Real-time UAV path planning based on LSTM network

To address the shortcomings of single-step decision making in the existing deep reinforcement learning based unmanned aerial vehicle(UAV)real-time path planning problem,a real-time UAV path planning algorithm based on long shortterm memory(RPP-LSTM)network is proposed,which combines the memory characteristics of recurrent neural network(RNN)and the deep reinforcement learning algorithm.LSTM networks are used in this algorithm as Q-value networks for the deep Q network(DQN)algorithm,which makes the decision of the Q-value network has some memory.Thanks to LSTM network,the Q-value network can use the previous environmental information and action information which effectively avoids the problem of single-step decision considering only the current environment.Besides,the algorithm proposes a hierarchical reward and punishment function for the specific problem of UAV real-time path planning,so that the UAV can more reasonably perform path planning.Simulation verification shows that compared with the traditional feed-forward neural network(FNN)based UAV autonomous path planning algorithm,the RPP-LSTM proposed in this paper can adapt to more complex environments and has significantly improved robustness and accuracy when performing UAV real-time path planning.

Improved Double Deep Q Network Algorithm Based on Average Q-Value Estimation and Reward Redistribution for Robot Path Planning

By integrating deep neural networks with reinforcement learning,the Double Deep Q Network(DDQN)algorithm overcomes the limitations of Q-learning in handling continuous spaces and is widely applied in the path planning of mobile robots.However,the traditional DDQN algorithm suffers from sparse rewards and inefficient utilization of high-quality data.Targeting those problems,an improved DDQN algorithm based on average Q-value estimation and reward redistribution was proposed.First,to enhance the precision of the target Q-value,the average of multiple previously learned Q-values from the target Q network is used to replace the single Q-value from the current target Q network.Next,a reward redistribution mechanism is designed to overcome the sparse reward problem by adjusting the final reward of each action using the round reward from trajectory information.Additionally,a reward-prioritized experience selection method is introduced,which ranks experience samples according to reward values to ensure frequent utilization of high-quality data.Finally,simulation experiments are conducted to verify the effectiveness of the proposed algorithm in fixed-position scenario and random environments.The experimental results show that compared to the traditional DDQN algorithm,the proposed algorithm achieves shorter average running time,higher average return and fewer average steps.The performance of the proposed algorithm is improved by 11.43%in the fixed scenario and 8.33%in random environments.It not only plans economic and safe paths but also significantly improves efficiency and generalization in path planning,making it suitable for widespread application in autonomous navigation and industrial automation.

Design of Aided Decision-Making Program for Prioritizing Construction Projects in Urban Road Network Planning

The importance and complexity of prioritizing construction projects (PCP) in urban road network planning lead to the necessity to develop an aided decision making program (ADMP). Cost benefit ratio model and stage rolled method are chosen as the theoretical foundations of the program, and then benefit model is improved to accord with the actuality of urban traffic in China. Consequently, program flows, module functions and data structures are designed, and particularly an original data structure of road ...

Specific Problems in the Planning and Development of Power Network in China

In light of the situation that the nationwide interconnection of power networks in China in the coming years will take shape, it is imperative to emphasize the importance of setting up rational power network configuration. Combined with the characteristics of regional power networks in China, problems in network planning that need to be solved are put forward in this paper, such as, the access of power plants to grid by layers and zones, the share of external power in the load of local network, the power network configuration study in-depth in planning and design stage, and enforcement of receiving-end power network trunk etc. The background of these problems and their countermeasures are also analyzed in the paper.

Reuse partitioning based frequency planning for two-hop cellular network

Following the principle of reuse partitioning, two new frequency planning schemes are proposed, the coverage-oriented scheme and the efficiency-oriented scheme, for the cellular system with two-hop fixed relay nodes （FRNs）. Compared with the effficiency-oriented scheme, the coverage-oriented scheme has higher reuse distances and is developed with emphasis on the coverage, while compared with the coverage-oriented scheme, the efficiency-oriented scheme has smaller reuse distances and is developed with emphasis on the spectral efficiency. Taking uplink as an example, both simplified analysis and intensive computer simulations are presented to offer comparisons among FRN enhanced systems with the proposed schemes, with a known channel-borrowing based frequency planning scheme and the conventional cellular system without relaying. Studies show that the FRN enhanced system with the coverage-oriented scheme provides the best coverage, while that with the efficiency-oriented scheme offers the highest area spectral efficiency.

