Uncertainty Estimation for Deep Reconstruction in Actuatic Disaster Scenarios with Autonomous Vehicles
This addresses the need for reliable uncertainty estimation in autonomous vehicles for real-time monitoring, though it is incremental as it compares existing methods rather than introducing a new one.
The paper tackled the problem of reconstructing environmental scalar fields from sparse sensor data in aquatic monitoring scenarios, comparing several uncertainty quantification methods; results showed that Evidential Deep Learning achieved the best accuracy and calibration with the lowest inference cost.
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.