Lawson L.S. Wong
Assistant Professor
Office: 513 ISEC (805 Columbus Avenue) |
|
Assistant Professor (Northeastern): 2018-present
Robot Navigation in Unseen Environments using Coarse Maps
Chengguang Xu, Christopher Amato, Lawson L.S. Wong
IEEE International Conference on Robotics and Automation (ICRA), 2024
[pdf]
[mp4]
A Hierarchical Framework for Robot Safety using Whole-body Tactile Sensors
Shuo Jiang, Lawson L.S. Wong
IEEE International Conference on Robotics and Automation (ICRA), 2024
[pdf]
[mp4]
Snake Robot with Tactile Perception Navigates on Large-scale Challenging Terrain
Shuo Jiang, Adarsh Salagame, Alireza Ramezani, Lawson L.S. Wong
IEEE International Conference on Robotics and Automation (ICRA), 2024
[pdf]
[mp4]
E(2)-Equivariant Graph Planning for Navigation
Linfeng Zhao, Hongyu Li, Taskin Padir, Huaizu Jiang, Lawson L.S. Wong
IEEE Robotics and Automation Letters (RA-L), 2024
[pdf]
[RA-L]
[arXiv]
Modeling Dynamics over Meshes with Gauge Equivariant Nonlinear Message Passing
Jung Yeon Park, Lawson L.S. Wong, Robin Walters
Neural Information Processing Systems (NeurIPS), 2023
[pdf]
[NeurIPS]
[arXiv]
One-shot Imitation Learning via Interaction Warping
Ondrej Biza, Skye Thompson, Kishore Reddy Pagidi, Abhinav Kumar, Elise van der Pol, Robin Walters, Thomas Kipf, Jan-Willem van de Meent, Lawson L.S. Wong, Robert Platt
Conference on Robot Learning (CoRL), 2023
[pdf]
[CoRL]
[arXiv]
“The wallpaper is ugly”: Indoor Localization using Vision and Language
Seth Pate, Lawson L.S. Wong
IEEE International Conference on Robot and Human Interactiv Communication (RO-MAN), 2023
[pdf]
[RO-MAN]
Integrating Symmetry into Differentiable Planning with Steerable Convolutions
Linfeng Zhao, Xupeng Zhu*, Lingzhi Kong*, Robin Walters, Lawson L.S. Wong
International Conference on Learning Representations (ICLR), 2023
[pdf]
[ICLR]
[arXiv]
Scaling up and Stabilizing Differentiable Planning with Implicit Differentiation
Linfeng Zhao, Huazhe Xu, Lawson L.S. Wong
International Conference on Learning Representations (ICLR), 2023
[pdf]
[ICLR]
[arXiv]
The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetry
Dian Wang, Jung Yeon Park, Neel Sortur, Lawson L.S. Wong, Robin Walters, Robert Platt
International Conference on Learning Representations (ICLR), 2023
[pdf]
[ICLR]
[arXiv]
Robust Imitation of a Few Demonstrations with a Backwards Model
Jung Yeon Park, Lawson L.S. Wong
Neural Information Processing Systems (NeurIPS), 2022
[pdf]
[NeurIPS]
[arXiv]
Active Tactile Exploration using Shape-Dependent Reinforcement Learning
Shuo Jiang, Lawson L.S. Wong
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022
[pdf]
[mp4]
[IROS]
Toward Compositional Generalization in Object-Oriented World Modeling
Linfeng Zhao, Lingzhi Kong, Robin Walters, Lawson L.S. Wong
International Conference on Machine Learning (ICML), 2022
[pdf]
[ICML]
[arXiv]
Binding Actions to Objects in World Models
Ondřej Bíža, Robert Platt, Jan-Willem van de Meent, Lawson L.S. Wong, Thomas Kipf
International Conference on Learning Representations (ICLR) Workshop on the Elements of Reasoning: Objects, Structure, and Causality, 2022
[pdf]
[ICLR WS]
[arXiv]
Factored World Models for Zero-Shot Generalization in Robotic Manipulation
Ondřej Bíža, Thomas Kipf, David Klee, Robert Platt, Jan-Willem van de Meent, Lawson L.S. Wong
[arXiv]
Natural Language for Human-Robot Collaboration: Problems Beyond Language Grounding
Seth Pate, Wei Xu, Ziyi Yang, Maxwell Love, Siddarth Ganguri, Lawson L.S. Wong
