B
Brent Yi
Researcher at University of California, Berkeley
Publications - 10
Citations - 158
Brent Yi is an academic researcher from University of California, Berkeley. The author has contributed to research in topics: Computer science & Differentiable function. The author has an hindex of 3, co-authored 6 publications receiving 41 citations. Previous affiliations of Brent Yi include Stanford University.
Papers
More filters
Proceedings ArticleDOI
Quasi-Direct Drive for Low-Cost Compliant Robotic Manipulation
David V. Gealy,Stephen McKinley,Brent Yi,Philipp Wu,Phillip R. Downey,Greg Balke,Allan Zhao,Menglong Guo,Rachel Thomasson,Anthony Sinclair,Peter Cuellar,Zoe McCarthy,Pieter Abbeel +12 more
TL;DR: This work proposes Quasi-Direct Drive actuation as a capable paradigm for robotic force-controlled manipulation in human environments at low-cost and demonstrates a Virtual Reality based interface that can be used as a method for telepresence and collecting robot training demonstrations.
Posted ContentDOI
Nerfstudio: A Modular Framework for Neural Radiance Field Development
Matthew Tancik,Ethan Weber,Evonne Ng,Ruilong Li,Brent Yi,Justin Kerr,Terrance Wang,Alexander Kristoffersen,Jake Austin,Kamyar Salahi,Abhik Ahuja,David McAllister,Angjoo Kanazawa +12 more
TL;DR: Nerfstudio as discussed by the authors is a PyTorch-based framework for implementing NeRF-based methods, which makes it easy for researchers and practitioners to incorporate NeRF into their projects.
Posted Content
Multimodal Sensor Fusion with Differentiable Filters
TL;DR: In extensive evaluations, it is found that differentiable filters that leverage crossmodal sensor information reach comparable accuracies to unstructured LSTM models, while presenting interpretability benefits that may be important for safety-critical systems.
Proceedings ArticleDOI
Multimodal Sensor Fusion with Differentiable Filters
TL;DR: Differentiable filters as discussed by the authors leverage multimodal information with recursive Bayesian filters to improve performance and robustness of state estimation, as recursive filters can combine different modalities according to their uncertainties.
Posted Content
Quasi-Direct Drive for Low-Cost Compliant Robotic Manipulation
David V. Gealy,Stephen McKinley,Brent Yi,Philipp Wu,Phillip R. Downey,Greg Balke,Allan Zhao,Menglong Guo,Rachel Thomasson,Anthony Sinclair,Peter Cuellar,Zoe McCarthy,Pieter Abbeel +12 more
TL;DR: The QuasiDirect Drive actuation (QD) as discussed by the authors is a capable paradigm for robotic force-controlled manipulation in human environments at low-cost and can be used for telepresence and collecting robot training demonstrations.