Periodic Reporting for period 1 - URANUS (Real-Time Urban Mobility Management via Intelligent UAV-based Sensing)
Berichtszeitraum: 2023-07-01 bis 2025-12-31
The ever-increasing urbanization overcrowds cities with vehicles, leading to congestion and accidents. Inefficient management of Urban Mobility (UM) causes long travel times, increased travel costs, degraded quality of life, high greenhouse gas emissions and huge waste of fossil-fuel energy. Despite numerous research efforts and deployed technological solutions to address congestion, the problem persists. One of the main reasons is attributed to the poor quality of traffic data due to inadequate sensing of the urban network.
Unmanned Aerial Vehicles (UAVs) have emerged as vision-based sensing technologies with strong potential for UM monitoring. UAVs can fly across areas, collecting high-quality spatiotemporal data. UAVs also have multi-sensing capabilities, simultaneously measuring multiple parameters related to vehicles, junctions, and pedestrians. They are non-invasive, economically viable, fast to deploy, and highly reliable.
The URANUS project proposes a novel concept of intelligent, coordinated, and dynamic UAV-based sensing for real-time UM management. The idea is to dynamically and strategically plan the operation of a swarm of autonomous UAVs, which continuously fly above an urban network to collect and communicate diverse traffic data for real-time UM management. In this context, the envisioned UAV-based sensing paradigm will be utilized to achieve a step-change improvement in UM management in terms of monitoring and control.
Towards this direction, the following objectives have been set:
- Objective 1: Develop real-time algorithms for vehicular and pedestrian monitoring in urban networks.
- Objective 2: Develop novel model-based and data-driven real-time UM control methodologies with and without uncertainty considerations.
- Objective 3: Design the URANUS system architecture and UAV-fleet size and develop multi-UAV operational planning algorithms for intelligent spatiotemporal sampling.
- Objective 4: Investigate the co-optimization of UAV operational planning and UM control.
- Objective 5: Built an open-source, calibrated, UM micro-simulation platform for intelligent UAV-based sensing.
- Objective 6: Evaluate the developed methodologies in calibrated microsimulation environments and small-scale real-life experiments.
In this respect, the URANUS project is organized in four interconnected research pillars, each contributing towards achieving its objectives:
- Pillar 1: Urban Mobility Monitoring – Objective 1.
- Pillar 2: Urban Mobility Control – Objective 2.
- Pillar 3: UAV Operational Planning – Objectives 3 and 4.
- Pillar 4: Integration, Validation and Evaluation – Objectives 5 and 6.
Unmanned Aerial Vehicles (UAVs) have emerged as vision-based sensing technologies with strong potential for UM monitoring. UAVs can fly across areas, collecting high-quality spatiotemporal data. UAVs also have multi-sensing capabilities, simultaneously measuring multiple parameters related to vehicles, junctions, and pedestrians. They are non-invasive, economically viable, fast to deploy, and highly reliable.
The URANUS project proposes a novel concept of intelligent, coordinated, and dynamic UAV-based sensing for real-time UM management. The idea is to dynamically and strategically plan the operation of a swarm of autonomous UAVs, which continuously fly above an urban network to collect and communicate diverse traffic data for real-time UM management. In this context, the envisioned UAV-based sensing paradigm will be utilized to achieve a step-change improvement in UM management in terms of monitoring and control.
Towards this direction, the following objectives have been set:
- Objective 1: Develop real-time algorithms for vehicular and pedestrian monitoring in urban networks.
- Objective 2: Develop novel model-based and data-driven real-time UM control methodologies with and without uncertainty considerations.
- Objective 3: Design the URANUS system architecture and UAV-fleet size and develop multi-UAV operational planning algorithms for intelligent spatiotemporal sampling.
- Objective 4: Investigate the co-optimization of UAV operational planning and UM control.
- Objective 5: Built an open-source, calibrated, UM micro-simulation platform for intelligent UAV-based sensing.
