Unmanned air vehicles(UAVs) have been regularly employed in modern wars to conduct different missions. Instead of addressing mission planning and route planning separately,this study investigates the issue of joint mi...Unmanned air vehicles(UAVs) have been regularly employed in modern wars to conduct different missions. Instead of addressing mission planning and route planning separately,this study investigates the issue of joint mission and route planning for a fleet of UAVs. The mission planning determines the configuration of weapons in UAVs and the weapons to attack targets, while the route planning determines the UAV’s visiting sequence for the targets. The problem is formulated as an integer linear programming model. Due to the inefficiency of CPLEX on large scale optimization problems, an effective learningbased heuristic, namely, population based adaptive large neighborhood search(P-ALNS), is proposed to solve the model. In P-ALNS, seven neighborhood structures are designed and adaptively utilized in terms of their historical performance. The effectiveness and superiority of the proposed model and algorithm are demonstrated on test instances of small, medium and large sizes. In particular, P-ALNS achieves comparable solutions or as good as those of CPLEX on small-size(20 targets)instances in much shorter time.展开更多
Unmanned combat air vehicles(UCAVs) mission planning is a fairly complicated global optimum problem. Military attack missions often employ a fleet of UCAVs equipped with weapons to attack a set of known targets. A UCA...Unmanned combat air vehicles(UCAVs) mission planning is a fairly complicated global optimum problem. Military attack missions often employ a fleet of UCAVs equipped with weapons to attack a set of known targets. A UCAV can carry different weapons to accomplish different combat missions. Choice of different weapons will have different effects on the final combat effectiveness. This work presents a mixed integer programming model for simultaneous weapon configuration and route planning of UCAVs, which solves the problem optimally using the IBM ILOG CPLEX optimizer for simple missions. This paper develops a heuristic algorithm to handle the medium-scale and large-scale problems. The experiments demonstrate the performance of the heuristic algorithm in solving the medium scale and large scale problems. Moreover, we give suggestions on how to select the most appropriate algorithm to solve different scale problems.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
To address the issue of premature convergence and slow convergence rate in three-dimensional (3D) route planning of unmanned aerial vehicle (UAV) low-altitude penetration,a novel route planning method was proposed.Fir...To address the issue of premature convergence and slow convergence rate in three-dimensional (3D) route planning of unmanned aerial vehicle (UAV) low-altitude penetration,a novel route planning method was proposed.First and foremost,a coevolutionary multi-agent genetic algorithm (CE-MAGA) was formed by introducing coevolutionary mechanism to multi-agent genetic algorithm (MAGA),an efficient global optimization algorithm.A dynamic route representation form was also adopted to improve the flight route accuracy.Moreover,an efficient constraint handling method was used to simplify the treatment of multi-constraint and reduce the time-cost of planning computation.Simulation and corresponding analysis show that the planning results of CE-MAGA have better performance on terrain following,terrain avoidance,threat avoidance (TF/TA2) and lower route costs than other existing algorithms.In addition,feasible flight routes can be acquired within 2 s,and the convergence rate of the whole evolutionary process is very fast.展开更多
Unmanned aerial vehicle(UAV)was introduced as a novel traffic device to collect road traffic information and its cruise route planning problem was considered.Firstly,a multi-objective optimization model was proposed a...Unmanned aerial vehicle(UAV)was introduced as a novel traffic device to collect road traffic information and its cruise route planning problem was considered.Firstly,a multi-objective optimization model was proposed aiming at minimizing the total cruise distance and the number of UAVs used,which used UAV maximum cruise distance,the number of UAVs available and time window of each monitored target as constraints.Then,a novel multi-objective evolutionary algorithm was proposed.Next,a case study with three time window scenarios was implemented.The results show that both the total cruise distance and the number of UAVs used continue to increase with the time window constraint becoming narrower.Compared with the initial optimal solutions,the optimal total cruise distance and the number of UAVs used fall by an average of 30.93% and 31.74%,respectively.Finally,some concerns using UAV to collect road traffic information were discussed.展开更多
