The modern flexible workshop is characterized by the diversification of AGV equipment and a large number of production tasks. The traditional multi-AGV collaborative handling method has been unable to meet the needs of modern users who pursue high efficiency and high precision. The knowledge graph is an important part of the knowledge management field which has great advantages in creating an efficient and interconnected knowledge base. The knowledge graph can manage the performance parameters and other information of AGV equipment in modern flexible workshops efficiently. In order to solve the problem of low collaboration efficiency of AGV in flexible workshops, initially, this paper constructs the AGV performance parameter spectrum based on the knowledge graph in a combination of top-down and bottom-up methods. Then, based on the experience of factory experts, this paper constructs a multi-AGV collaborative handling paradigm and maps the paradigm to the performance parameter spectrum of the workpiece handling AGV to form an AGV collaborative chain spectrum. Secondly, this paper constructs a multi-AGV collaborative handling link network topology graph using a complex network to dynamically simulate the AGV and station location of the flexible workshop. We query relevant performance data from the AGV performance parameter spectrum and match the AGV collaborative chain to the production task. Finally, we aim to minimize the completion time of the handling task and realize the AGV collaborative handling optimization problem through linear programming to improve the production efficiency of modern flexible workshops.

This paper investigates the automatic guided vehicle (AGV) route planning problem. AGVs perform simultaneous pickup and delivery services to workstations at specified times. An AGV route planning model with minimum transportation cost as the optimization objective is constructed. We add a time window constraint to the model to ensure the overall operational efficiency of the workshop. Meanwhile, a hybrid genetic algorithm with improved variable neighborhood search (GA-VNS) is designed to solve the problem. The algorithm combines the strong local search ability of VNS algorithm to optimize GA. We redesigned the coding method of chromosomes to generate chromosomes that meet the needs of optimization. Five types of neighborhood structures are also designed to improve the algorithm’s optimality seeking ability. We designed two sets of experiments for the characteristics of the problem. The experiments test the example in the literature and the actual AGV logistics transportation data of a workshop. The algorithm compares experimental data with other algorithms to verify the effectiveness and applicability of the proposed algorithm.

For the problem of collaborative decision-making, we propose a multi-agent deep reinforcement learning collaborative behavior decision-making algorithm. Firstly, a discrete state space and a greedy strategy-based action space are established in the context of multi- agent collaborative attack, the conditions for successful collaborative siege are given for the requirements of rapidity and collocation. Secondly, the Markov Decision Process (MDP) framework is established based on the multi-agent collaborative behavior decision algorithm, we introduce the experience replay to train the neural network using gradient descent. Finally, a centralized training and distributed execution architecture is used to complete the training of collaborative behavioral decision making, in which the agents share the same strategy and execute actions independently. The simulation shows that the deep reinforcement learning algorithm is able to realize the multi-agent collaborative decision. It can be placed in a real environment.

The development of the intelligent transportation system has the potential to improve traffic management considerably. This paper research the car-following control of the autonomous vehicle in high way scenario. The given traditional car-following model does not consider the lateral lane change of the leader vehicle; Besides, the traditional control directly takes the related motion in the platoon of the leader vehicle as the system input of the following vehicle. But this paper combines the lateral and longitudinal movement of the vehicle as to the following control method. In addition, vehicle communication is taken as the way of platoon exchange between vehicles. Therefore, considering the influence of communication delay on the following control of vehicle platoon. The relevant simulation is carried out through Matlab/Simulink.

With the arrival of the Internet of Things, many fragmented intelligent terminals unload data to the edge cloud for computing. Based on the background of the vehicle platooning assisted by the edge cloud server, this paper conducted the following research on the problem of computing task offloading: First, considering the limited heterogeneous network resources of the Internet of Vehicles, the limited computing resources allocated by the edge cloud server for the vehicle platoon and member vehicle onboard computing unit, and the different delay constraints of the computing tasks, a computation offloading model was established with the optimization objective of reducing the total energy consumption of the platooning. Second, this paper used the proposed extended adaptive large neighbourhood search (EALNS) algorithm to optimize the offloading decision of computing tasks and used a method that enables computing tasks to be completed within the time delay constraint to optimize the allocation of computing resources. Finally, the EALNS and the generalized Benders decomposition algorithm were compared for energy optimization experiments. The experimental results verified the EALNS algorithm's effectiveness in optimizing the platooning's total energy consumption in the task offloading decision-making process.

The logistics distribution link in the modern logistics industry is the primary stumbling block to the industry’s development, as well as the terminal link for logistics activities. A well-planned vehicle routing scheme and a well-packaged customer’s goods can significantly reduce logistics delivery time, increase vehicle efficiency, and serve as a valuable reference for lowering logistics delivery costs. This paper analyzes the requirements for modern logistics distribution and develops a mathematical model aimed at achieving the shortest vehicle path, the lowest penalty cost associated with waiting time, and the highest packing utilization rate possible. Then, it solves the 2L-CVRPTW problem using a hybrid algorithm that incorporates an improved ant colony algorithm and a heuristic packing algorithm based on a minimum waste priority strategy. Finally, it demonstrates the effectiveness of the proposed algorithm using Solomon standard calculation examples and the comparison of solution results.

