Touchsdf: A deepsdf approach for 3d shape reconstruction using vision-based tactile sensing

M Comi, Y Lin, A Church, A Tonioni… - IEEE Robotics and …, 2024 - ieeexplore.ieee.org
Humans rely on their visual and tactile senses to develop a comprehensive 3D
understanding of their physical environment. Recently, there has been a growing interest in …

Scaling gaussian processes with derivative information using variational inference

M Padidar, X Zhu, L Huang… - Advances in Neural …, 2021 - proceedings.neurips.cc
Gaussian processes with derivative information are useful in many settings where derivative
information is available, including numerous Bayesian optimization and regression tasks …

Variational gaussian processes with decoupled conditionals

X Zhu, K Wu, N Maus, J Gardner… - Advances in Neural …, 2023 - proceedings.neurips.cc
Abstract Variational Gaussian processes (GPs) approximate exact GP inference by using a
small set of inducing points to form a sparse approximation of the true posterior, with the …

Exploratory hand: Leveraging safe contact to facilitate manipulation in cluttered spaces

MA Lin, R Thomasson, G Uribe, H Choi… - IEEE Robotics and …, 2021 - ieeexplore.ieee.org
We present a new gripper and exploration approach that uses a finger with very low
reflected inertia for probing and then gras** objects. The finger employs a transparent …

RUMI: Rummaging Using Mutual Information

S Zhong, N Fazeli, D Berenson - arxiv preprint arxiv:2408.10450, 2024 - arxiv.org
This paper presents Rummaging Using Mutual Information (RUMI), a method for online
generation of robot action sequences to gather information about the pose of a known …

Curiosity driven self-supervised tactile exploration of unknown objects

Y Lu, J Wang, V Kumar - arxiv preprint arxiv:2204.00035, 2022 - arxiv.org
Intricate behaviors an organism can exhibit is predicated on its ability to sense and
effectively interpret complexities of its surroundings. Relevant information is often distributed …

[PDF][PDF] Efficient variational Gaussian processes initialization via kernel-based least squares fitting

X Zhu, JR Gardner, D Bindel - NeurIPS Workshop …, 2022 - gp-seminar-series.github.io
Stochastic variational Gaussian processes (SVGP) scale Gaussian process inference to
large datasets through inducing points and stochastic training. However, the training …

Scalable Gaussian Processes and Bayesian Optimization with Application to Hyperparameter Tuning

X Zhu - 2024 - search.proquest.com
This dissertation delves into the advanced realms of Gaussian Processes (GPs) and
Bayesian Optimization (BO), presenting novel methodologies that enhance their …