Generative Adversarial Network Based Heuristics for Sampling-Based Path Planning

Sampling-based path planning is a popular methodology for robot path planning.With a uniform sampling strategy to explore the state space,a feasible path can be found without the complex geometric modeling of the configuration space.However,the quality of the initial solution is not guaranteed,and the convergence speed to the optimal solution is slow.In this paper,we present a novel image-based path planning algorithm to overcome these limitations.Specifically,a generative adversarial network(GAN)is designed to take the environment map(denoted as RGB image)as the input without other preprocessing works.The output is also an RGB image where the promising region(where a feasible path probably exists)is segmented.This promising region is utilized as a heuristic to achieve non-uniform sampling for the path planner.We conduct a number of simulation experiments to validate the effectiveness of the proposed method,and the results demonstrate that our method performs much better in terms of the quality of the initial solution and the convergence speed to the optimal solution.Furthermore,apart from the environments similar to the training set,our method also works well on the environments which are very different from the training set.

A hybrid particle swarm optimization approach with neural network and set pair analysis for transmission network planning

Transmission network planning (TNP) is a large-scale, complex, with more non-linear discrete variables and the multi-objective constrained optimization problem. In the optimization process, the line investment, network reliability and the network loss are the main objective of transmission network planning. Combined with set pair analysis (SPA), particle swarm optimization (PSO), neural network (NN), a hybrid particle swarm optimization model was established with neural network and set pair analysis for transmission network planning (HPNS). Firstly, the contact degree of set pair analysis was introduced, the traditional goal set was converted into the collection of the three indicators including the identity degree, difference agree and contrary degree. On this bases, using shi(H), the three objective optimization problem was converted into single objective optimization problem. Secondly, using the fast and efficient search capabilities of PSO, the transmission network planning model based on set pair analysis was optimized. In the process of optimization, by improving the BP neural network constantly training so that the value of the fitness function of PSO becomes smaller in order to obtain the optimization program fitting the three objectives better. Finally, compared HPNS with PSO algorithm and the classic genetic algorithm, HPNS increased about 23% efficiency than THA, raised about 3.7% than PSO and improved about 2.96% than GA.

Path Planning and Tracking for Vehicle Parallel Parking Based on Preview BP Neural Network PID Controller

In order to diminish the impacts of extemal disturbance such as parking speed fluctuation and model un- certainty existing in steering kinematics, this paper presents a parallel path tracking method for vehicle based on pre- view back propagation （BP） neural network PID controller. The forward BP neural network can adjust the parameters of PID controller in real time. The preview time is optimized by considering path curvature, change in curvature and road boundaries. A fuzzy controller considering barriers and different road conditions is built to select the starting po- sition. In addition, a kind of path planning technology satisfying the requirement of obstacle avoidance is introduced. In order to solve the problem of discontinuous curvature, cubic B spline curve is used for curve fitting. The simulation results and real vehicle tests validate the effectiveness of the proposed path planning and tracking methods.

A Novel MILP Model Based on the Topology of a Network Graph for Process Planning in an Intelligent Manufacturing System

Intelligent process planning(PP)is one of the most important components in an intelligent manufacturing system and acts as a bridge between product designing and practical manufacturing.PP is a nondeterministic polynomial-time(NP)-hard problem and,as existing mathematical models are not formulated in linear forms,they cannot be solved well to achieve exact solutions for PP problems.This paper proposes a novel mixed-integer linear programming(MILP)mathematical model by considering the network topology structure and the OR nodes that represent a type of OR logic inside the network.Precedence relationships between operations are discussed by raising three types of precedence relationship matrices.Furthermore,the proposed model can be programmed in commonly-used mathematical programming solvers,such as CPLEX,Gurobi,and so forth,to search for optimal solutions for most open problems.To verify the effectiveness and generality of the proposed model,five groups of numerical experiments are conducted on well-known benchmarks.The results show that the proposed model can solve PP problems effectively and can obtain better solutions than those obtained by the state-ofthe-art algorithms.

