Sotabase

Career

· Founder and Lead Scientist, Emancro Robotics2022–
· Research Intern, Google Inc.2020–2020
· PhD in Computer Science, UC Berkeley2017–2022
· PhD in Computer Science, University of California, Berkeley2017–2022
· Visiting Researcher, UC Berkeley2016–2017
· Master of Science in Robotics Cognition Intelligence, Technical University Munich2014–2016
· Exchange Student, Tongji University2012–2013
· Exchange Student, Tongji University, Shanghai, China2012–2013
· Bachelor of Science in Mechatronics Engineering and Information Technology, Technical University Munich2010–2014
· Founder, Emancro

Publications (22)

BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning
Conference on Robot Learning · 2022
704
cited
Stochastic Adversarial Video Prediction
arXiv.org · 2018
470
cited
Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control
arXiv.org · 2018
433
cited
RoboNet: Large-Scale Multi-Robot Learning
Conference on Robot Learning · 2019
368
cited
Self-Supervised Visual Planning with Temporal Skip Connections
Conference on Robot Learning · 2017
344
cited
Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets
Robotics: Science and Systems · 2021
301
cited
OmniTact: A Multi-Directional High-Resolution Touch Sensor
IEEE International Conference on Robotics and Automation · 2020
142
cited
Manipulation by Feel: Touch-Based Control with Deep Predictive Models
IEEE International Conference on Robotics and Automation · 2019
140
cited
Time-Agnostic Prediction: Predicting Predictable Video Frames
International Conference on Learning Representations · 2018
95
cited
Improvisation through Physical Understanding: Using Novel Objects as Tools with Visual Foresight
Robotics: Science and Systems · 2019
86
cited
Pre-Training for Robots: Offline RL Enables Learning New Tasks in a Handful of Trials
Robotics: Science and Systems · 2022
86
cited
Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors
Neural Information Processing Systems · 2020
81
cited
Model-Based Visual Planning with Self-Supervised Functional Distances
International Conference on Learning Representations · 2020
66
cited
Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning
Conference on Robot Learning · 2018
65
cited
Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials
arXiv.org · 2022
19
cited
Goal-Conditioned Video Prediction
2019
1
cited
Application of Helicopter Air-to-Air Combat Test (AACT) Data to Current LHX Concerns
1985
Learned Tactile Dynamics Candidate actions Sequence Prediction Compute Costs Choose Best Action Model Predictive Control
2019
Nonlinear Model Predictive Control in the Application of Constrained Manipulator Control
2014
Predict futures using video prediction model Training Time Test Time Collect Kinesthetic Demonstrations Autonomous Random Data
Sotabase
Frederik Ebert | Researcher Profile | Sotabase | Sotabase