Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Cooperative Multi-Agent Probabilistic Framework for Search and Track Missions

Savvas Papaioannou, Panayiotis Kolios, Theocharis Theocharides, Christos G. Panayiotou, Marios M. Polycarpou

TL;DR

A robust and scalable cooperative multiagent searching and tracking (SAT) framework is proposed and decentralized cooperative look-ahead strategies for efficient SAT of an unknown number of targets inside a bounded surveillance area are developed.

Abstract

In this work a robust and scalable cooperative multi-agent searching and tracking framework is proposed. Specifically, we study the problem of cooperative searching and tracking of multiple moving targets by a group of autonomous mobile agents with limited sensing capabilities. We assume that the actual number of targets present is not known a priori and that target births/deaths can occur anywhere inside the surveillance region thus efficient search strategies are required to detect and track as many targets as possible. To address the aforementioned challenges we recursively compute and propagate in time the searching-and-tracking (SAT) density. Using the SAT-density, we then develop decentralized cooperative look-ahead strategies for efficient searching and tracking of an unknown number of targets inside a bounded surveillance area.

A Cooperative Multi-Agent Probabilistic Framework for Search and Track Missions

TL;DR

A robust and scalable cooperative multiagent searching and tracking (SAT) framework is proposed and decentralized cooperative look-ahead strategies for efficient SAT of an unknown number of targets inside a bounded surveillance area are developed.

Abstract

In this work a robust and scalable cooperative multi-agent searching and tracking framework is proposed. Specifically, we study the problem of cooperative searching and tracking of multiple moving targets by a group of autonomous mobile agents with limited sensing capabilities. We assume that the actual number of targets present is not known a priori and that target births/deaths can occur anywhere inside the surveillance region thus efficient search strategies are required to detect and track as many targets as possible. To address the aforementioned challenges we recursively compute and propagate in time the searching-and-tracking (SAT) density. Using the SAT-density, we then develop decentralized cooperative look-ahead strategies for efficient searching and tracking of an unknown number of targets inside a bounded surveillance area.
Paper Structure (20 sections, 11 equations, 5 figures, 1 algorithm)

This paper contains 20 sections, 11 equations, 5 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Background
  4. Multi-Target Tracking
  5. Random Finite sets
  6. Bernoulli RFS
  7. Poisson RFS
  8. System Model
  9. Single Target Dynamics and Measurement Model
  10. Agent Dynamics
  11. Single Agent Sensing Model
  12. Multi-object dynamics and measurement models
  13. Proposed Approach
  14. Searching-and-Tracking Density
  15. Multi-agent Searching
  16. ...and 5 more sections

Figures (5)

  • Figure 1: The figure shows the performance of the cooperative multi-agent path-planning and searching technique proposed in this work versus a random search scheme.
  • Figure 2: The figure illustrates the impact of communication range on the performance of the cooperative multi-agent searching. (a) Communication range $C_R=10$m, (b) Communication range $C_R=50$m.
  • Figure 3: The figure illustrates the search-and-track performance of the proposed system by means of the OSPA error for two configurations of the communication range: (a) $C_R=10$m, (b) $C_R=50$m.
  • Figure 4: The figure shows the percentage of the searched area for the tasks of cooperative searching versus cooperative search-and-track for the case of 2, 3, 4 and 5 agents.
  • Figure 5: The figure shows a) the average ratio of target tracking time to target lifetime as a function of the number of agents and communication range b) the performance gain from the use of tracking overlap detection and resolution.