Efficient flight path design for unmanned aerial vehicles(UAVs)in urban environmental event monitoring remains a critical challenge,particularly in prioritizing high-risk zones within complex urban landscapes.Current ...Efficient flight path design for unmanned aerial vehicles(UAVs)in urban environmental event monitoring remains a critical challenge,particularly in prioritizing high-risk zones within complex urban landscapes.Current UAV path planning methodologies often inadequately account for environmental risk factors and exhibit limitations in balancing global and local optimization efficiency.To address these gaps,this study proposes a hybrid path planning framework integrating an improved Ant Colony Optimization(ACO)algorithm with an Orthogonal Jump Point Search(OJPS)algorithm.Firstly,a two-dimensional grid model is constructed to simulate urban environments,with key monitoring nodes selected based on grid-specific environmental risk values.Subsequently,the improved ACO algorithm is used for global path planning,and the OJPS algorithm is integrated to optimize the local path.The improved ACO algorithm introduces the risk value of environmental events,which is used to direct the UAV to the area with higher risk.In the OJPS algorithm,the path search direction is restricted to the orthogonal direction,which improves the computational efficiency of local path optimization.In order to evaluate the performance of the model,this paper utilizes the metrics of the average risk value of the path,the flight time,and the number of turns.The experimental results demonstrate that the proposed improved ACO algorithm performs well in the average risk value of the paths traveled within the first 5 min,within the first 8 min,and within the first 10 min,with improvements of 48.33%,26.10%,and 6.746%,respectively,over the Particle Swarm Optimization(PSO)algorithm and 70.33%,19.08%,and 10.246%,respectively,over theArtificial Rabbits Optimization(ARO)algorithm.TheOJPS algorithmdemonstrates superior performance in terms of flight time and number of turns,exhibiting a reduction of 40%,40%and 57.1%in flight time compared to the other three algorithms,and a reduction of 11.1%,11.1%and 33.8%in the number of turns compared to the other three algorithms.These results highlight the effectiveness of the proposed method in improving the UAV’s ability to respond efficiently to urban environmental events,offering significant implications for the future of UAV path planning in complex urban settings.展开更多
基金supported by the Special Project forKey Fields of Ordinary Universities in Guangdong Province(Number:2023ZDZX1076).
文摘Efficient flight path design for unmanned aerial vehicles(UAVs)in urban environmental event monitoring remains a critical challenge,particularly in prioritizing high-risk zones within complex urban landscapes.Current UAV path planning methodologies often inadequately account for environmental risk factors and exhibit limitations in balancing global and local optimization efficiency.To address these gaps,this study proposes a hybrid path planning framework integrating an improved Ant Colony Optimization(ACO)algorithm with an Orthogonal Jump Point Search(OJPS)algorithm.Firstly,a two-dimensional grid model is constructed to simulate urban environments,with key monitoring nodes selected based on grid-specific environmental risk values.Subsequently,the improved ACO algorithm is used for global path planning,and the OJPS algorithm is integrated to optimize the local path.The improved ACO algorithm introduces the risk value of environmental events,which is used to direct the UAV to the area with higher risk.In the OJPS algorithm,the path search direction is restricted to the orthogonal direction,which improves the computational efficiency of local path optimization.In order to evaluate the performance of the model,this paper utilizes the metrics of the average risk value of the path,the flight time,and the number of turns.The experimental results demonstrate that the proposed improved ACO algorithm performs well in the average risk value of the paths traveled within the first 5 min,within the first 8 min,and within the first 10 min,with improvements of 48.33%,26.10%,and 6.746%,respectively,over the Particle Swarm Optimization(PSO)algorithm and 70.33%,19.08%,and 10.246%,respectively,over theArtificial Rabbits Optimization(ARO)algorithm.TheOJPS algorithmdemonstrates superior performance in terms of flight time and number of turns,exhibiting a reduction of 40%,40%and 57.1%in flight time compared to the other three algorithms,and a reduction of 11.1%,11.1%and 33.8%in the number of turns compared to the other three algorithms.These results highlight the effectiveness of the proposed method in improving the UAV’s ability to respond efficiently to urban environmental events,offering significant implications for the future of UAV path planning in complex urban settings.
