Choosing the best path during unmanned air vehicle （UAV） flying is the target of the UAV mission planning problem. Because of its nearly constant flight height, the UAV mission planning problem can be treated as a 2...Choosing the best path during unmanned air vehicle （UAV） flying is the target of the UAV mission planning problem. Because of its nearly constant flight height, the UAV mission planning problem can be treated as a 2-D （horizontal） path arrangement problem. By modeling the antiaircraft threat, the UAV mission planning can be mapped to the traveling seaman problem （TSP）. A new algorithm is presented to solve the TSP. The algorithm combines the traditional ant colony system （ACS） with particle swarm optimization （PSO）, thus being called the AC-PSO algorithm. It uses one by one tour building strategy like ACS to determine that the target point can be chosen like PSO. Experiments show that AC-PSO synthesizes both ACS and PSO and obtains excellent solution of the UAV mission planning with a higher accuracy.展开更多
To satisfy the increasing demands of high-speed transmission, high-efficiency computing, and real-time communications in the high-dynamic and heterogeneous networks, the Contact Plan Design(CPD) has attracted continuo...To satisfy the increasing demands of high-speed transmission, high-efficiency computing, and real-time communications in the high-dynamic and heterogeneous networks, the Contact Plan Design(CPD) has attracted continuous attention in recent years, especially for the spatial-node-based Internet of Everything(IoE). In this paper, we study the NP-hardness of contact scheduling and the attenuation of atmospheric precipitation in the spatial-node-based IoE. Two heuristic computing methods for contact plan design are proposed by comprehensively considering the time-varying topology, the intermittent connectivity, and the adaptive transmission in different weather conditions, which are named Contact Plan Design-Particle Swarm Optimization(CPD-PSO) and Contact Plan Design-Greedy algorithm with the Minimum Delivery Time(CPD-GMDT) separately. For the population-based algorithm, CPD-PSO not only solves the CPD problem with a limited-resource condition, but also dynamically adjusts the search scope to ensure the continuous searching capability of the algorithm. For the CPD-GMDT that makes CP decisions based on the current state, the algorithm uses the idea of greedy algorithm to schedule Satellite-Platform Links(SPLs) and Inter Satellite Links(ISLs) respectively using the strategies of optimal matching and load balancing. The simulation results show that the proposed CPD-PSO outperforms Contact Plan Design-Genetic Algorithm(CPD-GA) in terms of fitness and delivery time, and CPD-GMDT presents better overall delay than Fair Contact Plan(FCP).展开更多
Intelligent and connected vehicles have leveraged edge computing paradigm to enhance their environment comprehension and behavior planning capabilities.As the quantity of intelligent vehicles and the demand for edge c...Intelligent and connected vehicles have leveraged edge computing paradigm to enhance their environment comprehension and behavior planning capabilities.As the quantity of intelligent vehicles and the demand for edge computing are increasing rapidly,it becomes critical to efficiently orchestrate the communication and computation resources on edge clouds.Existing methods usually perform resource allocation in a fairly effective but still reactive manner,which is subject to the capacity of nearby edge clouds.To deal with the contradiction between the spatiotemporally varying demands for edge computing and the fixed edge cloud capacity,we proactively balance the edge computing demands across edge clouds by appropriate route planning.In this paper,route planning and resource allocation are jointly optimized to enhance intelligent driving.We propose a multi-scale decentralized optimization method to deal with the curse of dimensionality.In large-scale optimization,backpressure algorithm is used to conduct route planning and load balancing across edge clouds.In small-scale optimization,game-theoretic multi-agent learning is exploited to perform regional resource allocation.The experimental results show that the proposed algorithm outperforms the baseline algorithms which optimize route planning and resource allocation separately.展开更多
Autonomous Underwater Vehicles （AUVs） are capable of conducting various underwater missions and marine tasks over long periods of time. In this study, a novel conflict-free motion-planning framework is introduced. T...Autonomous Underwater Vehicles （AUVs） are capable of conducting various underwater missions and marine tasks over long periods of time. In this study, a novel conflict-free motion-planning framework is introduced. This framework enhances AUV mission performance by completing the maximum number of highest priority tasks in a limited time through a large-scale waypoint cluttered operating field and ensuring safe deployment during the mission. The proposed combinatorial route-path-planner model takes advantage of the Biogeography- Based Optimization （BBO） algorithm to satisfy the objectives of both higher- and lower-level motion planners and guarantee the maximization of mission productivity for a single vehicle operation. The performance of the model is investigated under different scenarios, including cost constraints in time-varying operating fields. To demonstrate the reliability of the proposed model, the performance of each motion planner is separately assessed and statistical analysis is conducted to evaluate the total performance of the entire model. The simulation results indicate the stability of the proposed model and the feasibility of its application to real-time experiments.展开更多
融合物联网技术云计算技术提出智能传感激光SLAM(Simultaneous localization and mapping)算法,首先基于成分分析法相邻帧的点云计算矩阵进行粗配准,再使用改良后算法提供的改进点到线迭代的最近配准算法来弥补传统算法精度较低的问题...融合物联网技术云计算技术提出智能传感激光SLAM(Simultaneous localization and mapping)算法,首先基于成分分析法相邻帧的点云计算矩阵进行粗配准,再使用改良后算法提供的改进点到线迭代的最近配准算法来弥补传统算法精度较低的问题。采用了多重采样的算法在多次复制大权重例子集合的背景下利用小权重粒子集合来提升移动机器人路径定位精准度。最后将改良后的算法运用于AI移动机器人,实验结果表明,改进后的SLAM算法对移动机器人的路径设计的定位精准度有了较大提升,AI机器人可以具备优良的避障功能,对于已知环境或者非完全已知环境中存在的障碍物都具有良好的适应能力。展开更多
文摘Choosing the best path during unmanned air vehicle （UAV） flying is the target of the UAV mission planning problem. Because of its nearly constant flight height, the UAV mission planning problem can be treated as a 2-D （horizontal） path arrangement problem. By modeling the antiaircraft threat, the UAV mission planning can be mapped to the traveling seaman problem （TSP）. A new algorithm is presented to solve the TSP. The algorithm combines the traditional ant colony system （ACS） with particle swarm optimization （PSO）, thus being called the AC-PSO algorithm. It uses one by one tour building strategy like ACS to determine that the target point can be chosen like PSO. Experiments show that AC-PSO synthesizes both ACS and PSO and obtains excellent solution of the UAV mission planning with a higher accuracy.