AAAI Fall Symposium on Artificial Intelligence for Human-Robot Interaction (AI-HRI), 2021
[pdf]
[AI-HRI]
[arXiv]
Bad-Policy Density: A Measure of Reinforcement-Learning Hardness
David Abel, Cameron Allen, Dilip Arumugam, D. Ellis Hershkowitz, Michael L. Littman, Lawson L.S. Wong
International Conference on Machine Learning (ICML) Workshop on Reinforcement Learning Theory, 2021
[pdf]
[ICML WS]
[arXiv]
Action Priors for Large Action Spaces in Robotics
Ondřej Bíža, Dian Wang, Robert Platt, Jan-Willem van de Meent, Lawson L.S. Wong
International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2021
[pdf]
[AAMAS]
[arXiv]
Learning Discrete State Abstractions with Deep Variational Inference
Ondřej Bíža, Robert Platt, Jan-Willem van de Meent, Lawson L.S. Wong
Symposium on Advances in Approximate Bayesian Inference (AABI), 2021
[pdf]
[AABI]
[arXiv]
Deep Imitation Learning for Bimanual Robotic Manipulation
Fan Xie, Alexander Chowdhury, M. Clara De Paolis Kaluza, Linfeng Zhao, Lawson L.S. Wong, Rose Yu
Neural Information Processing Systems (NeurIPS), 2020
[pdf]
[NeurIPS]
[arXiv]
Model-based Navigation in Environments with Novel Layouts Using Abstract 2-D Maps
Linfeng Zhao, Lawson L.S. Wong
Neural Information Processing Systems (NeurIPS) Workshop on Deep Reinforcement Learning, 2020
[pdf]
[NeurIPS WS]
Hierarchical Robot Navigation in Novel Environments Using Rough 2-D Maps
Chengguang Xu, Christopher Amato, Lawson L.S. Wong
Conference on Robot Learning (CoRL), 2020
[pdf]
[CoRL]
[arXiv]
Postdoctoral Fellow (Brown): 2016-2018
Grounding Natural Language Instructions to Semantic Goal Representations for Abstraction and Generalization
Dilip Arumugam*, Siddharth Karamcheti*, Nakul Gopalan, Edward C. Williams, Mina Rhee, Lawson L.S. Wong, Stefanie Tellex
Autonomous Robots (AURO), 2019.
[pdf (preprint)]
[AURO]
Multi-Object Search using Object-Oriented POMDPs
Arthur Wandzel, Yoonseon Oh, Michael Fishman, Nishanth Kumar, Lawson L.S. Wong, Stefanie Tellex
IEEE International Conference on Robotics and Automation (ICRA), 2019
[pdf]
[mp4]
State Abstraction as Compression in Apprenticeship Learning
David Abel, Dilip Arumugam, Kavosh Asadi, Yuu Jinnai, Michael L. Littman, Lawson L.S. Wong
AAAI Conference on Artificial Intelligence (AAAI), 2019
[pdf]
Sequence-to-Sequence Language Grounding of Non-Markovian Task Specifications
Nakul Gopalan*, Dilip Arumugam*, Lawson L.S. Wong, Stefanie Tellex.
Robotics: Science and Systems (RSS), 2018
[pdf]
Accurately and Efficiently Interpreting Human-Robot Instructions of Varying Granularities
Dilip Arumugam*, Siddharth Karamcheti*, Nakul Gopalan, Lawson L.S. Wong, Stefanie Tellex
Robotics: Science and Systems (RSS), 2017
[pdf]
[YouTube]
Planning with Abstract Markov Decision Processes
Nakul Gopalan, Marie desJardins, Michael L. Littman, James MacGlashan, Shawn Squire, Stefanie Tellex, John Winder, Lawson L.S. Wong
International Conference on Automated Planning and Scheduling (ICAPS), 2017
[pdf]
[YouTube]
Reducing Errors in Object-Fetching Interactions through Social Feedback
David Whitney, Eric Rosen, James MacGlashan, Lawson L.S. Wong, Stefanie Tellex
IEEE International Conference on Robotics and Automation (ICRA), 2017
[pdf]
[YouTube]
Ph.D. (MIT): 2009-2016
I completed my Ph.D. in 2016 at the MIT Computer Science and Artificial Intelligence Laboratory. I was a part of the Learning and Intelligent Systems Group, supervised by Leslie Pack Kaelbling and Tomás Lozano-Pérez.
