Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Multiple Target Tracking Using a UAV Swarm in Maritime Environments

Andreas Anastasiou, Savvas Papaioannou, Panayiotis Kolios, Christos G. Panayiotou

TL;DR

This paper addresses tracking multiple castaways in maritime environments using a UAV swarm. It formulates a collaborative Model Predictive Control (MPC) problem as a Nonlinear Mixed Integer Program (NMIP) to generate non-myopic trajectories over a planning horizon $K$, aiming to minimize the posterior covariance by reducing $tr(P^{j}_{\tau+k|\tau})$ across targets. A target-clustering module predicts drift-driven groupings, and a distributed fusion scheme via Covariance Intersection along with sequential planning ensures coordinated, collision-free operation; castaway motion uses a modified Stokes drift model. Simulation results from 300 Monte Carlo runs show substantial covariance reduction (e.g., up to ~87% with $N=2$ UAVs), reliable collision avoidance with a minimum inter-agent distance of $d_t=2.5$ m, and accurate tracking with RMSE around $0.18$ m for representative scenarios, indicating strong practical SAR potential.

Abstract

Nowadays, unmanned aerial vehicles (UAVs) are increasingly utilized in search and rescue missions, a trend driven by technological advancements, including enhancements in automation, avionics, and the reduced cost of electronics. In this work, we introduce a collaborative model predictive control (MPC) framework aimed at addressing the joint problem of guidance and state estimation for tracking multiple castaway targets with a fleet of autonomous UAV agents. We assume that each UAV agent is equipped with a camera sensor, which has a limited sensing range and is utilized for receiving noisy observations from multiple moving castaways adrift in maritime conditions. We derive a nonlinear mixed integer programming (NMIP) -based controller that facilitates the guidance of the UAVs by generating non-myopic trajectories within a receding planning horizon. These trajectories are designed to minimize the tracking error across multiple targets by directing the UAV fleet to locations expected to yield targets measurements, thereby minimizing the uncertainty of the estimated target states. Extensive simulation experiments validate the effectiveness of our proposed method in tracking multiple castaways in maritime environments.

Multiple Target Tracking Using a UAV Swarm in Maritime Environments

TL;DR

This paper addresses tracking multiple castaways in maritime environments using a UAV swarm. It formulates a collaborative Model Predictive Control (MPC) problem as a Nonlinear Mixed Integer Program (NMIP) to generate non-myopic trajectories over a planning horizon , aiming to minimize the posterior covariance by reducing across targets. A target-clustering module predicts drift-driven groupings, and a distributed fusion scheme via Covariance Intersection along with sequential planning ensures coordinated, collision-free operation; castaway motion uses a modified Stokes drift model. Simulation results from 300 Monte Carlo runs show substantial covariance reduction (e.g., up to ~87% with UAVs), reliable collision avoidance with a minimum inter-agent distance of m, and accurate tracking with RMSE around m for representative scenarios, indicating strong practical SAR potential.

Abstract

Nowadays, unmanned aerial vehicles (UAVs) are increasingly utilized in search and rescue missions, a trend driven by technological advancements, including enhancements in automation, avionics, and the reduced cost of electronics. In this work, we introduce a collaborative model predictive control (MPC) framework aimed at addressing the joint problem of guidance and state estimation for tracking multiple castaway targets with a fleet of autonomous UAV agents. We assume that each UAV agent is equipped with a camera sensor, which has a limited sensing range and is utilized for receiving noisy observations from multiple moving castaways adrift in maritime conditions. We derive a nonlinear mixed integer programming (NMIP) -based controller that facilitates the guidance of the UAVs by generating non-myopic trajectories within a receding planning horizon. These trajectories are designed to minimize the tracking error across multiple targets by directing the UAV fleet to locations expected to yield targets measurements, thereby minimizing the uncertainty of the estimated target states. Extensive simulation experiments validate the effectiveness of our proposed method in tracking multiple castaways in maritime environments.

Paper Structure

This paper contains 14 sections, 17 equations, 8 figures.

Table of Contents

  1. Introduction
  2. Preliminaries
  3. System Architecture
  4. Agent Dynamics
  5. Sensing Model
  6. Probability of observing a target
  7. Castaway Motion Model
  8. Proposed Approach
  9. Target Clustering And Assignment
  10. Collaborative Model Predictive Control
  11. Simulation Experiments
  12. Simulation Setup
  13. Simulation Results
  14. Conclusions

Figures (8)

  • Figure 1: Scenario illustration of the proposed system.
  • Figure 2: Drift paths of three castaways induced rough sea conditions over a time span of 10 minutes.
  • Figure 3: Flow diagram of the proposed approach showing the flow of exchanged information between agents and the sequence of steps that each agent follows.
  • Figure 4: Average target estimation covariance based on fleet size.
  • Figure 5: Empirical cumulative distribution functions of separation distance between agents given fleet size $N$. Safety distance was set to $2.5$ meters.
  • ...and 3 more figures