With technological advancements in 6G and Internet of Things(IoT), the incorporation of Unmanned Aerial Vehicles (UAVs) and cellularnetworks has become a hot research topic. At present, the proficient evolution of 6G ...With technological advancements in 6G and Internet of Things(IoT), the incorporation of Unmanned Aerial Vehicles (UAVs) and cellularnetworks has become a hot research topic. At present, the proficient evolution of 6G networks allows the UAVs to offer cost-effective and timelysolutions for real-time applications such as medicine, tracking, surveillance,etc. Energy efficiency, data collection, and route planning are crucial processesto improve the network communication. These processes are highly difficultowing to high mobility, presence of non-stationary links, dynamic topology,and energy-restricted UAVs. With this motivation, the current research paperpresents a novel Energy Aware Data Collection with Routing Planning for6G-enabled UAV communication (EADCRP-6G) technique. The goal of theproposed EADCRP-6G technique is to conduct energy-efficient cluster-baseddata collection and optimal route planning for 6G-enabled UAV networks.EADCRP-6G technique deploys Improved Red Deer Algorithm-based Clustering (IRDAC) technique to elect an optimal set of Cluster Heads (CH) andorganize these clusters. Besides, Artificial Fish Swarm-based Route Planning(AFSRP) technique is applied to choose an optimum set of routes for UAVcommunication in 6G networks. In order to validated whether the proposedEADCRP-6G technique enhances the performance, a series of simulationswas performed and the outcomes were investigated under different dimensions.The experimental results showcase that the proposed model outperformed allother existing models under different evaluation parameters.展开更多
Unmanned aerial vehicle(UAV)was introduced to take road segment traffic surveillance.Considering the limited UAV maximum flight distance,UAV route planning problem was studied.First,a multi-objective optimization mode...Unmanned aerial vehicle(UAV)was introduced to take road segment traffic surveillance.Considering the limited UAV maximum flight distance,UAV route planning problem was studied.First,a multi-objective optimization model of planning UAV route for road segment surveillance was proposed,which aimed to minimize UAV cruise distance and minimize the number of UAVs used.Then,an evolutionary algorithm based on Pareto optimality technique was proposed to solve multi-objective UAV route planning problem.At last,a UAV flight experiment was conducted to test UAV route planning effect,and a case with three scenarios was studied to analyze the impact of different road segment lengths on UAV route planning.The case results show that the optimized cruise distance and the number of UAVs used decrease by an average of 38.43% and 33.33%,respectively.Additionally,shortening or extending the length of road segments has different impacts on UAV route planning.展开更多
Automated Guided Vehicles(AGVs)have been introduced into various applications,such as automated warehouse systems,flexible manufacturing systems,and container terminal systems.However,few publications have outlined pr...Automated Guided Vehicles(AGVs)have been introduced into various applications,such as automated warehouse systems,flexible manufacturing systems,and container terminal systems.However,few publications have outlined problems in need of attention in AGV applications comprehensively.In this paper,several key issues and essential models are presented.First,the advantages and disadvantages of centralized and decentralized AGVs systems were compared;second,warehouse layout and operation optimization were introduced,including some omitted areas,such as AGVs fleet size and electrical energy management;third,AGVs scheduling algorithms in chessboardlike environments were analyzed;fourth,the classical route-planning algorithms for single AGV and multiple AGVs were presented,and some Artificial Intelligence(AI)-based decision-making algorithms were reviewed.Furthermore,a novel idea for accelerating route planning by combining Reinforcement Learning(RL)andDijkstra’s algorithm was presented,and a novel idea of the multi-AGV route-planning method of combining dynamic programming and Monte-Carlo tree search was proposed to reduce the energy cost of systems.展开更多
Vehicle routing problem in distribution (VRPD) is a widely used type of vehicle routing problem (VRP), which has been proved as NP-Hard, and it is usually modeled as single objective optimization problem when mode...Vehicle routing problem in distribution (VRPD) is a widely used type of vehicle routing problem (VRP), which has been proved as NP-Hard, and it is usually modeled as single objective optimization problem when modeling. For multi-objective optimization model, most researches consider two objectives. A multi-objective mathematical model for VRP is proposed, which considers the number of vehicles used, the length of route and the time arrived at each client. Genetic algorithm is one of the most widely used algorithms to solve VRP. As a type of genetic algorithm (GA), non-dominated sorting in genetic algorithm-Ⅱ (NSGA-Ⅱ) also suffers from premature convergence and enclosure competition. In order to avoid these kinds of shortage, a greedy NSGA-Ⅱ (GNSGA-Ⅱ) is proposed for VRP problem. Greedy algorithm is implemented in generating the initial population, cross-over and mutation. All these procedures ensure that NSGA-Ⅱ is prevented from premature convergence and refine the performance of NSGA-Ⅱ at each step. In the distribution problem of a distribution center in Michigan, US, the GNSGA-Ⅱ is compared with NSGA-Ⅱ. As a result, the GNSGA-Ⅱ is the most efficient one and can get the most optimized solution to VRP problem. Also, in GNSGA-Ⅱ, premature convergence is better avoided and search efficiency has been improved sharply.展开更多
