Top PDF A modified membrane-inspired algorithm based on particle swarm optimization for mobile robot path planning

A modified membrane-inspired algorithm based on particle swarm optimization for mobile robot path planning

A modified membrane-inspired algorithm based on particle swarm optimization for mobile robot path planning

To solve the multi-objective mobile robot path planning in a dangerous environment with dynamic obstacles, this paper proposes a modified membrane-inspired algorithm based on particle swarm optimization (mMPSO), which combines membrane systems with particle swarm optimization. In mMPSO, a dynamic double one-level membrane structure is intro- duced to arrange the particles with various dimensions and perform the communications between particles in different membranes; a point repair algorithm is presented to change an infeasible path into a feasible path; a smoothness algorithm is proposed to remove the redundant information of a feasible path; inspired by the idea of tightening the fishing line, a moving direction adjustment for each node of a path is introduced to enhance the algorithm performance. Extensive experiments conducted in different environments with three kinds of grid models and five kinds of obstacles show the effectiveness and practicality of mMPSO. Keywords: Membrane computing, evolutionary membrane computing, particle swarm optimization, variable dimensions, mobile robot path planning, membrane systems.
Show more

15 Read more

Hybrid fastslam approach using genetic algorithm and particle swarm optimization for robotic path planning

Hybrid fastslam approach using genetic algorithm and particle swarm optimization for robotic path planning

It should be a robot that is able to perform the designated tasks by itself without human intervention. It is scientifically known as artificial intelligent robot as it is able to ‘think’ before making decision and ‘act’ accordingly then. This research focuses on the autonomous mobile robot that is able to move into an unknown environment. The robot must ‘think’ how it should move. According to Pirahansiah et al. (2013), the challenges faced by autonomous robot are the environment factors, its capability to explore, navigate without any knowledge on the unknown environment and generates its own map for the environment. Another challenge faced by the robot is its capabilities to recognize its own position, landmark and any obstacles, and making decision based on the new environment data and is able to navigate through the environment without human intervention.
Show more

28 Read more

GA-based Global Path Planning for Mobile Robot Employing A* Algorithm

GA-based Global Path Planning for Mobile Robot Employing A* Algorithm

The global optimal path planning as the second factor for mobile robots have been a hotspot research area for many years, and several optimization methods such as potential field method [1-3], visibility graph method [2] , grid method [3-5], modified simulated annealing algorithm[9] and straight line path planning[10] have been developed to solve this problem. For the grid method, the main problem is how to determine the size of grid, which has great influence on both the representation precision for obstacles and the planned path. In recent years, many intelligent algorithms were applied to the path planning for mobile robots, such as fuzzy logic and reinforcement learning [6], neural network [7], genetic algorithm [8], and so on.
Show more

5 Read more

Path Planning of Mobile Robot by using Modified Optimized Potential Field Method

Path Planning of Mobile Robot by using Modified Optimized Potential Field Method

best solution and that solution called pbest. Particle swarm optimizer is also keeping track another value called the best value that get by particle in the neighbors of the particle. This location is called lbest. When one of particles takes all the population as its topological neighbors, the best value is a global best and it is named gbest [16]. The PSO algorithm is used to find the optimal parameters for the two PID controllers, one for controlling velocity and another for controlling angle of mobile robot. Figure (4) shows the block diagram of PID-PSO controller for the mobile robot.
Show more

5 Read more

A Cooperative Path Planning Algorithm for a Multiple Mobile Robot System in a Dynamic Environment

A Cooperative Path Planning Algorithm for a Multiple Mobile Robot System in a Dynamic Environment

The probabilistic roadmap method is also a popular path planning scheme for mobile robots. This method uses a sampling technique to discover a sparse representation of obstacles in a configuration space. Reference [9] makes use of a probabilistic roadmap to avoid occlusions of the target and any obstacles. The probabilistic roadmap method is easily implemented and can be applied to complex environments. However, this method may fail when the environment does not have a sufficient number of free points with which to construct a probabilistic map. There are also many heuristic methods that can be used for path planning, such as rapidly exploring random trees [10], neural networks [11], genetic algorithms [12], simulated annealing [13], ant colony optimization [14], particle swarm optimizer and fuzzy logic [15, 16]. These methods can yield feasible schemes; however, their optimality cannot be assured with any of the above-mentioned methods.
Show more