Distributed Contact Plan Design for Multi-Layer Satellite-Terrestrial Network

In multi-layer satellite-terrestrial network, Contact Graph Routing(CGR) uses the contact information among satellites to compute routes. However, due to the resource constraints in satellites, it is extravagant to configure lots of the potential contacts into contact plans. What's more, a huge contact plan makes the computing more complex, which further increases computing time. As a result, how to design an efficient contact plan becomes crucial for multi-layer satellite network, which usually has a large scaled topology. In this paper, we propose a distributed contact plan design scheme for multi-layer satellite network by dividing a large contact plan into several partial parts. Meanwhile, a duration based inter-layer contact selection algorithm is proposed to handle contacts disruption problem. The performance of the proposed design was evaluated on our Identifier/Locator split based satellite-terrestrial network testbed with 79 simulation nodes. Experiments showed that the proposed design is able to reduce the data delivery delay.

Analysis of effect factors-based stochastic network planning model

Looking at all the indeterminate factors as a whole and regarding activity durations as independent random variables, the traditional stochastic network planning models ignore the inevitable relationship and dependence among activity durations when more than one activity is possibly affected by the same indeterminate factors. On this basis of analysis of indeterminate effect factors of durations, the effect factors-based stochastic network planning （EFBSNP） model is proposed, which emphasizes on the effects of not only logistic and organizational relationships, but also the dependent relationships, due to indeterminate factors among activity durations on the project period. By virtue of indeterminate factor analysis the model extracts and describes the quantitatively indeterminate effect factors, and then takes into account the indeterminate factors effect schedule by using the Monte Carlo simulation technique. The method is flexible enough to deal with effect factors and is coincident with practice. A software has been developed to simplify the model-based calculation, in VisualStudio.NET language. Finally, a case study is included to demonstrate the applicability of the proposed model and comparison is made with some advantages over the existing models.

Integration of Neural Networks and Cellular Automata for Urban Planning

This paper presents a new type of cellular automa ta (CA) model for the simulation of alternative land development using neural netw orks for urban planning. CA models can be regarded as a planning tool because th ey can generate alternative urban growth. Alternative development patterns can b e formed by using different sets of parameter values in CA simulation. A critica l issue is how to define parameter values for realistic and idealized simulation . This paper demonstrates that neural networks can simplify CA models but genera te more plausible results. The simulation is based on a simple three-layer netw ork with an output neuron to generate conversion probability. No transition rule s are required for the simulation. Parameter values are automatically obtained f rom the training of network by using satellite remote sensing data. Original tra ining data can be assessed and modified according to planning objectives. Altern ative urban patterns can be easily formulated by using the modified training dat a sets rather than changing the model.

Application and Realization of Hierarchical Network Planning Based on Web

Making use of Microsoft Visual Studio. NET platform, hierarchical network planning is realized in working procedure time-optimization of the construction by TBM, and hierarchical network graph of the construction by TBM is drawn based on browser. Then the theory of system realization is discussed, six components of system that can be reused are explained emphatically. The realization of hierarchical network panning in Internet provides available guarantee for controlling rate of progress in large-scale or middle-sized projects. Key words Web - network graph - hierarchical network planning CLC number TU721 Biography: WU Shi-jing (1963-), male, Professor, research direction: equipments management engineering, mechatronics, state monitoring and malfunction diagnostics of machine and electronics equipments.

Sensor planning method for visual tracking in 3D camera networks

Most sensors or cameras discussed in the sensor network community are usually 3D homogeneous, even though their2 D coverage areas in the ground plane are heterogeneous. Meanwhile, observed objects of camera networks are usually simplified as 2D points in previous literature. However in actual application scenes, not only cameras are always heterogeneous with different height and action radiuses, but also the observed objects are with 3D features（i.e., height）. This paper presents a sensor planning formulation addressing the efficiency enhancement of visual tracking in 3D heterogeneous camera networks that track and detect people traversing a region. The problem of sensor planning consists of three issues：（i） how to model the 3D heterogeneous cameras;（ii） how to rank the visibility, which ensures that the object of interest is visible in a camera＇s field of view;（iii） how to reconfigure the 3D viewing orientations of the cameras. This paper studies the geometric properties of 3D heterogeneous camera networks and addresses an evaluation formulation to rank the visibility of observed objects. Then a sensor planning method is proposed to improve the efficiency of visual tracking. Finally, the numerical results show that the proposed method can improve the tracking performance of the system compared to the conventional strategies.

