Sotabase

Career

· Professor, University of Washington2024–
· Chief Executive Officer, Overland AI2023–
· Associate Professor, University of Washington2019–2024
· Principal Research Scientist, NVIDIA2018–2022
· Visiting Faculty, Google2017–2017
· Assistant Professor, Georgia Institute of Technology2014–2019
· Postdoctoral Scholar, University of Washington2012–2014
· Doctoral Student, Carnegie Mellon University2006–2012
· Associate Researcher, Duke University2004–2006
· Robotics Engineer, ActivMedia Robotics2003–2004
· MS and PhD, Machine Learning, Carnegie Mellon University

Publications (231)

One-Shot Learning for Semantic Segmentation
British Machine Vision Conference · 2017
834
cited
Information theoretic MPC for model-based reinforcement learning
IEEE International Conference on Robotics and Automation · 2017
590
cited
Differentiable MPC for End-to-end Planning and Control
Neural Information Processing Systems · 2018
431
cited
Truncated Back-propagation for Bilevel Optimization
International Conference on Artificial Intelligence and Statistics · 2018
300
cited
Agile Autonomous Driving using End-to-End Deep Imitation Learning
Robotics: Science and Systems · 2017
277
cited
Closing the learning-planning loop with predictive state representations
Int. J. Robotics Res. · 2009
268
cited
Continuous-time Gaussian process motion planning via probabilistic inference
Int. J. Robotics Res. · 2017
251
cited
Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction
International Conference on Machine Learning · 2017
245
cited
Hilbert Space Embeddings of Hidden Markov Models
International Conference on Machine Learning · 2010
242
cited
Imitation learning for agile autonomous driving
Int. J. Robotics Res. · 2019
162
cited
Gaussian Process Motion planning
IEEE International Conference on Robotics and Automation · 2016
149
cited
A Constraint Generation Approach to Learning Stable Linear Dynamical Systems
Neural Information Processing Systems · 2007
145
cited
STORM: An Integrated Framework for Fast Joint-Space Model-Predictive Control for Reactive Manipulation
Conference on Robot Learning · 2021
143
cited
Motion Planning as Probabilistic Inference using Gaussian Processes and Factor Graphs
Robotics: Science and Systems · 2016
139
cited
Reduced-Rank Hidden Markov Models
International Conference on Artificial Intelligence and Statistics · 2009
136
cited
IRIS: Implicit Reinforcement without Interaction at Scale for Learning Control from Offline Robot Manipulation Data
IEEE International Conference on Robotics and Automation · 2019
134
cited
Learning from Conditional Distributions via Dual Embeddings
International Conference on Artificial Intelligence and Statistics · 2016
133
cited
Fast and Efficient Locomotion via Learned Gait Transitions
Conference on Robot Learning · 2021
118
cited
Provably Efficient Imitation Learning from Observation Alone
International Conference on Machine Learning · 2019
110
cited
4D crop monitoring: Spatio-temporal reconstruction for agriculture
IEEE International Conference on Robotics and Automation · 2016
108
cited
Sotabase