ProbeMDE: Uncertainty-Guided Active Proprioception for Monocular Depth Estimation in Surgical Robotics

2025-12-12

AI Summary

Monocular depth estimation (MDE) in surgical robotics suffers from high uncertainty and low accuracy under challenging conditions—including textureless regions, specular reflections, and occlusions. Method: This paper proposes an active perception framework that fuses RGB imagery with sparse tactile ranging. It introduces, for the first time, an uncertainty quantification mechanism based on ensemble model variance; employs Stein variational gradient descent (SVGD) to optimize tactile contact selection—thereby avoiding mode collapse; and designs an uncertainty-gradient-driven, information-maximizing active probing strategy. Results: Evaluated on both airway obstruction surgery simulation and a physical robotic platform, the method significantly improves depth estimation accuracy over state-of-the-art baselines while minimizing the required number of tactile contacts. It achieves robust, low-invasive, proprioceptively enhanced depth estimation—demonstrating substantial improvements in reliability and clinical practicality.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

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.

Problem

• Improves monocular depth estimation accuracy in surgical scenes
• Reduces uncertainty in depth predictions via active proprioceptive sensing
• Minimizes required touch measurements while enhancing robotic perception

Innovation

• Combines RGB images with sparse proprioceptive measurements
• Uses ensemble models to predict depth with uncertainty quantification
• Applies SVGD to select optimal touch locations for accuracy