基金jointly supported by the National Natural Science Foundation in China (61601075, 61671092, 61771120, 61801105)the Fundamental Research Funds for the Central University (N171602002)the Natural Science Foundation Project of CQ CSTC (cstc2016jcyjA0174)
文摘To satisfy the increasing demands of high-speed transmission, high-efficiency computing, and real-time communications in the high-dynamic and heterogeneous networks, the Contact Plan Design(CPD) has attracted continuous attention in recent years, especially for the spatial-node-based Internet of Everything(IoE). In this paper, we study the NP-hardness of contact scheduling and the attenuation of atmospheric precipitation in the spatial-node-based IoE. Two heuristic computing methods for contact plan design are proposed by comprehensively considering the time-varying topology, the intermittent connectivity, and the adaptive transmission in different weather conditions, which are named Contact Plan Design-Particle Swarm Optimization(CPD-PSO) and Contact Plan Design-Greedy algorithm with the Minimum Delivery Time(CPD-GMDT) separately. For the population-based algorithm, CPD-PSO not only solves the CPD problem with a limited-resource condition, but also dynamically adjusts the search scope to ensure the continuous searching capability of the algorithm. For the CPD-GMDT that makes CP decisions based on the current state, the algorithm uses the idea of greedy algorithm to schedule Satellite-Platform Links(SPLs) and Inter Satellite Links(ISLs) respectively using the strategies of optimal matching and load balancing. The simulation results show that the proposed CPD-PSO outperforms Contact Plan Design-Genetic Algorithm(CPD-GA) in terms of fitness and delivery time, and CPD-GMDT presents better overall delay than Fair Contact Plan(FCP).
基金supported in part by the Natural Science Foundation of China under Grant 61902035 and Grant 61876023in part by the Natural Science Foundation of Shandong Province of China under Grant ZR2020LZH005in part by China Postdoctoral Science Foundation under Grant 2019M660565.
文摘Intelligent and connected vehicles have leveraged edge computing paradigm to enhance their environment comprehension and behavior planning capabilities.As the quantity of intelligent vehicles and the demand for edge computing are increasing rapidly,it becomes critical to efficiently orchestrate the communication and computation resources on edge clouds.Existing methods usually perform resource allocation in a fairly effective but still reactive manner,which is subject to the capacity of nearby edge clouds.To deal with the contradiction between the spatiotemporally varying demands for edge computing and the fixed edge cloud capacity,we proactively balance the edge computing demands across edge clouds by appropriate route planning.In this paper,route planning and resource allocation are jointly optimized to enhance intelligent driving.We propose a multi-scale decentralized optimization method to deal with the curse of dimensionality.In large-scale optimization,backpressure algorithm is used to conduct route planning and load balancing across edge clouds.In small-scale optimization,game-theoretic multi-agent learning is exploited to perform regional resource allocation.The experimental results show that the proposed algorithm outperforms the baseline algorithms which optimize route planning and resource allocation separately.
文摘Autonomous Underwater Vehicles （AUVs） are capable of conducting various underwater missions and marine tasks over long periods of time. In this study, a novel conflict-free motion-planning framework is introduced. This framework enhances AUV mission performance by completing the maximum number of highest priority tasks in a limited time through a large-scale waypoint cluttered operating field and ensuring safe deployment during the mission. The proposed combinatorial route-path-planner model takes advantage of the Biogeography- Based Optimization （BBO） algorithm to satisfy the objectives of both higher- and lower-level motion planners and guarantee the maximization of mission productivity for a single vehicle operation. The performance of the model is investigated under different scenarios, including cost constraints in time-varying operating fields. To demonstrate the reliability of the proposed model, the performance of each motion planner is separately assessed and statistical analysis is conducted to evaluate the total performance of the entire model. The simulation results indicate the stability of the proposed model and the feasibility of its application to real-time experiments.
文摘融合物联网技术云计算技术提出智能传感激光SLAM(Simultaneous localization and mapping)算法,首先基于成分分析法相邻帧的点云计算矩阵进行粗配准,再使用改良后算法提供的改进点到线迭代的最近配准算法来弥补传统算法精度较低的问题。采用了多重采样的算法在多次复制大权重例子集合的背景下利用小权重粒子集合来提升移动机器人路径定位精准度。最后将改良后的算法运用于AI移动机器人,实验结果表明,改进后的SLAM算法对移动机器人的路径设计的定位精准度有了较大提升,AI机器人可以具备优良的避障功能,对于已知环境或者非完全已知环境中存在的障碍物都具有良好的适应能力。
