I am an Assistant Professor and the director of the Personal Autonomous Robotics Lab (PeARL) in the Department of Computer Science at the University of Texas at Austin. I am also a core faculty member in the interdepartmental robotics group at UT.
The goal of my research is to enable personal robots to be deployed in the home and workplace with minimal intervention by robotics experts. In settings such as these, robots do not operate in isolation, but have continual interactions with people and objects in the world. With this in mind, we focus on developing algorithms to solve problems that robot learners encounter in real-world interactive settings. Thus, our work draws roughly equally from both machine learning and robotics, including topics such as learning from demonstration, manipulation, probabilistic safety, human-robot interaction, and reinforcement learning.
Recent News
- 12/8/18 — Our new paper on Machine Teaching for Inverse Reinforcement Learning: Algorithms and Applications will appear at AAAI 2019.
- 10/4/18 — Two new CoRL 2018 papers now available: Efficient Hierarchical Robot Motion Planning Under Uncertainty and Hybrid Dynamics and Risk-Aware Active Inverse Reinforcement Learning.
- 3/23/18 — I was awarded the 2018 NSF CAREER Award.
- 1/12/18 — Two ICRA 2018 papers accepted on Active Reward Learning from Critiques and Incremental Task Modification via Corrective Demonstrations.
- 11/9/17 — Two new AAAI 2018 papers accepted on Efficient Probabilistic Performance Bounds for Inverse Reinforcement Learning and Safe Reinforcement Learning via Shielding.
- 8/6/17 — New ICML 2017 paper now available, showing a novel and efficient method for off-policy evaluation: Data-Efficient Policy Evaluation Through Behavior Policy Search.
- 7/30/17 — Our team UT Austin Villa won third place in the 2017 Robocup@Home Domestic Standard Platform League in Nagoya, Japan. And we got a shiny trophy!
- 6/22/17 — We have five workshop papers at RSS 2017 on active inverse reinforcement learning, human mental modeling, incremental learning from demonstration, hybrid POMDP planning, and visually grounding spatial relationships.
- 6/14/17 — Two papers accepted to IROS 2017 on Viewpoint Selection for Visual Failure Detection and Error Correction for Brain-Computer Interfaces.
- 5/12/17 — Our AAMAS 2017 paper shows how to perform safe policy evaluation more efficienty: Bootstrapping with Models: Confidence Intervals for Off-Policy Evaluation.