In order to increase the number of parking spaces, AGV (automated guided vehicle) intelligent parking lot sets the channel as a two-way single lane. In this paper, a general parking space allocation model is proposed to solve the problem that parking AGVs are prone to fall into deadlock in two-way single lane, and a conflict probability calculation model for AGV paths is further designed. By planning and allocating the target parking spaces of vehicles before the route planning, the potential deadlocks can be avoided reasonably. According to the conflict probability calculation model proposed above, the conflict probability of parking spaces sequence calculated by genetic algorithm is lower than serial number sequence method, from near to far method and alternate allocation method. The simulation results show that the conflict probability is positively correlated with the total transportation time of AGV intelligent parking lot. With the increase of parking AGVs number, it begins obvious that reducing conflict probability to improve the transportation efficiency of AGV intelligent parking lot. Therefore, reasonable planning and allocating the target parking spaces of vehicles can effectively improve the transportation efficiency of AGV intelligent parking lot.

The virtual AGV fully automatic parking system is theoretically researched based on the parking management problems of traditional parking lots such as shortage of parking spaces, poor service quality, and low satisfaction. In this paper, a virtual intelligent parking system based on the signal request mechanism is designed. In theoretical research, corresponding solutions are proposed for the selection of parking spaces, the path planning of the parking AGV and the deadlock processing of the AGV. The selection mechanism of free parking spaces is based on the principle of proximity, path planning is based on Dijkstra's algorithm, and the deadlock conflict resolution method is based on the signal request mechaLnism. The core part is the deadlock conflict processing of intersection nodes. Based on the original priority of transportation tasks, this paper takes into consideration factors such as remaining distance, transportation type, waiting time, time peaks. This paper introduces a new type of dynamic priority which effectively improves the efficiency of solving the backlog of parking AGV caused by deadlock conflicts.

In actual transportation processes, besides time windows requirements, waiting departure time caused by fixed schedules, also has an important influence on optimal transport scheme for multimodal transport. In order to choose, scientifically and rationally, routes of multimodal transport network and modes of transport, an optimal route selection model is established for minimizing total costs under constraints of mixed time windows. Considering the optimization efficiency brought by the chicken rank system, the chicken swarm optimization (CSO) is used to solve relevant examples with schedule constraints and no limited schedule. Optimization results show that under same time window constraints, costs with schedule constraints does not increase comparing that with no schedule constraints. In the result, effects of time window constraints and fixed schedule should be fully considered in actual determination of multimodal transport scheme.

Due to complexity of the train energy absorbers, multiple parameters must be considered in their structure optimization. However, the traditional optimization design methods lack an overall point of view for structure analysis and, therefore, cannot deal with multi-objective problems comprehensively. In this paper, a cooperative optimization platform is proposed to establish the design and optimization process, using a modular modeling system for the high speed train collision absorber. Playing the role of each module, the platform can have a real-time grasp of the entire optimization design process. In addition, with the help of the powerful file data processing system and driving engine of computer, the whole optimization design process is automated, which improves data analysis and post-processing ability. Therefore, the optimization platform can realize automation of optimization design process, shorten optimization time and reduce analysis costs. This platform can achieve the goal of collaborative optimization.

We herein build a smart parking system for large-scale underground parking lot in China, and deal with scheduling problems for multiple automatic guided vehicles (AGVs). In previous studies, multiple AGVs usually were scheduled in warehouse system, workshop system, etc. There was little report about AGVs in smart parking. In underground parking lot, designing maximum layout of parking space led to limited and double pathway for AGVs. Therefore, we proposed a dynamic time-window based on scheduling method (DTWS for short). In our DTWS, each AGV can dynamically adjust the path according to a time window, and thus implement the conflict-free pathway of AGVs. Finally, the experimental results showed that the our method solved the scheduling problems such as deadlock of multiple AGVs, and our parking system had an improved performance.

We herein propose an evolutionary multi-agent system (EMAS for short) to build an ensemble of surrogates for prediction. In our EMAS, we employ six kinds of basic surrogates, including Gaussian process, Kriging model, polynomial response surface, radial basis function, radial basis function neural network, and support vector regression machine. We define each surrogate as one agent and co-evolve parameters of basic surrogates to obtain the evolutionary weighted average surrogate, where sample cross-validation errors evaluate an ensemble of surrogates. The preliminary results from predicting the benchmark function with high dimension showed the effectiveness of our EMAS for an ensemble of surrogates.