- Objective 6: Evaluate the developed methodologies in calibrated microsimulation environments and small-scale real-life experiments.
In this respect, the URANUS project is organized in four interconnected research pillars, each contributing towards achieving its objectives:
- Pillar 1: Urban Mobility Monitoring – Objective 1.
- Pillar 2: Urban Mobility Control – Objective 2.
- Pillar 3: UAV Operational Planning – Objectives 3 and 4.
- Pillar 4: Integration, Validation and Evaluation – Objectives 5 and 6.
The main achievements in each pillar during the first two years of URANUS are summarized below.
In Pillar 1, we proposed a novel methodology, based on Bayesian Statistics, to predict traffic patterns in areas and times where direct measurements are not available. In addition, we proposed algorithms that reveal urban traffic demand patterns. To support this, we developed a model-based origin-destination (OD) estimation framework that integrates a path-based traffic model within an optimization-based formulation, effectively reconciling observed link-level data with modelled traffic flows. To address data quality challenges from sensor faults, we developed a fault-tolerant algorithm that detects, isolates, and corrects faulty data during OD estimation. Finally, we developed custom, real-time optimization and machine learning solutions for fine-grained traffic state estimation.
In Pillar 2, we developed several model-based traffic control schemes from an optimization and control-theoretic view. The established approaches tackled the challenge of improving UM performance from multiple angles by developing better and faster solution algorithms, analyzing the stability and optimality properties of the network, optimizing multiple objectives, considering mixed traffic (both human-driven and autonomous vehicles), dealing efficiently with uncertainty, and securing the road networks against adversaries. Moreover, we devised UM control strategies that rely solely on traffic data. The developed strategies explicitly (by selecting when each vehicle should depart and what route to take) or implicitly (through pricing) control traffic demand, aiming to eliminate congestion.
In Pillar 3, we developed novel UAV placement and control methodologies to improve UM performance. Specifically, we designed and solved multi-objective optimization problems that select the locations of sensors to maximize traffic flow coverage and maintain minimum distances between sensor locations for fixed sensor locations (e.g. stationary UAVs). In addition, we proposed an online, uncertainty-driven UAV trajectory planning methodology inspired by statistical learning theory, enabling UAVs to select their future sensing locations in real-time.
In Pillar 4, we established a comprehensive framework for generating and analyzing real-life UM datasets. Towards this direction, our work focused on: (a) establishing a regulatory and operational framework for multi-UAV missions in urban settings, (b) developing Computer Vision algorithms for vehicle detection, re-identification, trajectory mapping, and speed estimation, and (c) building the software tool “UAVTrafficPy” for extracting and visualizing traffic data. Moreover, we established an optimization framework for calibrating simulated traffic models and constructed a calibrated simulation model for part of the Nicosia traffic network. Finally, we developed and released “SUMO-UAV-Py”, an open-source plugin integrated into the SUMO simulation environment to emulate UAV-based traffic sensing.
In Pillar 1, we proposed a novel methodology, based on Bayesian Statistics, to predict traffic patterns in areas and times where direct measurements are not available. In addition, we proposed algorithms that reveal urban traffic demand patterns. To support this, we developed a model-based origin-destination (OD) estimation framework that integrates a path-based traffic model within an optimization-based formulation, effectively reconciling observed link-level data with modelled traffic flows. To address data quality challenges from sensor faults, we developed a fault-tolerant algorithm that detects, isolates, and corrects faulty data during OD estimation. Finally, we developed custom, real-time optimization and machine learning solutions for fine-grained traffic state estimation.
In Pillar 2, we developed several model-based traffic control schemes from an optimization and control-theoretic view. The established approaches tackled the challenge of improving UM performance from multiple angles by developing better and faster solution algorithms, analyzing the stability and optimality properties of the network, optimizing multiple objectives, considering mixed traffic (both human-driven and autonomous vehicles), dealing efficiently with uncertainty, and securing the road networks against adversaries. Moreover, we devised UM control strategies that rely solely on traffic data. The developed strategies explicitly (by selecting when each vehicle should depart and what route to take) or implicitly (through pricing) control traffic demand, aiming to eliminate congestion.
