eduzhai > Applied Sciences > Engineering >

Multi-Swarm Herding Protecting against Adversarial Swarms

  • king
  • (0) Download
  • 20210505
  • Save

... pages left unread,continue reading

Document pages: 8 pages

Abstract: This paper studies a defense approach against one or more swarms ofadversarial agents. In our earlier work, we employ a closed formation(`StringNet ) of defending agents (defenders) around a swarm of adversarialagents (attackers) to confine their motion within given bounds, and guide themto a safe area. The control design relies on the assumption that theadversarial agents remain close enough to each other, i.e., within a prescribedconnectivity region. To handle situations when the attackers no longer staywithin such a connectivity region, but rather split into smaller swarms(clusters) to maximize the chance or impact of attack, this paper proposes anapproach to learn the attacking sub-swarms and reassign defenders towards theattackers. We use a `Density-based Spatial Clustering of Application with Noise(DBSCAN) algorithm to identify the spatially distributed swarms of theattackers. Then, the defenders are assigned to each identified swarm ofattackers by solving a constrained generalized assignment problem. Simulationsare provided to demonstrate the effectiveness of the approach.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...