A quasi-dynamic air traffic assignment model for mitigating air traffic complexity and congestion for high-density UAM operations

Wang, Zhengyi; Delahaye, Daniel; Farges, Jean‐Loup; Alam, Sameer

doi:10.1016/j.trc.2023.104279

Cited by 6 publications

(3 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, the implementation of virtual channels in this framework effectively addresses the issue of chaotic trajectories in apron operations [38], thereby standardizing the operating routes of GSE vehicles and improving operational efficiency. The techniques in this paper can also be used in research related to Urban Air Mobility (UAM) [45,46] and autonomous driving communication [47].…”

Section: Discussionmentioning

confidence: 99%

Detection and Control Framework for Unpiloted Ground Support Equipment within the Aircraft Stand

Zhang,

Zhu

2023

Sensors

View full text Add to dashboard Cite

The rapid advancement in Unpiloted Robotic Vehicle technology has significantly influenced ground support operations at airports, marking a critical shift towards future development. This study presents a novel Unpiloted Ground Support Equipment (GSE) detection and control framework, comprising virtual channel delineation, boundary line detection, object detection, and navigation and docking control, to facilitate automated aircraft docking within the aircraft stand. Firstly, we developed a bespoke virtual channel layout for Unpiloted GSE, aligning with operational regulations and accommodating a wide spectrum of aircraft types. This layout employs turning induction markers to define essential navigation points, thereby streamlining GSE movement. Secondly, we integrated cameras and Lidar sensors to enable rapid and precise pose adjustments during docking. The introduction of a boundary line detection system, along with an optimized, lightweight YOLO algorithm, ensures swift and accurate identification of boundaries, obstacles, and docking sites. Finally, we formulated a unique control algorithm for effective obstacle avoidance and docking in varied apron conditions, guaranteeing meticulous management of vehicle pose and speed. Our experimental findings reveal an 89% detection accuracy for the virtual channel boundary line, a 95% accuracy for guiding markers, and an F1-Score of 0.845 for the YOLO object detection algorithm. The GSE achieved an average docking error of less than 3 cm and an angular deviation under 5 degrees, corroborating the efficacy and advanced nature of our proposed approach in Unpiloted GSE detection and aircraft docking.

show abstract

Section: Discussionmentioning

confidence: 99%

Detection and Control Framework for Unpiloted Ground Support Equipment within the Aircraft Stand

Zhang,

Zhu

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The economy is also burdened with large expenses as a result of productivity losses. Therefore, there is a pressing need for creative solutions to lessen the negative consequences of congestion and improve urban mobility [21]- [26].…”

Section: Review Of Literature 1 Urban Traffic Jams and Their Conseque...mentioning

confidence: 99%

Data-Intensive Traffic Management: Real-Time Insights from the Traffic Management Simulation Test

Blinova,

Kumar,

Kansal

et al. 2024

BIO Web Conf.

View full text Add to dashboard Cite

This research examined the effectiveness of data-intensive traffic management in urban settings using real-time insights from traffic management simulation experiments. The examination of data on traffic flow revealed a noteworthy decrease in congestion, with a 25% increase in traffic velocity during peak hours. Real-time information led to a 40% drop in the severity of traffic accidents and a 50% reduction in reaction times. Improved road safety was aided by a 30% decrease in accidents during inclement weather thanks to real-time weather data. To further optimize urban traffic flow, dynamic traffic management operations based on real-time information also resulted in a 20% reduction in congestion. These results highlight the revolutionary potential of data-intensive traffic management, offering safer and more effective urban transportation solutions by incorporating real-time information into traffic control plans.

show abstract

“…However, the optimization-based approach often cannot guarantee satisfactory real-time performance due to computational complexity, and, sometimes, it does not take control feasibility into consideration. Flow-based path planning and collision avoidance has also been the focus of recent research, like the unmanned air mobility study in reference [17], with a simulated annealing and parallel computing solution, and path planning for shared autonomous vehicles in a dynamic traffic network in reference [18].…”

Section: Introductionmentioning

confidence: 99%

Deep-Reinforcement-Learning-Based Collision Avoidance of Autonomous Driving System for Vulnerable Road User Safety

Chen,

Cao,

Guvenc

et al. 2024

Electronics

View full text Add to dashboard Cite

The application of autonomous driving system (ADS) technology can significantly reduce potential accidents involving vulnerable road users (VRUs) due to driver error. This paper proposes a novel hierarchical deep reinforcement learning (DRL) framework for high-performance collision avoidance, which enables the automated driving agent to perform collision avoidance maneuvers while maintaining appropriate speeds and acceptable social distancing. The novelty of the DRL method proposed here is its ability to accommodate dynamic obstacle avoidance, which is necessary as pedestrians are moving dynamically in their interactions with nearby ADSs. This is an improvement over existing DRL frameworks that have only been developed and demonstrated for stationary obstacle avoidance problems. The hybrid A* path searching algorithm is first applied to calculate a pre-defined path marked by waypoints, and a low-level path-following controller is used under cases where no VRUs are detected. Upon detection of any VRUs, however, a high-level DRL collision avoidance controller is activated to prompt the vehicle to either decelerate or change its trajectory to prevent potential collisions. The CARLA simulator is used to train the proposed DRL collision avoidance controller, and virtual raw sensor data are utilized to enhance the realism of the simulations. The model-in-the-loop (MIL) methodology is utilized to assess the efficacy of the proposed DRL ADS routine. In comparison to the traditional DRL end-to-end approach, which combines high-level decision making with low-level control, the proposed hierarchical DRL agents demonstrate superior performance.

show abstract

A quasi-dynamic air traffic assignment model for mitigating air traffic complexity and congestion for high-density UAM operations

Cited by 6 publications

References 51 publications

Detection and Control Framework for Unpiloted Ground Support Equipment within the Aircraft Stand

Detection and Control Framework for Unpiloted Ground Support Equipment within the Aircraft Stand

Data-Intensive Traffic Management: Real-Time Insights from the Traffic Management Simulation Test

Deep-Reinforcement-Learning-Based Collision Avoidance of Autonomous Driving System for Vulnerable Road User Safety

Contact Info

Product

Resources

About