We herein tackled concurrent design of machines layout and automated guided vehicle (AGV) planning in a workshop, and proposed a co-evolutionary framework for the whole design with tandem AGVs system. Our objective is to reduce the material transporting costs in the manufacturing process and realize the flexible reconfigurable. Firstly, we divide the whole workshop into several regions (or groups), and each region is a subsystem of cooperative co-evolutionary (CC) framework (Potter's CC model). Then, we employ a typical evolutionary algorithm, such as genetic algorithm, to solve the machine layout with AGV planning in each region. Also, we use a group generator to regroup the regions for improving the design. The preliminary experimental results from an example with ten parts, 30 machines and three loops in a workshop showed the effectiveness of our framework compared with noncoevolutionary framework.

In this paper, we propose a block nonlocal total variation (TV) regularization method for image restoration. We extend the existing nonlocal TV method in two aspects: first, some block nonlocal operators are introduced to extend the point-based nonlocal diffusion as a block-based nonlocal diffusion process; second, the weighting function in the nonlocal method can be adaptively determined by the cost functional itself. The proposed method is derived from a block-based maximum a posteriori estimation. By the assumption of the self-similarity of small patches, we formulate a regularization term as a log-likelihood functional of a mixture model. To optimize this regularization term efficiently, we employ the idea of the expectation maximum algorithm and give a variational framework to propose a block-based nonlocal TV regularization. The weighting function occurring in our model can be regarded as a probability of the similarity for image patches, and it can be updated adaptively according to the newest estimation. In addition, we mathematically prove the existence of a minimizer for one of the proposed models. Compared with the nonlocal TV method, numerical results show that our method can greatly improve the quality of the restored images, especially under heavy noise.

This paper proposed a co-evolutionary methodology to optimize the layout of a practical tandem automated guided vehicles (AGV) workshop aiming to reduce the costs for material transporting in manufacturing process. This methodology provided a fresh line to address the machine assignment, internal and external loop layout, as well as the loops arrangement on the floor synthetically, the transfer station setting was also considered. This methodology is not like the previous method that solved these contents in sequence. Genetic algorithm (GA) was herein applied for the iteration after these contents were ascertained. A mathematical model was also established for this methodology. The optimization result illustrated the efficiency of proposed co-evolutionary methodology in decreasing the material transporting costs comparing with the non co-evolutionary method. The workshop layout design can apply our methodology, which involved an overall consideration, as guidance.

In this paper, we propose a Near Field Pairing Service system called NFV to enable group communication. This system leverages common mobile device, e.g., smartphones, equipped with motion sensors. A group of people can put their mobile devices on the table and setup a secure connection via a vibration-propagation based key delivery scheme. In this way, NFV is able to transmit a secure connection key among a group of trusted mobile devices. Based on this key, group users establish a confidential communication channel between their devices. NFV achieves group devices pairing without the complex operations needed in prior works. We implemented NFV using off-the-shelf Android smartphones. The experimental results shows the efficiency and security of our system.

We herein try to schedule multiple AGVs (Automated Guided Vehicles) in real time with two-phase strategy in the flexible manufacturing workshops. This study considers the impact of running time, vehicle stopping and turning of AGVs, and deals with static workshop scheduling, real-time workshop scheduling with time-window based micro genetic algorithm. And we present a two-stage scheduling strategy for offline shortest path library generation and online optimal scheduling scheme generation. The preliminary experimental results showed the efficiency and stability of the proposed strategy and algorithm for Multiple AGVs system.

We herein model workshop layout problem as quadratic assignment problem (QAP), which is an important NP-hard problem in logistics system. Moreover, we proposed an effective algorithm hybridizing invasive weed optimization (IWO for short) with the simulated annealing (SA) for solving this problem. Our basic idea is to employ IWO for providing diversity to explore solution, and use metropolis criterion of SA to provide a better direction. In our algorithm, we employed an offspring generation rule with disturbance, and used random-keys encoding to produce new solution for solving QAP. We also designed a harmonic coefficient to improve the fluctuation problem effectively. The computational results from equipment layout problems validated our algorithm.

Mobile sink has been a significant means to prolong the lifetime of Wireless Multimedia Sensor Networks (WMSNs). However, the mobility of the sink makes the modeling of the WMSNs lifetime a more complex issue. Considering the new properties introduced by a mobile sink, this paper proposed a novel model to define the lifetime of WMSNs with a mobile sink based on energy by taking into account the heterogeneity, network delay, delay jitter, data rate, and data accuracy. Tunable coefficients were introduced into the model for the balance of energy consumption and functions in the network. Both theoretical analysis and numerical simulation validate the correctness and effectiveness of the proposed model.

In this paper, we use complex network theory to analyze the evolving topology of wireless sensor networks (WSNs). Based on the BA model, we propose a novel complex network model, i.e., Neighborhood Log-on and Log-off model with energy awareness (NLL-E). NLL-E assumes locally preferential attachment, which exists in many complex networks. We further consider node addition and invalidation in topology evolvement, and add compensation mechanism for network robustness. The statistical properties and dynamics of NLL-E are analytically studied. Numerical simulations indicate that, comparing with BA, NLL-E has decreased average path length and increased network connectivity.