Justin Hart
Postdoctoral Fellow
I am a clinical assistant professor with the College of Natural Sciences at the University of Texas at Austin and a postdoctoral fellow affiliated with the Building-Wide Intelligence Project and the Learning Agents Research Group under the co-supervision of professors Raymond Mooney and Peter Stone in the Department of Computer Science. Currently I am working on grounded language learning for autonomous agents operating in work environments. Previously, I was a postdoctoral fellow at the CARIS Lab at the University of British Columbia where I war advised by Professor Elizabeth Croft. There, I worked on CHARM (Collaborative Human-Focused Assistive Robotics for Manufacturing). The goal of collaborative manufacturing is to break down the barriers in factories that separate robots from humans, allowing them to safely work alongside one another. Similar to my work at UT Austin, my role was to develop mechanisms to allow humans and robots to clearly, naturally communicate with one another, enabling them to quickly, safely, and effectively work together. In September 2014, I defended my dissertation at Yale University where I researched in the Social Robotics Lab, advised by Professor Brian Scassellati. For my PhD research, I constructed a robot that is able to autonomously learn about its sensory and motor capabilities, breaking from the standard practice in which such models, if present at all, are constructed during the design of the robot, by engineers, or meticulously calibrated offline. If robots are able to understand themselves in this way, it will open the possibility of highly robust machines that are able to adapt flexibly to different use cases or to damage, in software, and very precise machines that continuously self-calibrate. The models that my robot constructs are inspired by the process by which children learn about their sensory and physical capabilities and how they are able to interact with the environment, which represent the earliest forms of self-awareness to develop during infancy.
Interaction and Autonomy in RoboCup@Home and Building-Wide Intelligence 2018
Justin Hart, Harel Yedidsion, Yuqian Jiang, Nick Walker, Rishi Shah, Jesse Thomason, Aishwarya Padmakumar, Rolando Fernandez, Jivko Sinapov, Raymond Mooney, Peter Stone, In Artificial Intelligence (AI) for Human-Robot Interaction (HRI) symposium, AAAI Fall Symposium Series, Arlington, Virginia, October 2018.
Jointly Improving Parsing and Perception for Natural Language Commands through Human-Robot Dialog 2018
Jesse Thomason, Aishwarya Padmakumar, Jivko Sinapov, Nick Walker, Yuqian Jiang, Harel Yedidsion, Justin Hart, Peter Stone, and Raymond J. Mooney, In RSS Workshop on Models and Representations for Natural Human-Robot Communication (MRHRC-18). Robotics: Science and Systems (RSS), June 2018.
Jointly Improving Parsing and Perception for Natural Language Commands through Human-Robot Dialog 2018
Jesse Thomason, Aishwarya Padmakumar, Jivko Sinapov, Nick Walker, Yuqian Jiang, Harel Yedidsion, Justin Hart, Peter Stone, and Raymond J. Mooney, In Late-breaking Track at the SIGDIAL Special Session on Physically Situated Dialogue (RoboDIAL-18), Melbourne, Australia, July 2018.
Passive Demonstrations of Light-Based Robot Signals for Improved Human Interpretability 2018
Rolando Fernandez, Nathan John, Sean Kirmani, Justin Hart, Jivko Sinapov, and Peter Stone, In Proceedings of the 27th {IEEE} International Symposium on Robot and Human Interactive Communication {(RO-MAN)}, Nanjing, China, August 2018.
PRISM: Pose Registration for Integrated Semantic Mapping 2018
Justin W. Hart, Rishi Shah, Sean Kirmani, Nick Walker, Kathryn Baldauf, Nathan John, and Peter Stone, In Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain, October 2018.
Opportunistic Active Learning for Grounding Natural Language Descriptions 2017
Jesse Thomason, Aishwarya Padmakumar, Jivko Sinapov, Justin Hart, Peter Stone, and Raymond J. Mooney, In Proceedings of the 1st Annual Conference on Robot Learning (CoRL-17), Sergey Levine and Vincent Vanhoucke and Ken Goldberg (Eds.), pp. 67--76, Mountain View, California, November 2017. PMLR.
Currently affiliated with Learning Agents