The vehicle routing problem(VRP)is a typical discrete combinatorial optimization problem,and many models and algorithms have been proposed to solve the VRP and its variants.Although existing approaches have contribute...The vehicle routing problem(VRP)is a typical discrete combinatorial optimization problem,and many models and algorithms have been proposed to solve the VRP and its variants.Although existing approaches have contributed significantly to the development of this field,these approaches either are limited in problem size or need manual intervention in choosing parameters.To solve these difficulties,many studies have considered learning-based optimization(LBO)algorithms to solve the VRP.This paper reviews recent advances in this field and divides relevant approaches into end-to-end approaches and step-by-step approaches.We performed a statistical analysis of the reviewed articles from various aspects and designed three experiments to evaluate the performance of four representative LBO algorithms.Finally,we conclude the applicable types of problems for different LBO algorithms and suggest directions in which researchers can improve LBO algorithms.展开更多
As a new variant of vehicle routing problem( VRP),a finished vehicle routing problem with time windows in finished vehicle logistics( FVRPTW) is modeled and solved. An optimization model for FVRPTW is presented with t...As a new variant of vehicle routing problem( VRP),a finished vehicle routing problem with time windows in finished vehicle logistics( FVRPTW) is modeled and solved. An optimization model for FVRPTW is presented with the objective of scheduling multiple transport routes considering loading constraints along with time penalty function to minimize the total cost. Then a genetic algorithm( GA) is developed. The specific encoding and genetic operators for FVRPTW are devised.Especially,in order to accelerate its convergence,an improved termination condition is given. Finally,a case study is used to evaluate the effectiveness of the proposed algorithm and a series of experiments are conducted over a set of finished vehicle routing problems. The results demonstrate that the proposed approach has superior performance and satisfies users in practice. Contributions of the study are the modeling and solving of a complex FVRPTW in logistics industry.展开更多
With the challenge of great growing of transport diversity for the automobile enterprises, the heterogeneous vehicle routing problem with multiple depots, multiple types of finished vehicles and multiple types of tran...With the challenge of great growing of transport diversity for the automobile enterprises, the heterogeneous vehicle routing problem with multiple depots, multiple types of finished vehicles and multiple types of transport vehicles in finished vehicle logistics(HVRPMD) is modelled and solved. A multi-objective optimization model for HVRPMD is presented considering loading constraints to minimize the total cost and minimize the number of transport vehicles. Then a hybrid heuristic algorithm based on genetic algorithm and particle swarm optimization(GA-PSO) is developed. Moreover, a case study is used to evaluate the effectiveness of this algorithm. By comparing the GA-PSO algorithm with the traditional GA algorithm, the simulation results demonstrate the proposed GA-PSO algorithm is able to better support the HVRPMD problem in practice. Contributions of the paper are the modelling and solving of a complex HVRPMD in logistics industry.展开更多
As the proliferation and development of automated container terminal continue,the issues of efficiency and safety become increasingly significant.The container yard is one of the most crucial cargo distribution center...As the proliferation and development of automated container terminal continue,the issues of efficiency and safety become increasingly significant.The container yard is one of the most crucial cargo distribution centers in a terminal.Automated Guided Vehicles(AGVs)that carry materials of varying hazard levels through these yards without compromising on the safe transportation of hazardous materials,while also maximizing efficiency,is a complex challenge.This research introduces an algorithm that integrates Long Short-Term Memory(LSTM)neural network with reinforcement learning techniques,specifically Deep Q-Network(DQN),for routing an AGV carrying hazardous materials within a container yard.The objective is to ensure that the AGV carrying hazardous materials efficiently reaches its destination while