Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jan 10, 2026

An Emerging Target Paradigm to Evoke Fast Visuomotor Responses on Human Upper Limb Muscles

An Emerging Target Paradigm to Evoke Fast Visuomotor Responses on Human Upper Limb Muscles

Published on: August 25, 2020

Cognitive embodied learning for anomaly active target tracking.

Qihui Wu¹, Jiahao Li¹, Fuhui Zhou²

¹College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, P. R. China.

Communications Engineering

|November 27, 2025

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Multiomics Integration Reveals AFB1 Causes Liver Damage Involving the Gut-Microbiota-Lipid Metabolism Axis in Piglet.

Journal of agricultural and food chemistry·2026

Same author

Effects of electrical stimulation on lower limb function after anterior cruciate ligament reconstruction: a systematic review and network meta-analysis.

BMC musculoskeletal disorders·2026

Same author

Mechanisms of Traditional Chinese Medicine-Derived Alkaloids in Colorectal Cancer Therapy: Molecular Targets, Preclinical Evidence, and Translational Prospects.

Drug design, development and therapy·2026

Same author

Clinical value and cost-effectiveness analysis of conditionally approved anticancer drugs in China from 2015 to 2023.

Translational cancer research·2026

Same author

Genetic variability and intra-genotype recombination of DuCV from ducks and geese in central and north China.

Frontiers in veterinary science·2026

Same author

RETRACTED: Enhancing wound recovery in chemotherapy-induced leukopenia for malignant tumours: A meta-analysis of acupuncture treatment efficacy.

International wound journal·2026

Same journal

Enhanced magnetic moment discrimination for multiplex nanoparticle quantification via dual-frequency nonlinearity probing.

Communications engineering·2026

Same journal

Ultrahigh-speed micromachining of sapphire by enhancing laser absorption.

Communications engineering·2026

Same journal

Industry-Academia Interface: Exploring the growth of Additive Manufacturing as an industry with Laura Del Río Fernández.

Communications engineering·2026

Same journal

Operating smart grids by customizing large model agents.

Communications engineering·2026

Same journal

Photovoltaics for space applications.

Communications engineering·2026

Same journal

EdgeVolution: democratizing multi-objective neural architecture search and end-to-end deployment on microcontrollers.

Communications engineering·2026

See all related articles

Cognitive Embodied Learning (CEL) enhances active object tracking (AOT) by dynamically switching between normal tracking and anomaly handling. This novel method significantly improves tracking success rates and efficiency in complex environments.

Area of Science:

Computer Vision
Artificial Intelligence
Robotics

Background:

Active object tracking (AOT) faces challenges in complex scenarios due to limitations in current deep learning and reinforcement learning frameworks, including high computational costs and poor generalization.
Embodied intelligence (EI) shows promise for learning through physical interaction but struggles with severe anomalies in tracking tasks.
Existing methods lack robustness and adaptability for real-world AOT applications with unpredictable environmental changes.

Purpose of the Study:

To propose a novel embodied learning method, Cognitive Embodied Learning (CEL), to address the limitations of existing AOT frameworks, particularly in handling complex scenarios and anomalies.
To develop a system capable of dynamically switching between normal tracking and anomaly handling modes for improved AOT performance.
To introduce a categorical objective function to mitigate issues arising from function non-measurability and data confusion during severe anomalies.

More Related Videos

Eye Tracking During A Complex Aviation Task For Insights Into Information Processing

Eye Tracking During A Complex Aviation Task For Insights Into Information Processing

Published on: April 4, 2025

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

Related Experiment Videos

Last Updated: Jan 10, 2026

An Emerging Target Paradigm to Evoke Fast Visuomotor Responses on Human Upper Limb Muscles

An Emerging Target Paradigm to Evoke Fast Visuomotor Responses on Human Upper Limb Muscles

Published on: August 25, 2020

Eye Tracking During A Complex Aviation Task For Insights Into Information Processing

Eye Tracking During A Complex Aviation Task For Insights Into Information Processing

Published on: April 4, 2025

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

Main Methods:

Developed the Cognitive Embodied Learning (CEL) framework, inspired by the human brain's dual decision-making system.
Integrated specialized modules: anomaly cognition, rule reasoning, and anomaly elimination, enabling dynamic mode switching.
Introduced a categorical objective function to handle data confusion and non-measurability in anomalous situations.

Main Results:

Extensive experiments using unmanned aerial vehicle (UAV) anomaly active target tracking in simulated and real-world scenarios demonstrated CEL's superior performance.
CEL achieved a 361.4% increase in success rate compared to state-of-the-art methods.
The method showed a 54.4% improvement in task completion efficiency, highlighting its effectiveness in challenging environments.

Conclusions:

Cognitive Embodied Learning (CEL) offers a robust and intelligent solution for active object tracking in complex and anomalous environments.
The dynamic switching capability and specialized modules significantly enhance tracking accuracy and efficiency.
CEL has the potential to advance AOT research and enable more reliable tracking systems for challenging applications.