13 Read more

Development of Path Planning Algorithm Using Probabilistic Roadmap Based on Modified Ant Colony Optimization

Development of Path Planning Algorithm Using Probabilistic Roadmap Based on Modified Ant Colony Optimization

Global path planning starts from 1980 till these days and many algorithms have been proposed by researchers. Research leads to improve global planning year by year. At the beginning, path planning was focusing on finding path to goal only. Then it became bigger issue by not only reaching the goal but also considering optimization criteria [3]. There are a lot of algorithms used to solve path planning problems such as heuristic methods, meta-heuristic, and rando- mized method. A*, D*, and Dikstra can be considered as heuristic methods. A* algorithm is considered as a greedy, graph, and heuristic search algorithm that is able to find sub optimal but, not optimal path [4]. D* algorithm can be consi- dered as dynamic A* which is able to reform the path according to new informa- tion coming from sensors [5]. Meta-heuristic methods include particle swarm optimization (PSO), and ant colony optimization (ACO) [6]. Also there are in- telligent methods, like artificial potential field (APF), genetic algorithm (GA). APF is used in different types of robots where the field of forces is applied on robot. These forces are attractive force to goal and repulsive force from obstacles [7]. Randomized methods can be divided into two categories: rapidly exploring random tree (RRT) which is more suitable for dynamic environment and proba- bilistic roadmap (PRM) for static environment.
Show more

15 Read more

Application of Ant Colony Particle Swarm Optimization Algorithms in Path Planning of Security Robots

Application of Ant Colony Particle Swarm Optimization Algorithms in Path Planning of Security Robots

The actual working environment of a mobile robot is a realistic physical space, and the space handled by the path planning algorithm is an abstract space of the environment. Environment modeling is a very important link of the robot path planning. Through a large number of literature research [4], this paper uses the grid method to establish the model. The working environment is divided with grids of the same size and the obstacle model is constructed according to the working environment of the security robot.
Show more

7 Read more

Path Planning of Mobile Robot Based on Genetic Bee Colony Algorithm

Path Planning of Mobile Robot Based on Genetic Bee Colony Algorithm

Path planning of mobile robot is an important branch of robotics [1], which refers to the robot in work environment with obstacles. According to a certain performance indicators, the robot can recognize surroundings constantly to read the size, location and distance of the obstacles, and bypassing all the obstacles efficiently. Path planning of the robot began in 1970s, the methods of path planning are generally divided into two kinds, classical planning methods and heuristic planning methods. The classic planning methods: artificial potential field [2], grid method [3] and so on, which have been applied in path planning. However, the classic planning method is not so effective in complex environment, and it has some deficiencies, such as artificial field potential method is to control the speed, and it has the defect that the valuable information of the distribution is discarded in the obstacles. Grid method is the most widely method of path planning at present, and the main problem of grid method is how to determine the size of grid cell to make the experimental result best. Many researchers have proposed some improved methods, such as Castillo [4], who use genetic algorithm for multi-objective optimal path to resolve planning problems. Karaboga[5] is inspired by the foraging behavior of bees, the ABC algorithm is first proposed in 2005. It is a kind of intelligent stochastic optimization algorithm of simulating the bees to search the food source. Bees rely on their different division of the labor to achieve the exchange of the information, in order to find optimum solution. ABC algorithm has been applied to solve the practical problems [6], such as Taguchi [7] hybrid bee colony algorithm, Gbest-guided artificial bee colony[8], etc. In this paper, the genetic bee colony algorithm is proposed to solve the path planning of mobile robot.
Show more

6 Read more

Obstacle Avoidance Strategy of Intelligent Vehicle Path Planning Based on Particle Swarm Optimization

Obstacle Avoidance Strategy of Intelligent Vehicle Path Planning Based on Particle Swarm Optimization

