Uncertainty Estimation for Deep Reconstruction in Actuatic Disaster Scenarios with Autonomous Vehicles

2026-04-07

AI Summary

This study addresses the challenge of scalar field reconstruction and uncertainty quantification from sparse vehicle-mounted observations in underwater disaster scenarios. The authors systematically evaluate the performance of Gaussian processes, Monte Carlo Dropout, deep ensembles, and evidential deep learning (EDL) across three representative perception models. Experimental results demonstrate that EDL consistently achieves superior reconstruction accuracy and better-calibrated uncertainty estimates under diverse real-world sensor configurations, while also offering the highest inference efficiency. In contrast, Gaussian processes, constrained by their stationary kernel assumption, struggle to scale effectively to high-density observation settings. To the best of the authors’ knowledge, this work presents the first comprehensive comparison of multiple uncertainty quantification methods under realistic underwater perception conditions, establishing EDL’s combined advantages in accuracy, reliability, and computational efficiency.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Uncertainty Representations
• Intelligent Robots: State Estimation

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Accurate reconstruction of environmental scalar fields from sparse onboard observations is essential for autonomous vehicles engaged in aquatic monitoring. Beyond point estimates, principled uncertainty quantification is critical for active sensing strategies such as Informative Path Planning, where epistemic uncertainty drives data collection decisions. This paper compares Gaussian Processes, Monte Carlo Dropout, Deep Ensembles, and Evidential Deep Learning for simultaneous scalar field reconstruction and uncertainty decomposition under three perceptual models representative of real sensor modalities. Results show that Evidential Deep Learning achieves the best reconstruction accuracy and uncertainty calibration across all sensor configurations at the lowest inference cost, while Gaussian Processes are fundamentally limited by their stationary kernel assumption and become intractable as observation density grows. These findings support Evidential Deep Learning as the preferred method for uncertainty-aware field reconstruction in real-time autonomous vehicle deployments.

Problem

• Uncertainty Estimation
• Deep Reconstruction
• Autonomous Vehicles
• Scalar Field
• Aquatic Disaster Scenarios

Innovation

• Evidential Deep Learning
• Uncertainty Quantification
• Scalar Field Reconstruction
• Autonomous Vehicles
• Active Sensing