effectively avoiding AGVs carrying non-hazardous materials.Utilizing real data from the Meishan Port in Ningbo,Zhejiang,China,the actual yard is first abstracted into an undirected graph.Since LSTM neural network can efficiently conveys and represents information in long time sequences and do not causes useful information before long time to be ignored,a two-layer LSTM neural network with 64 neurons per layer was constructed for predicting the motion trajectory of AGVs carrying non-hazardous materials,which are incorporated into the map as background AGVs.Subsequently,DQN is employed to plan the route for an AGV transporting hazardous materials,aiming to reach its destination swiftly while avoiding encounters with other AGVs.Experimental tests have shown that the route planning algorithm proposed in this study improves the level of avoidance of hazardous material AGV in relation to non-hazardous material AGVs.Compared to the method where hazardous material AGV follow the shortest path to their destination,the avoidance efficiency was enhanced by 3.11%.This improvement demonstrates potential strategies for balancing efficiency and safety in automated terminals.Additionally,it provides insights for designing avoidance schemes for autonomous driving AGVs,offering solutions for complex operational environments where safety and efficient navigation are paramount.展开更多
This paper describes a route planner that enables an autonomous underwater vehicle to selectively complete part of the predetermined tasks in the operating ocean area when the local path cost is stochastic.The problem...This paper describes a route planner that enables an autonomous underwater vehicle to selectively complete part of the predetermined tasks in the operating ocean area when the local path cost is stochastic.The problem is formulated as a variant of the orienteering problem.Based on the genetic algorithm(GA),we propose the greedy strategy based GA(GGA)which includes a novel rebirth operator that maps infeasible individuals into the feasible solution space during evolution to improve the efficiency of the optimization,and use a differential evolution planner for providing the deterministic local path cost.The uncertainty of the local path cost comes from unpredictable obstacles,measurement error,and trajectory tracking error.To improve the robustness of the planner in an uncertain environment,a sampling strategy for path evaluation is designed,and the cost of a certain route is obtained by multiple sampling from the probability density functions of local paths.Monte Carlo simulations are used to verify the superiority and effectiveness of the planner.The promising simulation results show that the proposed GGA outperforms its counterparts by 4.7%–24.6%in terms of total profit,and the sampling-based GGA route planner(S-GGARP)improves the average profit by 5.5%compared to the GGA route planner(GGARP).展开更多
基金supportes by the National Nature Science Foundation o f China (71771215,62122093)。
文摘Unmanned air vehicles(UAVs) have been regularly employed in modern wars to conduct different missions. Instead of addressing mission planning and route planning separately,this study investigates the issue of joint mission and route planning for a fleet of UAVs. The mission planning determines the configuration of weapons in UAVs and the weapons to attack targets, while the route planning determines the UAV’s visiting sequence for the targets. The problem is formulated as an integer linear programming model. Due to the inefficiency of CPLEX on large scale optimization problems, an effective learningbased heuristic, namely, population based adaptive large neighborhood search(P-ALNS), is proposed to solve the model. In P-ALNS, seven neighborhood structures are designed and adaptively utilized in terms of their historical performance. The effectiveness and superiority of the proposed model and algorithm are demonstrated on test instances of small, medium and large sizes. In particular, P-ALNS achieves comparable solutions or as good as those of CPLEX on small-size(20 targets)instances in much shorter time.
基金supported by the National Natural Science Foundation of China(7147117571471174)
文摘Unmanned combat air vehicles(UCAVs) mission planning is a fairly complicated global optimum problem. Military attack missions often employ a fleet of UCAVs equipped with weapons to attack a set of known targets. A UCAV can carry different weapons to accomplish different combat missions. Choice of different weapons will have different effects on the final combat effectiveness. This work presents a mixed integer programming model for simultaneous weapon configuration and route planning of UCAVs, which solves the problem optimally using the IBM ILOG CPLEX optimizer for simple missions. This paper develops a heuristic algorithm to handle the medium-scale and large-scale problems. The experiments demonstrate the performance of the heuristic algorithm in solving the medium scale and large scale problems. Moreover, we give suggestions on how to select the most appropriate algorithm to solve different scale problems.
