Enregistré dans:
Détails bibliographiques
Auteurs principaux: Jordan, Britton, Thompson, Jordan, d'Almeida, Jesse F., Li, Hao, Kumar, Nithesh, Stern, Susheela Sharma, Ferguson, James, Oguz, Ipek, Webster III, Robert J., Brown, Daniel, Kuntz, Alan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2512.11773
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915887838134272
author Jordan, Britton
Thompson, Jordan
d'Almeida, Jesse F.
Li, Hao
Kumar, Nithesh
Stern, Susheela Sharma
Ferguson, James
Oguz, Ipek
Webster III, Robert J.
Brown, Daniel
Kuntz, Alan
author_facet Jordan, Britton
Thompson, Jordan
d'Almeida, Jesse F.
Li, Hao
Kumar, Nithesh
Stern, Susheela Sharma
Ferguson, James
Oguz, Ipek
Webster III, Robert J.
Brown, Daniel
Kuntz, Alan
contents Monocular depth estimation (MDE) provides a useful tool for robotic perception, but its predictions are often uncertain and inaccurate in challenging environments such as surgical scenes where textureless surfaces, specular reflections, and occlusions are common. To address this, we propose ProbeMDE, a cost-aware active sensing framework that combines RGB images with sparse proprioceptive measurements for MDE. Our approach utilizes an ensemble of MDE models to predict dense depth maps conditioned on both RGB images and on a sparse set of known depth measurements obtained via proprioception, where the robot has touched the environment in a known configuration. We quantify predictive uncertainty via the ensemble's variance and measure the gradient of the uncertainty with respect to candidate measurement locations. To prevent mode collapse while selecting maximally informative locations to propriocept (touch), we leverage Stein Variational Gradient Descent (SVGD) over this gradient map. We validate our method in both simulated and physical experiments on central airway obstruction surgical phantoms. Our results demonstrate that our approach outperforms baseline methods across standard depth estimation metrics, achieving higher accuracy while minimizing the number of required proprioceptive measurements. Project page: https://brittonjordan.github.io/probe_mde/
format Preprint
id arxiv_https___arxiv_org_abs_2512_11773
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ProbeMDE: Uncertainty-Guided Active Proprioception for Monocular Depth Estimation in Surgical Robotics
Jordan, Britton
Thompson, Jordan
d'Almeida, Jesse F.
Li, Hao
Kumar, Nithesh
Stern, Susheela Sharma
Ferguson, James
Oguz, Ipek
Webster III, Robert J.
Brown, Daniel
Kuntz, Alan
Robotics
Monocular depth estimation (MDE) provides a useful tool for robotic perception, but its predictions are often uncertain and inaccurate in challenging environments such as surgical scenes where textureless surfaces, specular reflections, and occlusions are common. To address this, we propose ProbeMDE, a cost-aware active sensing framework that combines RGB images with sparse proprioceptive measurements for MDE. Our approach utilizes an ensemble of MDE models to predict dense depth maps conditioned on both RGB images and on a sparse set of known depth measurements obtained via proprioception, where the robot has touched the environment in a known configuration. We quantify predictive uncertainty via the ensemble's variance and measure the gradient of the uncertainty with respect to candidate measurement locations. To prevent mode collapse while selecting maximally informative locations to propriocept (touch), we leverage Stein Variational Gradient Descent (SVGD) over this gradient map. We validate our method in both simulated and physical experiments on central airway obstruction surgical phantoms. Our results demonstrate that our approach outperforms baseline methods across standard depth estimation metrics, achieving higher accuracy while minimizing the number of required proprioceptive measurements. Project page: https://brittonjordan.github.io/probe_mde/
title ProbeMDE: Uncertainty-Guided Active Proprioception for Monocular Depth Estimation in Surgical Robotics
topic Robotics
url https://arxiv.org/abs/2512.11773