Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jul 12, 2026

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware
08:13

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware

Published on: December 25, 2017

A Novel DS-MADDPG Algorithm-Based Swarm-to-Swarm Interception Strategy.

He Cai, Yibo Zhang, Youfeng Su

    IEEE Transactions on Neural Networks and Learning Systems
    |July 9, 2026
    PubMed
    Summary

    This study presents a vision-based strategy for uncrewed aerial vehicle (UAV) swarms to intercept target UAVs. A novel dynamic sampling multiagent deep deterministic policy gradient (DS-MADDPG) algorithm enhances target allocation and motion planning for effective interception.

    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

    Spatiotemporal heterogeneity of recurrence and predictors after radical surgery for pancreatic ductal adenocarcinoma: a retrospective observational study.

    Surgical endoscopy·2026
    Same author

    Randomised, triple-blind, placebo-controlled trial of atosiban in women with previous embryo implantation failure and abnormal uterine contractions undergoing single blastocyst-stage embryo transfer: a study protocol.

    BMJ open·2026
    Same author

    Microinjection molded PLA/ZnO-TiO<sub>2</sub> composites with <i>in situ</i> fibrillation: achieving mechanical matching cortical bone and enhanced osteoinduction.

    RSC advances·2026
    Same author

    Learning curve of laparoscopic duodenum-preserving total pancreatic head resection: a single-center dual CUSUM and risk-adjusted CUSUM analysis.

    Surgical endoscopy·2026
    Same author

    A web-based self-assessment tool for root caries in older adults: development, validation, and transformation of the Root-caries Assessment Nomogram (RAN).

    BMC geriatrics·2026
    Same author

    A root-extended overlay design and finite element analysis for permanent molars with a 4-wall defect in adolescents.

    Journal of prosthodontic research·2026

    Area of Science:

    • Robotics
    • Artificial Intelligence
    • Aerospace Engineering

    Background:

    • Swarm robotics presents complex challenges in coordination and control.
    • Uncrewed Aerial Vehicle (UAV) swarms require sophisticated strategies for engagement and interception.
    • Vision-based guidance is crucial for autonomous aerial operations.

    Purpose of the Study:

    • To develop an effective swarm-to-swarm interception strategy for uncrewed aerial vehicles (UAVs).
    • To address the challenge of pure vision-feedback-based interception.
    • To enhance target allocation and motion planning within UAV swarms.

    Main Methods:

    • A hierarchical interception strategy integrating image processing, target allocation, and motion planning.
    • A novel dynamic sampling multiagent deep deterministic policy gradient (DS-MADDPG) algorithm for training the target allocation model.

    Related Experiment Videos

    Last Updated: Jul 12, 2026

    SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware
    08:13

    SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware

    Published on: December 25, 2017

  • Implementation of independent replay buffers, dynamic sampling networks, multidimensional convolution, multihead attention, and a TD3-inspired twin critic architecture.

    • Main Results:

    • The proposed DS-MADDPG algorithm optimizes learning efficiency and captures spatial-temporal relationships.
    • The strategy effectively mitigates overestimation bias in action-value functions.
    • Comprehensive case studies demonstrate the strategy's efficiency and effectiveness compared to existing algorithms.

    Conclusions:

    • The developed vision-based interception strategy is efficient and effective for UAV swarms.
    • The novel DS-MADDPG algorithm significantly improves target allocation performance.
    • This research contributes to advancements in autonomous swarm coordination and interception capabilities.