At present, the common global path planning methods are Artificial Potential Field [2], Genetic Algorithm [3], Ant Colony Optimization [4], Particle Swarm Optimization [5- 6], etc. Particle Swarm Optimization (hereinafter referred to as PSO) has fast convergence speed, less parameters needed to be set, simple implementation and so on. Therefore, it was widely used in path planning. Qin Yuanqing et al. [7] firstly applied PSO to robot path planning problem. They adopted Dijkstra algorithm to search the shortest path in the MAKLINK graph, and then used PSO to conduct secondary path optimization, but the ability of global optimization of PSO is limited by secondary optimization. Nie Zhibin et al. [8] proposed non-linearized inertia weight to adjust the exploration and exploitation of PSO and combining PSO with simulated annealing algorithm to solve the problem of easily being trapped into local optimal solution. However, it didn’t explain how to choose parameters. Li Qing et al. [9] put forward the concept of "movable area", and proposed the obstacle avoidance strategy of setting the invalid particles in the process of iteration as global optimal solution. Through the adaptive adjustment of PSO parameters, good path planning results were obtained. However, if the neighboring particle of the invalid particles were suboptimal, the algorithm can easily get into local optimal. From the above analysis, the present study is mainly aimed at path search algorithm, and the study of algorithm has been basically matured. However, the research of obstacle avoidance strategy is less and the obstacle avoidance strategy will make the algorithm fall into local optimum.
Show more

7 Read more

An Efficient Path Planning Algorithm for Networked Robots using Modified Optimization Algorithm

An Efficient Path Planning Algorithm for Networked Robots using Modified Optimization Algorithm

(Das, Behera & Panigrahy, 2015) employed hybridization of improved particle swarm optimization (IPSO) in combination with an improved gravitational search algorithm (IGSA) for multi-robot to determine the optimal trajectory of the determined path in a clutter environment. IPSO possesses social characteristics which the proposed approach incorporates into the movement of IGSA. The developed hybridization IPSO-IGSA maintains the suitable equilibrium between searching and overuse due to the adoption of co-evolutionary techniques for enhancing the expedition of IGSA and particle positions combined with IPSO velocity together. The algorithm diminishes the maximum path length. It also reduces the time of arrival of each robot to its distinct destination in the environment. The robot generates individualistic decisions by implementing the proposed hybrid IPSO–IGSA to understand, and communicate with each other to identify the next positions from their current
Show more

6 Read more

Path Planning for Unmanned Underwater Vehicle Based on Improved Particle Swarm Optimization Method

Path Planning for Unmanned Underwater Vehicle Based on Improved Particle Swarm Optimization Method

Among those algorithm, PSO [6,16,19] as a global evolutionary algorithm is inspired by the behaviors of stochastic swarm such as flocks of birds and schools of fish, which mainly uses the swarm intelligent to achieve the goal of optimization. PSO has been applied to many domains with good performance such as system identification, neural networks and system control because of its characteristics of swarm intelligence, intrin- sic parallelism, and inexpensive computational. However, Due to a few adjustable pa- rameters such as population size, inertia weight and acceleration coefficients, PSO suf- fered from the premature convergence and trapping in local optimum problem, and even lack of population diversity. Several improved PSO algorithms, such as PSO- linearly inertia weight, PSO-fuzzy inertia weight and PSO-nonlinear inertia weight, had been proposed [8,19]. At present those methods have obtained with a certain perfor- mance improvement, but convergence and scarce exploration was also the frequent problems in the application process.
Show more

13 Read more

Implementation of an Improved Path Selection Algorithm Using Particle Swarm Optimization (PSO) Technique

Implementation of an Improved Path Selection Algorithm Using Particle Swarm Optimization (PSO) Technique

Abstract - This paper presents optimizing the routing process in MANET. The proposed work is about the mobile networks and based on DSDV protocol. Malicious node is detected by PSO technique. PSO is used for shortest path problem inspired by behavior of swarm of fishes or flocks of birds to find a good food place. In this paper, we have compared three parameters distance, delay and energy of the existing work and proposed work based on PSO technique that is an improved safe routing approach to transfer data from congestion free and attack safe path. This technique provides effectiveness in terms of energy and the time as well as provides a reliable route over the network.
Show more

6 Read more

Real-Time Path Planning and Navigation for a Web-Based Mobile Robot Using a Modified Ant Colony Optimization Algorithm

Real-Time Path Planning and Navigation for a Web-Based Mobile Robot Using a Modified Ant Colony Optimization Algorithm

3.3 Binocular vision-based localization In this paper, a modified model of stereo vision is presented to develop a more accurate algorithm for computing three-dimensional information from a stereo pair of images by modification of the stereo vision model, as shown in Fig. 4 [26]. Two cameras are separated by a distance in the -direction and both optical axes are parallel. For convenience, the coordinate system centered between two cameras is called the world coordinate system. The goal is to find the coordinates , , of the world point having corresponding points , and , in left and right images, respectively. From the similar triangles of imaging as shown in Figs. 4(a) and 4(b), we have
Show more

