Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

LASER: Learning Active Sensing for Continuum Field Reconstruction

About

High-fidelity measurements of continuum physical fields are essential for scientific discovery and engineering design but remain challenging under sparse and constrained sensing. Conventional reconstruction methods typically rely on fixed sensor layouts, which cannot adapt to evolving physical states. We propose LASER, a unified, closed-loop framework that formulates active sensing as a Partially Observable Markov Decision Process (POMDP). At its core, LASER employs a continuum field latent world model that captures the underlying physical dynamics and provides intrinsic reward feedback. This enables a reinforcement learning policy to simulate ''what-if'' sensing scenarios within a latent imagination space. By conditioning sensor movements on predicted latent states, LASER navigates toward potentially high-information regions beyond current observations. Our experiments demonstrate that LASER consistently outperforms static and offline-optimized strategies, achieving high-fidelity reconstruction under sparsity across diverse continuum fields.

Huayu Deng, Jinghui Zhong, Xiangming Zhu, Yunbo Wang, Xiaokang Yang• 2026

Related benchmarks

TaskDatasetResultRank
Continuum Field Reconstruction (Rollout)2D Navier-Stokes nu=1e-3
MSE0.096
54
Continuum Field ReconstructionNS ν1e-5 (In-t)
MSE0.017
18
Continuum Field ReconstructionNSν1e-5 Avg
MSE0.59
18
Continuum Field ReconstructionShallow-Water (In-t)
MSE0.042
18
Continuum Field ReconstructionShallow-Water (Out-t)
MSE0.465
18
Continuum Field ReconstructionShallow-Water Avg
MSE0.257
18
Continuum Field Reconstruction (Rollout)2D Navier-Stokes nu=1e-5
MSE1.162
18
Online reconstruction with active sensingSST (test)
MSE0.6932
10
Spatio-temporal forecastingSST (test)
MSE2.6792
8
Continuum Field Reconstruction (Rollout)3D Shallow-Water
In-t MSE0.006
6
Showing 10 of 10 rows

Other info

Follow for update