My Ph.D. dissertation is about learning the state of the world for mobile-manipulation robots such as the Willow Garage PR2. Mobile-manipulation robots performing service tasks in human-centric indoor environments have long been a dream for developers of autonomous agents. Tasks such as cooking and cleaning typically involve interaction with the environment, hence robots need to know relevant aspects of their spatial surroundings. However, this information is rarely given a priori, and even if it is, the state of the world inevitably changes over time. Additionally, most information about the world is irrelevant to any particular task at hand.
Mobile manipulation robots therefore need to continuously perform the task of state estimation, using perceptual information to maintain a representation of the state, and its uncertainty, of task-relevant aspects of the world. By definition, mobile-manipulation robots are capable of moving in and interacting with the world. Hence, at the very least, such robots need to know about the physical occupancy of space and potential targets of interaction (i.e., objects). In my thesis, I proposed a representation based on objects, their 'semantic' attributes (task-relevant properties such as type and pose), and their geometric realizations in the physical world.
Learning the State of the World: Object-based World Modeling for Mobile-Manipulation Robots
Lawson L.S. Wong.
MIT EECS Ph.D. Dissertation, 2016.
[pdf]
MIT EECS Ph.D. Thesis Proposal, 2014.
[pdf]
Object-based World Modeling in Semi-Static Envrionments with Dependent Dirichlet Process Mixtures
Lawson L.S. Wong, Thanard Kurutach, Tomás Lozano-Pérez, Leslie Pack Kaelbling.
International Joint Conference on Artificial Intelligence (IJCAI), 2016.
[pdf]
Searching for Physical Objects in Partially Known Environments
Xinkun Nie, Lawson L.S. Wong, Leslie Pack Kaelbling.
IEEE International Conference on Robotics and Automation (ICRA), 2016.
[pdf]
Data Association for Semantic World Modeling from Partial Views
Lawson L.S. Wong, Leslie Pack Kaelbling, Tomás Lozano-Pérez.
International Journal of Robotics Research (IJRR), 2015.
[pdf (preprint)]
[IJRR]
Not Seeing is Also Believing: Combining Object and Metric Spatial Information
Lawson L.S. Wong, Leslie Pack Kaelbling, Tomás Lozano-Pérez.
IEEE International Conference on Robotics and Automation (ICRA), 2014.
[pdf]
[mp4]
Data Association for Semantic World Modeling from Partial Views
Lawson L.S. Wong, Leslie Pack Kaelbling, Tomás Lozano-Pérez.
International Symposium on Robotics Research (ISRR), 2013.
[pdf]
Manipulation-based Active Search for Occluded Objects
Lawson L.S. Wong, Leslie Pack Kaelbling, Tomás Lozano-Pérez.
IEEE International Conference on Robotics and Automation (ICRA), 2013.
[pdf]
[mp4]
Collision-free State Estimation.
Lawson L.S. Wong, Leslie Pack Kaelbling, Tomás Lozano-Pérez.
IEEE International Conference on Robotics and Automation (ICRA), 2012.
[pdf]
Undergraduate (Stanford): 2005-2009
During my undergraduate years at Stanford, I worked on the Stanford Artificial Intelligence Robot (STAIR) project, under the Perception/Manipulation group. My main work was on teaching STAIR how to grasp objects that it has not seen before by learning visual (2-D and 3-D) features of successful and unsuccessful grasp examples; this culminated in my undergraduate honors thesis. I was supervised by Ashutosh Saxena and advised by Andrew Ng.
Robotic Grasping on the Stanford Artificial Intelligence Robot.
Lawson L.S. Wong.
Undergraduate Computer Science Honors Thesis, 2008.
(Ben Wegbreit Prize for Best Computer Science Honors Thesis)
[pdf]
Learning Grasp Strategies with Partial Shape Information.
Ashutosh Saxena, Lawson L.S. Wong, Andrew Y. Ng.
AAAI Conference on Artificial Intelligence (AAAI), 2008.
[pdf]
A Vision-based System for Grasping Novel Objects in Cluttered Environments.
Ashutosh Saxena, Lawson Wong, Morgan Quigley, Andrew Y. Ng.
International Symposium on Robotics Research (ISRR), 2007.
[pdf]