Active Perception

Ask about this topic

Overview

Active perception studies how an agent can improve what it knows by moving a camera or robot, selecting video frames or image regions, or probing an object or person. Common approaches use information gain and belief models, next-best-view planning, learned policies, and vision-language agents that gather evidence in multiple steps; maps and memory help combine observations over time. These methods support tasks such as robot navigation and manipulation, 3D mapping, and visual question answering, where a poorly chosen viewpoint or missing detail can lead to errors. Benchmarks such as ESI-Bench and ActiveArena show that active observation can help, but agents still struggle with reliable memory, long-horizon tasks, transfer to new settings, and balancing information gathering against time, energy, and safety.

Latest papers

CardsList

107 papers11 papers in the last four weeks, down 50% on the four weeks before. 0.1% of all new papers.

  1. EVA: Bridging Performance and Human Alignment in Hard-Attention Vision Models for Image Classification

    Mar 28, 2026Pengcheng Pan, Yonekura Shogo, Kuniyoshi YasuoScanpath PredictionActive Vision

    The University of Tokyo

  2. PiCSRL: Physics-Informed Contextual Spectral Reinforcement Learning

    Mar 26, 2026Mitra Nasr Azadani, Syed Usama Imtiaz, Nasrin AlamdariContextual RLAdaptive Sensing

    Department of Civil and Environmental Engineering Florida State University, Tallahassee, FL, USA

  3. See, Remember, Explore: A Benchmark and Baselines for Streaming Spatial Reasoning

    Mar 25, 2026Yuxi Wei, Wei Huang, Qirui Chen +2Spatial Reasoning BenchmarksVisual Spatial Reasoning

    The University of Hong Kong · Shanghai Jiao Tong University · Yinwang Intelligent Technology Co. Ltd.

  4. Active Robotic Perception for Disease Detection and Mapping in Apple Trees

    Mar 24, 2026Hayden Feddock, Francisco Yandun, Srđan Aćimović +1Robotic InspectionActive Perception

    H. Feddock, F. Yandun, and A. Silwal are with the Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213, USA · S. Aćimović is with the Department of Plant Pathology, Virginia Polytechnic Institute and State University, Blacksburg, VA, USA

  5. CanViT: Toward Active-Vision Foundation Models

    Mar 23, 2026Yohaï-Eliel Berreby, Sabrina Du, Audrey Durand +1Active VisionActive Perception

    McGill University · Mila - Quebec AI Institute · Université Laval

  6. IGV-RRT: Prior-Real-Time Observation Fusion for Active Object Search in Changing Environments

    Mar 23, 2026Wei Zhang, Ping Gong, Yujie Wang +7Robot NavigationObject-Goal Navigation

    The School of Control Science and Engineering, Shandong University · Department of Data and Systems Engineering, HKU

  7. ADAPT: Adaptive Dual-projection Architecture for Perceptive Traversal

    Mar 17, 2026Shuo Shao, Tianchen Huang, Wei Gao +1Humanoid Robot LocomotionTerrain-Aware Robot Locomotion

    Department of Automation, University of Science and Technology of China, Anhui 230026, China. · Institute of Humanoid Robots, Department of Precision Machinery and Precision Instrumentation, University of Science and Technology of China, Hefei, Anhui 230026, China.

  8. OA-NBV: Occlusion-Aware Next-Best-View Planning for Human-Centered Active Perception on Mobile Robots

    Mar 10, 2026Boxun Hu, Chang Chang, Jiawei Ge +4Active PerceptionNext-Best-View Planning

    Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD 21218, USA · Department of Mechanical Engineering, Johns Hopkins University, Baltimore, MD 21218, USA · Laboratory for Computational Sensing and Robotics, Johns Hopkins University, Baltimore, MD 21218, USA +1

  9. A Saccade-inspired Approach to Image Classification using Vision Transformer Attention Maps

    Mar 10, 2026Matthis Dallain, Laurent Rodriguez, Laurent Udo Perrinet +1Active VisionFoveated Vision

    Institut de Neurosciences de la Timone, Aix-Marseille Université, CNRS, Marseille, 13005, France · Laboratoire d’Électronique, Antennes et Télécommunications, Université Côte d’Azur, CNRS, Sophia Antipolis, 06903, France

  10. Telogenesis: Goal Is All U Need

    Mar 10, 2026Zhuoran Deng, Yizhi Zhang, Ziyi Zhang +1Uncertainty-Aware ExplorationAttention Mechanisms

    Independent Research

  11. Active View Selection with Perturbed Gaussian Ensemble for Tomographic Reconstruction

    Mar 6, 2026Yulun Wu, Ruyi Zha, Wei Cao +33D Gaussian SplattingActive Perception

    University of Illinois Urbana-Champaign · Australian National University · Johns Hopkins University

  12. Adaptive Sensing of Continuous Physical Systems for Machine Learning

    Mar 4, 2026Felix Köster, Atsushi UchidaAdaptive SensingActive Perception

    Department of Information and Computer Sciences, Saitama University, 255 Shimo-Okubo, Sakura-ku, Saitama City, Saitama, 338–8570, Japan

  13. I-Perceive: A Foundation Model for Vision-Language Active Perception

    Feb 28, 2026Yongxi Huang, Zhuohang Wang, Wenjing Tang +33D Scene UnderstandingRobot Foundation Models

    Shanghai Jiao Tong University · Shanghai Innovation Institute · Beihang University

  14. See, Act, Adapt: Active Perception for Unsupervised Cross-Domain Visual Adaptation via Personalized VLM-Guided Agent

    Feb 27, 2026Tianci Tang, Tielong Cai, Hongwei Wang +1Active PerceptionUnsupervised Domain Adaptation

    Zhejiang University, Hangzhou, China.

  15. InCoM: Intent-Driven Perception and Structured Coordination for Mobile Manipulation

    Feb 26, 2026Jiahao Liu, Cui Wenbo, Zhongpu Xia +3Active PerceptionMobile Manipulation

    SKL-MAIS, Institute of Automation, Chinese Academy of Sciences · School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences · Anyverse Dynamics

  16. Active perception and disentangled representations allow continual, episodic zero and few-shot learning

    Feb 22, 2026David Rawlinson, Gideon KowadloContinual LearningFew-Shot Learning

    Cerenaut AI Melbourne Australia

  17. Multimodal Belief-Space Covariance Steering with Active Probing and Influence for Interactive Driving

    Feb 16, 2026Devodita Chakravarty, John Dolan, Yiwei LyuRisk-Sensitive PlanningAutonomous Driving Planning

    Department of Mechanical Engineering, Indian Institute of Technology Kharagpur, India · Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA · Department of Computer Science and Engineering, Texas A&M University, College Station, TX, USA