Calibrated Uncertainty for Informative Path Planning in Aquatic Environmental Monitoring

2026-09-28

AI Summary

This study addresses the issues of miscalibrated uncertainty and inefficient path planning caused by Gaussian process kernel misspecification. We propose a deep ensemble-based informative path planning framework for oil spill monitoring in aquatic environments. Methodologically, deep ensembles replace Gaussian processes to provide well-calibrated uncertainty estimates, which are integrated with Monte Carlo Tree Search (MCTS) to enable multi-step lookahead planning. The model is trained on physics-simulated data. Our analysis reveals an amplification effect of uncertainty calibration errors on planning performance and validates the advantages of multi-step strategies. Experimental results demonstrate that the proposed framework reduces reconstruction error by 83% and achieves an Intersection over Union (IoU) exceeding 0.85. Furthermore, MCTS attains optimal accuracy with minimal computational overhead.

Abstract

Informative Path Planning for scalar field reconstruction uses predictive uncertainty to direct sensing vehicles toward maximally informative locations. Gaussian Processes provide this signal but their stationary isotropic kernels are misspecified for non-homogeneous phenomena such as oil spills, producing miscalibrated estimates that degrade planning. We investigate whether replacing the Gaussian Process with a well-calibrated Deep Ensemble improves path planning outcomes, and whether uncertainty quality interacts with the choice of planning algorithm. Five strategies ($ε$-Greedy, Value Greedy, Uncertainty Greedy, Monte Carlo Tree Search, and Receding Horizon Orienteering) share a common Deep Ensemble backbone trained on physics-based oil spill simulations. On held-out stochastic spill scenarios, the Deep Ensemble reduces normalised reconstruction error by $83\%$ relative to the Gaussian Process baseline. Crucially, well-calibrated uncertainty amplifies the importance of the planning strategy: the performance gap between algorithms is negligible under miscalibrated models but becomes substantial under the ensemble, where multi-step lookahead planners outperform greedy selection by up to $32\%$ in reconstruction error and achieve IoU above $0.85$. Monte Carlo Tree Search is the recommended planner, matching Orienteering in reconstruction quality at an order-of-magnitude lower computational cost.

Problem

• Informative Path Planning
• Uncertainty Calibration
• Aquatic Environmental Monitoring
• Scalar Field Reconstruction
• Deep Ensemble

Innovation

• Informative Path Planning
• Deep Ensemble
• Uncertainty Calibration
• Monte Carlo Tree Search
• Scalar Field Reconstruction