Sotabase

Career

· PhD in Machine Learning, University of Cambridge2012–2017
· MPhil in Robotics, Australian Centre for Field Robotics2010–2012
· Australian Centre for Field Robotics
· Co-founder, Light Blue Labs
· Senior Manager, Toyota Research Institute
· Senior Manager, Automated Driving Advanced Development, Toyota Research Institute (TRI)
· Research Scientist, Uber ATG
· Uber ATG
· BEng in Mechatronics-Space, University of Sydney
· BSc in Math, CS, Physics, University of Sydney
· Research Scientist, Waymo

Publications (41)

Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
Neural Information Processing Systems · 2018
1,406
cited
Learning Invariant Representations for Reinforcement Learning without Reconstruction
International Conference on Learning Representations · 2020
539
cited
PRECOG: PREdiction Conditioned on Goals in Visual Multi-Agent Settings
IEEE International Conference on Computer Vision · 2019
398
cited
Concrete Problems for Autonomous Vehicle Safety: Advantages of Bayesian Deep Learning
International Joint Conference on Artificial Intelligence · 2017
334
cited
Improving PILCO with Bayesian Neural Network Dynamics Models
2016
271
cited
Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?
International Conference on Machine Learning · 2020
217
cited
Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research
Neural Information Processing Systems · 2023
162
cited
Deep Imitative Models for Flexible Inference, Planning, and Control
International Conference on Learning Representations · 2018
155
cited
Safety Augmented Value Estimation From Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks
IEEE Robotics and Automation Letters · 2019
104
cited
Model-Based Meta-Reinforcement Learning for Flight With Suspended Payloads
IEEE Robotics and Automation Letters · 2020
99
cited
Learned Stochastic Mobility Prediction for Planning with Control Uncertainty on Unstructured Terrain
J. Field Robotics · 2014
40
cited
Robustness to Out-of-Distribution Inputs via Task-Aware Generative Uncertainty
IEEE International Conference on Robotics and Automation · 2018
40
cited
Contingencies from Observations: Tractable Contingency Planning with Learned Behavior Models
IEEE International Conference on Robotics and Automation · 2021
39
cited
Heterogeneous-Agent Trajectory Forecasting Incorporating Class Uncertainty
IEEE/RJS International Conference on Intelligent RObots and Systems · 2021
38
cited
Data-Efficient Reinforcement Learning in Continuous State-Action Gaussian-POMDPs
Neural Information Processing Systems · 2017
36
cited
S2Net: Stochastic Sequential Pointcloud Forecasting
European Conference on Computer Vision · 2022
30
cited
Control-Aware Prediction Objectives for Autonomous Driving
IEEE International Conference on Robotics and Automation · 2022
23
cited
Hierarchical Planning for Self-reconfiguring Robots Using Module Kinematics
International Symposium on Distributed Autonomous Robotic Systems · 2010
23
cited
In-Distribution Barrier Functions: Self-Supervised Policy Filters that Avoid Out-of-Distribution States
Conference on Learning for Dynamics & Control · 2023
23
cited
Outcome-Driven Reinforcement Learning via Variational Inference
Neural Information Processing Systems · 2021
22
cited
Sotabase
Rowan McAllister | Researcher Profile | Sotabase | Sotabase