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.
基金Project(60925011) supported by the National Natural Science Foundation for Distinguished Young Scholars of ChinaProject(9140A06040510BQXXXX) supported by Advanced Research Foundation of General Armament Department,China
文摘To address the issue of premature convergence and slow convergence rate in three-dimensional (3D) route planning of unmanned aerial vehicle (UAV) low-altitude penetration,a novel route planning method was proposed.First and foremost,a coevolutionary multi-agent genetic algorithm (CE-MAGA) was formed by introducing coevolutionary mechanism to multi-agent genetic algorithm (MAGA),an efficient global optimization algorithm.A dynamic route representation form was also adopted to improve the flight route accuracy.Moreover,an efficient constraint handling method was used to simplify the treatment of multi-constraint and reduce the time-cost of planning computation.Simulation and corresponding analysis show that the planning results of CE-MAGA have better performance on terrain following,terrain avoidance,threat avoidance (TF/TA2) and lower route costs than other existing algorithms.In addition,feasible flight routes can be acquired within 2 s,and the convergence rate of the whole evolutionary process is very fast.
基金Project(2009AA11Z220)supported by the National High Technology Research and Development Program of China
文摘Unmanned aerial vehicle(UAV)was introduced as a novel traffic device to collect road traffic information and its cruise route planning problem was considered.Firstly,a multi-objective optimization model was proposed aiming at minimizing the total cruise distance and the number of UAVs used,which used UAV maximum cruise distance,the number of UAVs available and time window of each monitored target as constraints.Then,a novel multi-objective evolutionary algorithm was proposed.Next,a case study with three time window scenarios was implemented.The results show that both the total cruise distance and the number of UAVs used continue to increase with the time window constraint becoming narrower.Compared with the initial optimal solutions,the optimal total cruise distance and the number of UAVs used fall by an average of 30.93% and 31.74%,respectively.Finally,some concerns using UAV to collect road traffic information were discussed.
文摘With technological advancements in 6G and Internet of Things(IoT), the incorporation of Unmanned Aerial Vehicles (UAVs) and cellularnetworks has become a hot research topic. At present, the proficient evolution of 6G networks allows the UAVs to offer cost-effective and timelysolutions for real-time applications such as medicine, tracking, surveillance,etc. Energy efficiency, data collection, and route planning are crucial processesto improve the network communication. These processes are highly difficultowing to high mobility, presence of non-stationary links, dynamic topology,and energy-restricted UAVs. With this motivation, the current research paperpresents a novel Energy Aware Data Collection with Routing Planning for6G-enabled UAV communication (EADCRP-6G) technique. The goal of theproposed EADCRP-6G technique is to conduct energy-efficient cluster-baseddata collection and optimal route planning for 6G-enabled UAV networks.EADCRP-6G technique deploys Improved Red Deer Algorithm-based Clustering (IRDAC) technique to elect an optimal set of Cluster Heads (CH) andorganize these clusters. Besides, Artificial Fish Swarm-based Route Planning(AFSRP) technique is applied to choose an optimum set of routes for UAVcommunication in 6G networks. In order to validated whether the proposedEADCRP-6G technique enhances the performance, a series of simulationswas performed and the outcomes were investigated under different dimensions.The experimental results showcase that the proposed model outperformed allother existing models under different evaluation parameters.
基金Project(2009AA11Z220)supported by National High Technology Research and Development Program of ChinaProjects(61070112,61070116)supported by the National Natural Science Foundation of China+1 种基金Project(2012LLYJTJSJ077)supported by the Ministry of Public Security of ChinaProject(KYQD14003)supported by Tianjin University of Technology and Education,China
文摘Unmanned aerial vehicle(UAV)was introduced to take road segment traffic surveillance.Considering the limited UAV maximum flight distance,UAV route planning problem was studied.First,a multi-objective optimization model of planning UAV route for road segment surveillance was proposed,which aimed to minimize UAV cruise distance and minimize the number of UAVs used.Then,an evolutionary algorithm based on Pareto optimality technique was proposed to solve multi-objective UAV route planning problem.At last,a UAV flight experiment was conducted to test UAV route planning effect,and a case with three scenarios was studied to analyze the impact of different road segment lengths on UAV route planning.The case results show that the optimized cruise distance and the number of UAVs used decrease by an average of 38.43% and 33.33%,respectively.Additionally,shortening or extending the length of road segments has different impacts on UAV route planning.
