Scholar
Todor Davchev
Google Scholar ID: h_q7XhoAAAAJ
Research Scientist, Google DeepMind
Citations & Impact
Citations
2,391
H-index
12
i10-index
12
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Paper 'Residual Learning from Demonstration' accepted at RA:L and ICRA 2022; 'Hindsight Goal selection for Long-horizon Dexterous Manipulation' accepted at ICLR 2022; organized workshops on Learning-To-Learn for Robotics at ICRA 2021 and ICLR 2021; 'Model-Based Inverse Reinforcement Learning from Visual Demonstration' accepted at CoRL 2020.
Research Experience
- Currently a Research Scientist at DeepMind working on Robot Learning. He completed two Google X AI residencies (project Intrinsic) and a research scientist internship with DeepMind.
Education
- PhD student in Robot Learning at the University of Edinburgh, supervised by Prof. S. Schaal and F. Meier. He was part of the Robust Autonomy and Decisions (RAD) group.
Background
- Research interests lie at the intersection of robotics and machine learning. During his PhD, he focused on improving the sample efficiency and robustness of learned models through utilizing inductive biases in the context of robotics applications. He has a particular interest in fast contact-rich skill acquisitions, such as peg, gear, and plug insertions. He also studied ways to improve 2D trajectory generation in crowded and collaborative settings and extracting representations that are task-specific and robust to perturbations.
Miscellany
- Personal interests not specifically detailed.
Co-authors