004
[2]	All learning is Local: Multi-agent Learning in Global Reward Games (Yu-Han Chang, Tracey Ho, Leslie Pack Kaelbling), In Advances in Neural Information Processing Systems 16 (Sebastian Thrun, Lawrence Saul, Bernhard Schölkopf, eds.), MIT Press, 2004. [bib] [pdf]
2000
[1]	Learning to Cooperate via Policy Search (Leonid Peshkin, Kee-Eung Kim, Nicolas Meuleau, Leslie Pack Kaelbling), In Sixteenth Conference on Uncertainty in Artificial Intelligence (UAI-2000), 2000. [bib] [pdf]

(PO)MDP

2012
[7]	Diagnose and Decide: An Optimal Bayesian Approach (Christopher Amato, Emma Brunskill), In Proceedings of the Workshop on Bayesian Optimization and Decision Making at NIPS 2012, 2012. [bib] [pdf]
2011
[6]	Bayesian Policy Search with Policy Priors (David Wingate, Noah D. Goodman, Daniel M. Roy, Leslie P. Kaelbling, Joshua B. Tenenbaum), In International Joint Conference on Artificial Intelligence (IJCAI), 2011. [bib] [pdf]
[5]	DetH*: Approximate Hierarchical Solution of Large Markov Decision Processes (Jennifer L. Barry, Leslie Pack Kaelbling, Tomás Lozano-Pérez), In International Joint Conference on Artificial Intelligence (IJCAI), 2011. [bib] [pdf]
2010
[4]	Planning in partially observable switching-mode continuous domains (Emma Brunskill, Leslie Pack Kaelbling, Tomas Lozano-Perez, Nicholas Roy), In Annals of Mathematics and Artificial Intelligence, 2010. [bib] [pdf]
2004
[3]	Envelope-based Planning in Relational MDPs (Natalia H. Gardiol, Leslie Pack Kaelbling), In NIPS, volume 16, 2004. [bib] [pdf]
[2]	Approximate Planning in POMDPs with Macro-Actions (Georgios Theocharous, Leslie Pack Kaelbling), In Advances in Neural Information Processing Systems 16 (NIPS03), 2004. [bib] [pdf]
2002
[1]	Nearly deterministic abstractions of Markov decision processes (Terran Lane, Leslie Pack Kaelbling), In 18th National Conference on Artificial Intelligence, 2002. [bib] [pdf]

Game AI

2012
[2]	POMCoP: Belief Space Planning for Sidekicks in Cooperative Games (O. Macindoe, L. P. Kaelbling, T. Lozano-Pérez), In Proceedings of the 8th Annual AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 2012. (Best Paper Award) [bib] [pdf]
2011
[1]	CAPIR: Collaborative Action Planning with Intention Recognition (Truong-Huy Dinh Nguyen, David Hsu, Wee-Sun Lee, Tze-Yun Leong, Leslie Pack Kaelbling, Tomas Lozano-Perez, Andrew Haydn Grant), In Artificial Intelligence and Interactive Digital Entertainment Conference (AIIDE), 2011. [bib] [pdf]

Transfer Learning

2007
[3]	Efficient Bayesian Task-level Transfer Learning (Daniel M. Roy, Leslie Pack Kaelbling), In International Joint Conference on Artificial Intelligence (IJCAI), 2007. [bib] [pdf]
[2]	Learning Probabilistic Relational Dynamics for Multiple Tasks (Ashwin Deshpande, Brian Milch, Luke S. Zettlemoyer, Leslie Pack Kaelbling), In Conference on Uncertainty in Artificial Intelligence (UAI), 2007. [bib] [pdf]
2005
[1]	Transfer Learning with an Ensemble of Background Tasks (Michael Rosenstein, Zvika Marx, Tom Dietterich, Leslie Pack Kaelbling), In NIPS Workshop on Inductive Transfer, 2005. [bib] [pdf]

Object Recognition

2011
[3]	Monte Carlo Pose Estimation with Quaternion Kernels and the Bingham Distribution (J. Glover, G. Bradksi, R. Rusu), In Proceedings of Robotics: Science and Systems, 2011. [bib] [pdf]
2009
[2]	Learning to Generate Novel Views of Objects for Class Recognition. (Hang-Pan Chiu, Leslie P. Kaelbling, Tomas Lozano-Perez), In Computer Vision and Image Understanding, 2009. [bib] [pdf]
2007
[1]	Virtual Training for Multi-View Object Class Recognition. (Hang-Pan Chiu, Leslie Pack Kaelbling, Tomas Lozano-Perez), In CVPR, 2007. [bib] [pdf]

Computational Biology

2009
[4]	Rotamer optimization for protein design through MAP estimation and problem-size reduction (Eun-Jong Hong, Shaun M. Lippow, Bruce Tidor, Tomas Lozano-Perez), In J. Computational Chemistry, volume 30, 2009. [bib] [pdf]
2006
[3]	Protein side-chain placement through MAP estimation and problem-size reduction (Eun-Jong Hong, Tomas Lozano-Perez), In 6th Workshop on Algorithms in Bioinformatics(WABI), Springer, 2006. [bib] [pdf]
2002
[2]	De novo determination of peptide structure with solid-state magic-angle spinning NMR spectroscopy. (C. M. Rienstra, L. Tucker-Kellogg, C. P. Jaroniec, M. Hohwy, B. Reif, M. T. McMahon, B. Tidor, T. Lozano-Pérez, R. G. Griffin), In Proceedings of the National Academy of Sciences, USA, volume 99, 2002. [bib] [pdf]
1998
[1]	AmbiPack: a systematic algorithm for packing of macromolecular structures with ambiguous distance constraints (C.S. Wang, T. Lozano-Pérez, B. Tidor), In Proteins, volume 32, 1998. [bib] [pdf]


LIS logo design by Laura Lozano