Active Sensing

Ask about this topic

Overview

Active sensing studies how robots and other agents can select observations or sensing actions instead of relying on fixed, continuous measurements. Common approaches use Bayesian information gain, uncertainty-guided view selection, partially observable decision processes, and reinforcement learning to plan camera, tactile, acoustic, or other sensor actions. Applications range from robotic exploration and manipulation to medical imaging, environmental monitoring, and scientific measurement, often under limits on energy, time, or interaction. A central challenge is that reducing uncertainty does not always improve task success: methods must account for feasibility, latency, model error, and risk, and evaluate both evidence gained and downstream outcomes.

Latest papers

CardsList

61 papers6 papers in the last four weeks, down 25% on the four weeks before. 0.0% of all new papers.

Oct 6, 2025

CLEAR-IR: Clarity-Enhanced Active Reconstruction of Infrared Imagery

This paper presents CLEAR-IR (Clarity Enhanced Active Reconstruction of Infrared Imagery), a novel framework for enabling robust robotic perception in dark environments using active infrared (IR) sensing. IR streams are less susceptible to noise than RGB in low light conditions but are dominated by structured light emitter patterns that hinder high level tasks such as object detection, tracking, and localisation. CLEAR-IR addresses this by reconstructing clean, RGB styled images from emitter populated IR inputs using a dual stream architecture inspired by DeepMAO, enabling standard RGB trained vision pipelines to operate without visible light. Evaluation across object detection, ArUco marker detection, and visual SLAM demonstrates that CLEAR-IR produces reliable perception in conditions ranging from well lit to completely dark, where passive RGB based enhancement methods fail entirely due to the physical absence of sensor signal.

Nathan Shankar, Marton Gonczy, Hujun Yin +1

The authors are with the the Mechanical, Aerospace and Civil Engineering and the Electrical and Electronics Departments at the University of Manchester, Manchester, United Kingdom, M13 9PL.

Image ReconstructionRobotic PerceptionActive Sensing
AskPDF