Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Collaborating Unmanned Aerial Vehicle and Ground Sensors for Urban Signalized Network Traffic Monitoring

Jiarong Yao, Chaopeng Tan, Meng Wang, Wei Ma

TL;DR

This work tackles network-wide traffic state estimation in urban signalized networks using a limited fleet of UAVs in concert with ground sensors. It introduces a unified uncertainty metric, feasible domain size, and an uncertainty-minimization framework that transforms UAV placement into a network-wide optimization problem, solved via an Improved Quantum Genetic Algorithm (IQGA). Key contributions include the first study of collaborating ground sensors with UAVs for network-wide monitoring, the feasible-domain-uncertainty metric, and demonstrated improvements in arrival-rate (up to 7.23%), queue-length (up to 5.02%), and path-flow estimation, along with faster convergence than classic QGA. The approach supports more reliable traffic state estimation for urban management, with practical implications for allocating limited UAV resources and integrating heterogeneous sensors across network and intersection scales.

Abstract

Reliable estimation of network-wide traffic states is essential for urban traffic management. Unmanned Aerial Vehicles (UAVs), with their airborne full-sample continuous trajectory observation, bring new opportunities for traffic state estimation. In this study, we will explore the optimal UAV deployment problem in road networks in conjunction with ground sensors, including connected vehicle (CV) and loop detectors, to achieve more reliable estimation of vehicle path reconstruction as well as movement-based arrival rates and queue lengths. Oriented towards reliable estimation of traffic states, we propose an index, feasible domain size, as the uncertainty measurement, and transform the optimal UAV deployment problem into minimizing the observation uncertainty of network-wide traffic states. Given the large-scale and nonlinear nature of the problem, an improved quantum genetic algorithm (IQGA) that integrates two customized operators is proposed to enhance neighbor searching and solution refinement, thereby improving the observability of UAV pairs. Evaluation was conducted on an empirical network with 18 intersections. Results demonstrated that a UAV fleet size of 7 is sufficient for traffic monitoring, with more than 60\% of network-wide observation uncertainty reduced. Through horizontal comparison with three baselines, the optimal UAV location scheme obtained by the proposed method can reach an improvement of up to 7.23\% and 5.02\% in the estimation accuracy of arrival rate and queue length, respectively. The proposed IQGA is also shown to be faster in solution convergence than the classic QGA by about 9.22\% with better exploration ability in optimum searching.

Collaborating Unmanned Aerial Vehicle and Ground Sensors for Urban Signalized Network Traffic Monitoring

TL;DR

This work tackles network-wide traffic state estimation in urban signalized networks using a limited fleet of UAVs in concert with ground sensors. It introduces a unified uncertainty metric, feasible domain size, and an uncertainty-minimization framework that transforms UAV placement into a network-wide optimization problem, solved via an Improved Quantum Genetic Algorithm (IQGA). Key contributions include the first study of collaborating ground sensors with UAVs for network-wide monitoring, the feasible-domain-uncertainty metric, and demonstrated improvements in arrival-rate (up to 7.23%), queue-length (up to 5.02%), and path-flow estimation, along with faster convergence than classic QGA. The approach supports more reliable traffic state estimation for urban management, with practical implications for allocating limited UAV resources and integrating heterogeneous sensors across network and intersection scales.

Abstract

Reliable estimation of network-wide traffic states is essential for urban traffic management. Unmanned Aerial Vehicles (UAVs), with their airborne full-sample continuous trajectory observation, bring new opportunities for traffic state estimation. In this study, we will explore the optimal UAV deployment problem in road networks in conjunction with ground sensors, including connected vehicle (CV) and loop detectors, to achieve more reliable estimation of vehicle path reconstruction as well as movement-based arrival rates and queue lengths. Oriented towards reliable estimation of traffic states, we propose an index, feasible domain size, as the uncertainty measurement, and transform the optimal UAV deployment problem into minimizing the observation uncertainty of network-wide traffic states. Given the large-scale and nonlinear nature of the problem, an improved quantum genetic algorithm (IQGA) that integrates two customized operators is proposed to enhance neighbor searching and solution refinement, thereby improving the observability of UAV pairs. Evaluation was conducted on an empirical network with 18 intersections. Results demonstrated that a UAV fleet size of 7 is sufficient for traffic monitoring, with more than 60\% of network-wide observation uncertainty reduced. Through horizontal comparison with three baselines, the optimal UAV location scheme obtained by the proposed method can reach an improvement of up to 7.23\% and 5.02\% in the estimation accuracy of arrival rate and queue length, respectively. The proposed IQGA is also shown to be faster in solution convergence than the classic QGA by about 9.22\% with better exploration ability in optimum searching.

Paper Structure

This paper contains 27 sections, 21 equations, 16 figures, 2 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Literature review
  3. Detector location optimization
  4. UAV-based traffic monitoring
  5. Preliminaries
  6. Assumptions and definitions
  7. Problem statement
  8. Methodology
  9. Location optimization model
  10. Uncertainty of path reconstruction
  11. Uncertainty of traffic movement demand
  12. Traffic movement demand uncertainty modeling given UAV deployment
  13. Traffic movement demand uncertainty formulation
  14. Uncertainty of queue length
  15. Queue uncertainty modeling given UAV deployment
  16. ...and 12 more sections

Figures (16)

  • Figure 1: A sketch of the research scenario.
  • Figure 2: Feasible area of vehicle arrivals for Case 1-3.
  • Figure 3: Feasible area of vehicle arrivals for Case 4.
  • Figure 4: Feasible area of queue length for Case 1-3.
  • Figure 5: Uncertain area of queue length for Case 4.
  • ...and 11 more figures