文摘Automated Guided Vehicles(AGVs)have been introduced into various applications,such as automated warehouse systems,flexible manufacturing systems,and container terminal systems.However,few publications have outlined problems in need of attention in AGV applications comprehensively.In this paper,several key issues and essential models are presented.First,the advantages and disadvantages of centralized and decentralized AGVs systems were compared;second,warehouse layout and operation optimization were introduced,including some omitted areas,such as AGVs fleet size and electrical energy management;third,AGVs scheduling algorithms in chessboardlike environments were analyzed;fourth,the classical route-planning algorithms for single AGV and multiple AGVs were presented,and some Artificial Intelligence(AI)-based decision-making algorithms were reviewed.Furthermore,a novel idea for accelerating route planning by combining Reinforcement Learning(RL)andDijkstra’s algorithm was presented,and a novel idea of the multi-AGV route-planning method of combining dynamic programming and Monte-Carlo tree search was proposed to reduce the energy cost of systems.
基金supported by National Natural Science Foundation of China (No.60474059)Hi-tech Research and Development Program of China (863 Program,No.2006AA04Z160).
文摘Vehicle routing problem in distribution (VRPD) is a widely used type of vehicle routing problem (VRP), which has been proved as NP-Hard, and it is usually modeled as single objective optimization problem when modeling. For multi-objective optimization model, most researches consider two objectives. A multi-objective mathematical model for VRP is proposed, which considers the number of vehicles used, the length of route and the time arrived at each client. Genetic algorithm is one of the most widely used algorithms to solve VRP. As a type of genetic algorithm (GA), non-dominated sorting in genetic algorithm-Ⅱ (NSGA-Ⅱ) also suffers from premature convergence and enclosure competition. In order to avoid these kinds of shortage, a greedy NSGA-Ⅱ (GNSGA-Ⅱ) is proposed for VRP problem. Greedy algorithm is implemented in generating the initial population, cross-over and mutation. All these procedures ensure that NSGA-Ⅱ is prevented from premature convergence and refine the performance of NSGA-Ⅱ at each step. In the distribution problem of a distribution center in Michigan, US, the GNSGA-Ⅱ is compared with NSGA-Ⅱ. As a result, the GNSGA-Ⅱ is the most efficient one and can get the most optimized solution to VRP problem. Also, in GNSGA-Ⅱ, premature convergence is better avoided and search efficiency has been improved sharply.
文摘The vehicle routing problem(VRP)is a typical discrete combinatorial optimization problem,and many models and algorithms have been proposed to solve the VRP and its variants.Although existing approaches have contributed significantly to the development of this field,these approaches either are limited in problem size or need manual intervention in choosing parameters.To solve these difficulties,many studies have considered learning-based optimization(LBO)algorithms to solve the VRP.This paper reviews recent advances in this field and divides relevant approaches into end-to-end approaches and step-by-step approaches.We performed a statistical analysis of the reviewed articles from various aspects and designed three experiments to evaluate the performance of four representative LBO algorithms.Finally,we conclude the applicable types of problems for different LBO algorithms and suggest directions in which researchers can improve LBO algorithms.
基金Supported by the National Natural Science Foundation of China(No.51565036)
文摘As a new variant of vehicle routing problem( VRP),a finished vehicle routing problem with time windows in finished vehicle logistics( FVRPTW) is modeled and solved. An optimization model for FVRPTW is presented with the objective of scheduling multiple transport routes considering loading constraints along with time penalty function to minimize the total cost. Then a genetic algorithm( GA) is developed. The specific encoding and genetic operators for FVRPTW are devised.Especially,in order to accelerate its convergence,an improved termination condition is given. Finally,a case study is used to evaluate the effectiveness of the proposed algorithm and a series of experiments are conducted over a set of finished vehicle routing problems. The results demonstrate that the proposed approach has superior performance and satisfies users in practice. Contributions of the study are the modeling and solving of a complex FVRPTW in logistics industry.