6 Read more

Robot Path Planning using Swarm Intelligence: A Survey

Robot Path Planning using Swarm Intelligence: A Survey

Swarm intelligence system can act in a coordinated way without the presence of an external coordinator. Swarm intelligence added a new property in artificial intelligence to study the collective behaviour and emergent properties of complex systems with in predefined environment[3]. In recent years a number of swarm based optimization techniques have been proposed among which we have discuss about the Particle swarm optimization(PSO), Ant colony optimization(ACO), Artificial bee colony optimization(ABC) and Firefly Algorithm(FA) in terms of robot path planning. Robot path planning is an important problem in navigation of mobile robots. The aim is to find an optimal and collision-free path from a predefined start position to a target point in a given environment. Generally, there are many paths for robot to reach the target, but in fact the best path is selected according to some guide line. These guide lines are: shortest path, least energy consuming or shortest time. The field robot path planning was launched at the middle of the 1960’s [4][5]. The problem of path planning is very active area of research. This problem is solved by many conventional methods such as Artificial Potential Field [6], Neural Network [7], Distance Wave Transform [8], A* algorithm [9], D* algorithm [10] and etc, proposed by previous researchers have changed and evolved to other variation of path planning approaches that is based on approaches categorized as artificial intelligence [11]. In computational complexity theory, path planning is classified as an NP complete problem [12]. That is, the computational time that is required to solve such problem increases dramatically (usually in an exponential rate) when the size (or dimension) of the problem increases.
Show more

8 Read more

A Mobile Robot Path Planning Based on Multiple Destination points

A Mobile Robot Path Planning Based on Multiple Destination points

The distance of initial node is mainly consideration of the connection between two points. If the connection between two points does not intersect any obstacle, or not in the obstacle, it can be indicated as a direct straight-line link between two points and the initial distance is the Euclidean distance; In contrast, if the two points can not be directly linked, the initial distance can be assumed infinite. For the two types of adjacency relationship problems solving, an initial distance matrix is established based on the same obstacle’s polygon vertices adjacency relationship and the different obstacles’ polygon vertices adjacency relationship [11]. However, the problem of the two types of adjacency relationships can be solved by judging all the vertex-linkage line of V intersecting with the obstacle polygon, with V being a set of all vertices of the obstacle polygons, together with the initial and final points, i.e., V  { v 1 , v 2 ,  , v i ,  , v n } . In addition, for the purpose of computing of the distance between vertices, an initial node distance matrix is established as E  R n  n , with its
Show more

7 Read more

Storage planning of automated pharmacy based on an improved adaptive chaotic particle swarm optimization algorithm

Storage planning of automated pharmacy based on an improved adaptive chaotic particle swarm optimization algorithm

[10]. X Zhao et al. studied the irregular storage problem of automated pharmacy, and put forward to a multi-objective reservoir allocation model to improve the storage efficiency and space utilization, and presented a two-level genetic algorithm to solve the above problem [11]. All the above researches laid theoretical foundations of our projects, however, the above methods with the traditional models could not describe the rationalized allocation of medicine storage in warehousing system better, and moreover, though the genetic algorithm achieved fruitful results of solving combinatorial optimization problems, due to the slow convergence speed and being easy to fall into local optimum of the genetic algorithm, it was urgent to explore new ways to solve optimization problems of storage spaces in automated warehouse system.
Show more

7 Read more

A particle swarm optimization-based algorithm for finding gapped motifs

A particle swarm optimization-based algorithm for finding gapped motifs

Similar to all stochastic algorithms, the performance of PSO+ partially depends on the initial solutions. The convergence of the algorithm can be significantly improved if at least one of the agents has an initial solution near the optimal solution. In this work we consider two strategies. The first strategy is to simply generate a set of random consensus. The second strategy is to randomly choose a subsequence from the input sequence as an initial solution. Although the first strategy would allow the maximum coverage, the probability that any randomly generated consensus is near the optimal solution is very low, as there are 4 l possible solutions for a motif of length l. For the second strategy, we assume that the actual binding site is closer to the consensus than to random sequences. Since there is usually about one binding site per sequence, it is very likely that some agents may select a binding site as an initial solution. More pre- cisely, assuming that the average sequence length is L and the motif length is l, the probability that a randomly selected sequence is a binding site is 1/(L − l + 1). Also because of the Check Shift step in the algorithm, a random solution that contains a large suffix or prefix of the binding site can often lead to the recovery of the real motif quickly. We usually allow a binding site to be shifted by two bases to its left and right, respectively. Therefore, each true binding site can provide up to 5 initial solutions that are similar to the real motif. For this reason, we suggest the minimum number of agents to be (L − l + 1)/5 to ensure a high convergence probability. In our experiments on both synthetic and real sequences, we have found that the second strategy usually leads to much faster convergence and therefore is implemented as the default option.
Show more

