|Real-time and Coordinated UAV Path Planning for Road Traffic Surveillance: A Penalty-based Boundary Intersection Approach
Xiaofeng Liu*, Zhong-Ren Peng, Li-Ye Zhang, and Qiang Chen
International Journal of Control, Automation, and Systems, vol. 20, no. 8, pp.2655-2668, 2022
Abstract : Traffic surveillance of mountain roads accords problems of high risk, low efficiency, and high cost; thus, unmanned aerial vehicles (UAVs) are introduced for traffic surveillance, working in conjunction with a delivery van. UAVs are assigned to monitor the high-risk road segments, while the low-risk segments are monitored by the delivery van. UAVs take off from and return to the delivery van to improve the speed and flexibility of the traffic surveillance, with reduced risk. First, a real-time and coordinated UAV path-planning problem is presented, in which the number of monitored targets is dynamic and the delivery van is moving. Then, a multi-objective optimization model is proposed to minimize both the coordination value of UAV flight distance and the number of UAVs used. Next, a penalty-based boundary intersection optimization algorithm is proposed, which adopts the decomposition strategy and Pareto technique to acquire the optimized paths in real-time. In addition, a case study is implemented to compare the proposed algorithm with two commonly used algorithms and the results indicate that the proposed algorithm performs better with respect to solution quality and calculation time. Moreover, the cost versus performance of the UAV traffic surveillance was analyzed. This demonstrates that it is effective to use the proposed approach to conduct real-time and coordinated UAV path planning. Finally, the limitations and prospects of UAV traffic surveillance are presented.
Optimization, path planning, traffic surveillance, unmanned aerial vehicle.
Download PDF : Click this link