Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper benchmarks Gaussian Processes (GPs), Monte Carlo Dropout, Deep Ensembles, and Evidential Deep Learning (EDL) for reconstructing scalar fields from sparse sensor data collected by autonomous vehicles in aquatic environments. The study evaluates reconstruction accuracy, uncertainty calibration, and inference cost across three sensor models. Results indicate that EDL outperforms other methods, achieving superior accuracy and calibration with lower computational overhead, while GPs struggle with scalability and stationary kernel assumptions.
Evidential Deep Learning emerges as the clear winner for uncertainty-aware scalar field reconstruction on autonomous vehicles, offering the best accuracy, calibration, and speed.
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.