12 Read more

A Research Optimization of CMOS Analog Circuits using Modified Particle Swarm Algorithm

A Research Optimization of CMOS Analog Circuits using Modified Particle Swarm Algorithm

In this paper, a MPSO based framework is used for the perfect skill of a CMOS intensifier. The cream kind of the atom swarm improvement figuring and weighted system, is proposed to streamline the structure factors, for instance, MOS transistor size, power and meet the given detail. The structure central inspirations driving the CMOS circuits are considered as the cost most distant extents of the Modified Particle swarm movement figuring. The starting outcomes show that the proposed framework possibly meets the circuit structure subtleties what's more inspiration driving restriction the chip check. Regardless of the redirection based structure, the beat virtuoso expansions were done to engage the CMOS to circuit central center interests. It has been demonstrated that the structure of the CMOS circuit using the MPSO approach is advantageous separated and other procedure systems. The proposed system structure can reinforce the CMOS circuit shows up. Beginning now and into the not too expelled the MPSO estimation is a competent point of view for complex key IC structure.
Show more

6 Read more

A Modified Discrete Particle Swarm Optimization Algorithm for the Generalized Traveling Salesman Problem

A Modified Discrete Particle Swarm Optimization Algorithm for the Generalized Traveling Salesman Problem

The mDPSO algorithm proposed employs the destruction and construction procedure of the iterated greedy algorithm (IG) in its mutation phase. Its performance is enhanced by employing a population initialization scheme based on an NEH constructive heuristic for which some speed-up methods previously developed by authors are used for greedy node insertions. Furthermore, the mDPSO algorithm is hybridized with local search heuristics to achieve further improvements in the solution quality. To evaluate its performance, the mDPSO algorithm is tested on a set of benchmark instances with symmetric Euclidean distances ranging from 51 (11) to 1084 (217) nodes (clusters) from the literature. Furthermore, the mDPSO algorithm was able to find optimal solutions for a large percentage of problem instances from a set of test problems in the literature. It was also able to further improve 4 out of 9 larger instances from the literature. Both solution quality and computation times are competitive to or even better than the best performing algorithms from the literature.
Show more

23 Read more

Application of Multi-sensor Information Fusion Based on Improved Particle Swarm Optimization in Unmanned System Path Planning

Application of Multi-sensor Information Fusion Based on Improved Particle Swarm Optimization in Unmanned System Path Planning

At present, Kalman filter is the most widely used multi-sensor information fusion technology which is the general use of distributed or federated filter structure. How- ever, the classical Kalman filter algorithm used by the data processing of the federat- ed filtering subsystem does not achieve the desired effect when dealing with non- Gaussian, nonlinear states and parameter estimates, since the Kalman filter is used to obtain the optimal estimation result. 1) The statistical characteristics of the external jamming noise are subject to the Gaussian distribution. 2) The statistical characteris- tics of the external jamming noise are subject to the Gaussian distribution [6, 7]. Al- most all systems in the real world have non-linear, non-Gaussian features, it is diffi- cult to meet the classic Kalman filter use conditions. Extended Kalman filter is usual- ly used when the state equation or the measurement equation is nonlinear. EKF ap- plies the Taylor expansion of the nonlinear function to the first order linearization, ignoring the other higher order terms, so that the nonlinear problem is transformed into linear, and the Kalman linear filtering algorithm can be applied to the nonlinear system. This solves the problem of system nonlinearity. EKF has been widely used by non-linear state estimation systems and has been widely used by people. However, this method also brings two shortcomings [8-10]. One is that when strong nonlineari- ty, EKF violates local linear assumption, Taylor expansion EKF algorithm may make the filter divergence. In addition, because EKF linearization process requires Jacobi- an matrix, its cumbersome calculation process leads to the realization of the method which is relative to the EKF algorithm. Therefore, EKF is the suboptimal filter under the minimum variance criterion.
Show more

18 Read more

Show all 10000 documents...

Related subjects