In Pillar 3, we developed novel UAV placement and control methodologies to improve UM performance. Specifically, we designed and solved multi-objective optimization problems that select the locations of sensors to maximize traffic flow coverage and maintain minimum distances between sensor locations for fixed sensor locations (e.g. stationary UAVs). In addition, we proposed an online, uncertainty-driven UAV trajectory planning methodology inspired by statistical learning theory, enabling UAVs to select their future sensing locations in real-time.
In Pillar 4, we established a comprehensive framework for generating and analyzing real-life UM datasets. Towards this direction, our work focused on: (a) establishing a regulatory and operational framework for multi-UAV missions in urban settings, (b) developing Computer Vision algorithms for vehicle detection, re-identification, trajectory mapping, and speed estimation, and (c) building the software tool “UAVTrafficPy” for extracting and visualizing traffic data. Moreover, we established an optimization framework for calibrating simulated traffic models and constructed a calibrated simulation model for part of the Nicosia traffic network. Finally, we developed and released “SUMO-UAV-Py”, an open-source plugin integrated into the SUMO simulation environment to emulate UAV-based traffic sensing.
All achievements and results presented in the previous section go beyond the state-of-the-art and offer significant potential impacts.
In Pillar 1, three main potential impacts emanate from the results. First, the methodologies developed can significantly improve our understanding of current and future traffic conditions, even at times/areas with no sensor coverage, enabling improved traffic control and planning. Second, by reducing reliance on dense sensor networks and enabling UAV-based data collection, cities can achieve high-quality traffic insights with lower operational costs. Third, fault-tolerant algorithms ensure robust performance even under adverse data conditions, increasing trust in automated traffic systems. To fully realize these results, regulatory changes are needed to enable autonomous multi-UAV operations in urban environments.
The UM and UAV control strategies developed in Pillars 2 and 3 have transformative potential for UM by enabling dynamic, uncertainty-aware, and data-driven real-time traffic management. Simulations under realistic conditions show that the proposed demand management strategies can effectively eliminate congestion, marking a step-change in urban traffic efficiency. To fully realize these results, regulatory and standardization updates are needed to enable vehicle-to-infrastructure collaboration, enabling demand management strategies that advise travelers on choosing optimal departure times and routes.
Finally, the methods and tools developed under Pillar 4 provide a robust foundation for UAV-enabled traffic data generation and analysis, while also facilitating the evaluation of different UM monitoring and control methodologies under UAV-based sensing from researchers and practitioners.
In Pillar 1, three main potential impacts emanate from the results. First, the methodologies developed can significantly improve our understanding of current and future traffic conditions, even at times/areas with no sensor coverage, enabling improved traffic control and planning. Second, by reducing reliance on dense sensor networks and enabling UAV-based data collection, cities can achieve high-quality traffic insights with lower operational costs. Third, fault-tolerant algorithms ensure robust performance even under adverse data conditions, increasing trust in automated traffic systems. To fully realize these results, regulatory changes are needed to enable autonomous multi-UAV operations in urban environments.
The UM and UAV control strategies developed in Pillars 2 and 3 have transformative potential for UM by enabling dynamic, uncertainty-aware, and data-driven real-time traffic management. Simulations under realistic conditions show that the proposed demand management strategies can effectively eliminate congestion, marking a step-change in urban traffic efficiency. To fully realize these results, regulatory and standardization updates are needed to enable vehicle-to-infrastructure collaboration, enabling demand management strategies that advise travelers on choosing optimal departure times and routes.
Finally, the methods and tools developed under Pillar 4 provide a robust foundation for UAV-enabled traffic data generation and analysis, while also facilitating the evaluation of different UM monitoring and control methodologies under UAV-based sensing from researchers and practitioners.