Neural network and genetic algorithm based global path planning in a static environment

Mobile robot global path planning in a static environment is an important problem. The paper proposes a method of global path planning based on neural network and genetic algorithm. We constructed the neural network model of environmental information in the workspace for a robot and used this model to establish the relationship between a collision avoidance path and the output of the model. Then the two-dimensional coding for the path via-points was converted to one-dimensional one and the fitness of both the collision avoidance path and the shortest distance are integrated into a fitness function. The simulation results showed that the proposed method is correct and effective.

3D multipath planning for UAV based on network graph

According to the characteristic and the requirement of multipath planning, a new multipath planning method is proposed based on network. This method includes two steps： the construction of network and multipath searching. The construction of network proceeds in three phases： the skeleton extraction of the configuration space, the judgment of the cross points in the skeleton and how to link the cross points to form a network. Multipath searching makes use of the network and iterative penalty method （IPM） to plan multi-paths, and adjusts the planar paths to satisfy the requirement of maneuverability of unmanned aerial vehicle （UAV）. In addition, a new height planning method is proposed to deal with the height planning of 3D route. The proposed algorithm can find multiple paths automatically according to distribution of terrain and threat areas with high efficiency. The height planning can make 3D route following the terrain. The simulation experiment illustrates the feasibility of the proposed method.

Distribution network planning based on shortest path

In order to form an algorithm for distribution network routing,an automatic routing method of distribution network planning was proposed based on the shortest path.The problem of automatic routing was divided into two steps in the method:the first step was that the shortest paths along streets between substation and load points were found by the basic ant colony algorithm to form a preliminary radial distribution network,and the second step was that the result of the shortest path was used to initialize pheromone concentration and pheromone updating rules to generate globally optimal distribution network.Cases studies show that the proposed method is effective and can meet the planning requirements.It is verified that the proposed method has better solution and utility than planning method based on the ant colony algorithm.

Correlation knowledge extraction based on data mining for distribution network planning

Traditional distribution network planning relies on the professional knowledge of planners,especially when analyzing the correlations between the problems existing in the network and the crucial influencing factors.The inherent laws reflected by the historical data of the distribution network are ignored,which affects the objectivity of the planning scheme.In this study,to improve the efficiency and accuracy of distribution network planning,the characteristics of distribution network data were extracted using a data-mining technique,and correlation knowledge of existing problems in the network was obtained.A data-mining model based on correlation rules was established.The inputs of the model were the electrical characteristic indices screened using the gray correlation method.The Apriori algorithm was used to extract correlation knowledge from the operational data of the distribution network and obtain strong correlation rules.Degree of promotion and chi-square tests were used to verify the rationality of the strong correlation rules of the model output.In this study,the correlation relationship between heavy load or overload problems of distribution network feeders in different regions and related characteristic indices was determined,and the confidence of the correlation rules was obtained.These results can provide an effective basis for the formulation of a distribution network planning scheme.

SHARING AND PLANNING OF DISTRIBUTED EQUIPMENT FOR NETWORKED MANUFACTURING

Efficient utilization of the equipment distributed in different enterprises and optimal allocation of these resources is an important concern for networked manufacturing. The third party based equipment sharing approach is put forward to optimize the utilization of distributed equipment for networked manufacturing; Taking advantage of the shared equipment offered by equipment providers by means of lease agreement, the third party carries out production by establishing networked virtual factory. Operational mechanism of the third party based equipment sharing is discussed, and characteristics of this approach in achieving resource allocation are analyzed. Shared equipment planning is formulated as an optimization problem with the objective of maximizing profits for equipment coordinator, a mathematical model for shared equipment planning is developed. Finally a case study is discussed to show the effectiveness of the planning model.

Coordinated Planning Transmission Tasks in Heterogeneous Space Networks:A Semi-Distributed Approach

This paper studies the coordinated planning of transmission tasks in the heterogeneous space networks to enable efficient sharing of ground stations cross satellite systems.Specifically,we first formulate the coordinated planning problem into a mixed integer liner programming(MILP)problem based on time expanded graph.Then,the problem is transferred and reformulated into a consensus optimization framework which can be solved by satellite systems parallelly.With alternating direction method of multipliers(ADMM),a semi-distributed coordinated transmission task planning algorithm is proposed,in which each satellite system plans its own tasks based on local information and limited communication with the coordination center.Simulation results demonstrate that compared with the centralized and fully-distributed methods,the proposed semi-distributed coordinated method can strike a better balance among task complete rate,complexity,and the amount of information required to be exchanged.