基金Supported by the National Natural Science Foundation of China(No.51565036)。
文摘With the challenge of great growing of transport diversity for the automobile enterprises, the heterogeneous vehicle routing problem with multiple depots, multiple types of finished vehicles and multiple types of transport vehicles in finished vehicle logistics(HVRPMD) is modelled and solved. A multi-objective optimization model for HVRPMD is presented considering loading constraints to minimize the total cost and minimize the number of transport vehicles. Then a hybrid heuristic algorithm based on genetic algorithm and particle swarm optimization(GA-PSO) is developed. Moreover, a case study is used to evaluate the effectiveness of this algorithm. By comparing the GA-PSO algorithm with the traditional GA algorithm, the simulation results demonstrate the proposed GA-PSO algorithm is able to better support the HVRPMD problem in practice. Contributions of the paper are the modelling and solving of a complex HVRPMD in logistics industry.
文摘As the proliferation and development of automated container terminal continue,the issues of efficiency and safety become increasingly significant.The container yard is one of the most crucial cargo distribution centers in a terminal.Automated Guided Vehicles(AGVs)that carry materials of varying hazard levels through these yards without compromising on the safe transportation of hazardous materials,while also maximizing efficiency,is a complex challenge.This research introduces an algorithm that integrates Long Short-Term Memory(LSTM)neural network with reinforcement learning techniques,specifically Deep Q-Network(DQN),for routing an AGV carrying hazardous materials within a container yard.The objective is to ensure that the AGV carrying hazardous materials efficiently reaches its destination while effectively avoiding AGVs carrying non-hazardous materials.Utilizing real data from the Meishan Port in Ningbo,Zhejiang,China,the actual yard is first abstracted into an undirected graph.Since LSTM neural network can efficiently conveys and represents information in long time sequences and do not causes useful information before long time to be ignored,a two-layer LSTM neural network with 64 neurons per layer was constructed for predicting the motion trajectory of AGVs carrying non-hazardous materials,which are incorporated into the map as background AGVs.Subsequently,DQN is employed to plan the route for an AGV transporting hazardous materials,aiming to reach its destination swiftly while avoiding encounters with other AGVs.Experimental tests have shown that the route planning algorithm proposed in this study improves the level of avoidance of hazardous material AGV in relation to non-hazardous material AGVs.Compared to the method where hazardous material AGV follow the shortest path to their destination,the avoidance efficiency was enhanced by 3.11%.This improvement demonstrates potential strategies for balancing efficiency and safety in automated terminals.Additionally,it provides insights for designing avoidance schemes for autonomous driving AGVs,offering solutions for complex operational environments where safety and efficient navigation are paramount.
基金supported by the National Natural Science Foundation of China and Zhejiang Joint Fund for the Integration of Industrialization and Informatization(Nos.U1809212 and U1909206)the Fundamental Research Funds for the Zhejiang Provincial Universities(No.2021XZZX014)the National Natural Science Foundation of China(No.62088102)。
文摘This paper describes a route planner that enables an autonomous underwater vehicle to selectively complete part of the predetermined tasks in the operating ocean area when the local path cost is stochastic.The problem is formulated as a variant of the orienteering problem.Based on the genetic algorithm(GA),we propose the greedy strategy based GA(GGA)which includes a novel rebirth operator that maps infeasible individuals into the feasible solution space during evolution to improve the efficiency of the optimization,and use a differential evolution planner for providing the deterministic local path cost.The uncertainty of the local path cost comes from unpredictable obstacles,measurement error,and trajectory tracking error.To improve the robustness of the planner in an uncertain environment,a sampling strategy for path evaluation is designed,and the cost of a certain route is obtained by multiple sampling from the probability density functions of local paths.Monte Carlo simulations are used to verify the superiority and effectiveness of the planner.The promising simulation results show that the proposed GGA outperforms its counterparts by 4.7%–24.6%in terms of total profit,and the sampling-based GGA route planner(S-GGARP)improves the average profit by 5.5%compared to the GGA route planner(GGARP).