Top PDF Fuzzy Logic-Ant Colony Optimization for Explorer-Follower Robot with Global Optimal Path Planning

Fuzzy Logic-Ant Colony Optimization for Explorer-Follower Robot with Global Optimal Path Planning

Fuzzy Logic-Ant Colony Optimization for Explorer-Follower Robot with Global Optimal Path Planning

Currently, many algorithms for solving the problem in path planning, such as Artificial Potential Field [4], Fuzzy Logic [5], Neural Networks [6], Genetic Algorithm [7][8], Particle Swarm Optimization [9][10] and others. However, such algorithms can‟t reach an ideal solution separately in a complex dynamic environment, the methods are inefficient when the target is a long distance away or the environment is cluttered. Artificial potential field easily gets traps into local minima. Fuzzy logic offers a possibility to mimic expert human knowledge, however, the computational expensive when the input increases. Neural network has the capability to learn from existing knowledge, unfortunately, the learning process needs more time to converge. Genetic Algorithm is an evolutionary algorithm, is able to resolve composition optimization problems. However, it updates the good individuals entirely and doesn‟t have exploited the characteristics of the path solution space. Particle swarm optimization is suitable for the optimization problem but only sub-optimal, and it can get trap in local minima. Many intelligent autonomous systems for exploring their environment require estimating the positions of surrounding objects as precisely as possible. Due to the real-world optimization problems are dynamic, regarding the objective function, decision variables, problem instance, constraints, and it changes stochastically over time [10]. To track the optimal solution over time with the environmental changes is desirable. Previous research shows that the interest in ant-based algorithm meta-heuristics is growing in mobile robotics system [11][12][13][14]. The ant colony optimization (ACO) algorithm is one of the prominent algorithms in the robotic fields. The idea is to find the optimal path from the nest to where the food is a graph based on the behavior of food seeking ants [15][16][17]. Unfortunately, the implementation introduces a number of practical challenges and issues that are not encountered, and it addressed only at the simulation level.
Show more

14 Read more

Robot Path Planning using An Ant Colony Optimization Approach:A Survey

Robot Path Planning using An Ant Colony Optimization Approach:A Survey

Ms. Alpa Reshamwala is currently an Asistant Professor in the Department of Computers at MPSTME, NMIMS University. She received her B.E degree in Computer Engineering from Fr. CRCE, Bandra, Mumbai University in 2000 and M.E degree in Computer Engineering from TSEC, Mumbai University in 2008. Her area of Interest includes Artificial Intelligence, Data Mining, Soft Computing – Fuzzy Logic, Neural Network and Genetic Algorithm. She has 20 papers in National/International Conferences/ Journal to her credit. She is also associated as an International Expert of International Journal of Electronics Engineering and Mobile Computing. She has a membership of International Association of Computer Science and Information Technology (IACSIT) and is also a student member of UACEE (Universal Association of Computer and Electronics Engineers)
Show more

7 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

In general, in order to achieve an autonomous navigation capability, a mobile robot must be able to plan a feasible path from a start to a destination in a working environment. Meanwhile, path planning can also be viewed as a constrained dynamic optimization problem. A number of solutions have been recently proposed in the literature to address this problem, such as neural networks [1], [2], fuzzy logic [3], [4], genetic algorithms [5]-[7], hybrid approaches [8], [9], and swarm intelligence-based optimization algorithms. Here, swarm intelligence is a form of artificial intelligence based upon the study of collective behavior in many kinds of animal
Show more

6 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

Welding Path Planning of welding Robot Based on Improved Ant Colony Algorithm

Welding Path Planning of welding Robot Based on Improved Ant Colony Algorithm

With the development of the economy and the strong support of the government, the demand for robots in various industries is getting higher and higher. In the automobile, motorcycle, ship, engineering equipment and other manufacturing industry, the role of welding robot is growing. In general, an ordinary car's white body has 4200-6300 welding points, only to the welding robot as the core of the production line, in order to complete the mass production and technological reform. The application of welding robots is becoming more and more extensive, and more and more scholars and researchers are engaged in the research of key technologies of welding robots. For welding robots, the planning of welding tasks is particularly important, so the welding path planning is one of the key research. The welding path planning of the spot welding robot is the most important step in the welding process. If the welding path can be planned reasonably, the working time of the robot can be reduced, the working efficiency of the robot can be improved and the production cost can be reduced. In [1], an evolutionary algorithm based on the introduction of new genetic operators is proposed to optimize the robot path. In [2], it is pointed out that when the number of solder joints is small, the dynamic programming is better than other optimization algorithms, but when the solder joint increases, it will often cause no solution. In [3], a double global optimal genetic algorithm is proposed to optimize the path length of welding robot. In [4], a new algorithm is proposed, which is based on TSP (traveled salesman problem) elastic network and neural network to solve the deformation problem of welding robot path planning. In this paper, the combination of Adadelta algorithm and ant colony algorithm is used to increase the randomness of pheromone to avoid the local optimization of the algorithm, so as to improve the performance of the algorithm and realize the path planning by discretizing the objective function.
Show more

6 Read more

Unmanned vehicle path planning using a novel ant colony algorithm

Unmanned vehicle path planning using a novel ant colony algorithm

The ant colony optimization algorithm, which is de- rived from the study of ant group behavior, simulates a bionic intelligent optimization algorithm based on the cooperation between ant colonies. When ants are for- aging, they will leave exogenous hormone, and others can recognize the intensity of pheromone. And ants tend to move toward higher pheromone concentrations. That can be said as a kind of positive feedback phenomenon of the ant group during the foraging process [5]. It is be- cause of this positive feedback mechanism that the ant colony can search for food more quickly. This algorithm has strong global search ability, can perform parallel and distributed computing, and has fast convergence speed and strong adaptability [6], so it has been widely used in solving path planning problems. In the literature [7], the paper proposes an improved ant colony algorithm. The article mainly improves the positional distribution of the initial population and increases the adaptive evaporation factor and simulated annealing. It is found through ex- periments that the algorithm can effectively reduce the problem of search time. In the literature [8], the author can avoid the blindness of initial planning by adjusting the transition probability based on the classical ant col- ony algorithm and introducing relevant strategies to solve the deadlock problem. The simulation experiment proves that the algorithm is superior to the classical ant colony algorithm, which can effectively guide the mobile robot to avoid dynamic obstacles in the environment, obtain the optimal or suboptimal path without collision,
Show more

9 Read more

Improved Ant Colony Optimization Algorithm and Its Application on Path Planning of Mobile Robot

Improved Ant Colony Optimization Algorithm and Its Application on Path Planning of Mobile Robot

All ants update their pheromones after ant colony completed an iteration in conventional ACO algorithm. But it doesn’t adequately reveal guidance function of optimal solutions; at the same time the information of bad solutions also disturbs colony iteration of next generation. But if only optimal ants update their pheromones, there are also some problems. More specifically, if only global optimal ants update their pheromones, then the convergence speed is quicker at initial phase of ACO algorithm, but the possibility of running into local optima will increase. On the contrary, if current optimal ants are updated, the diversity of ACO algorithm appeared well maintained, but the convergence speed isn't perfect. So this paper applies itself to find preferable updating strategy and replace former two kinds of updating strategies in order to improve performance of algorithm.
Show more

8 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

Abstract. In order to improve the efficiency in path planning of security robot, this paper addresses to construct three kinds of grid obstacle models from simple to complicated, and use the integrated ant colony-particle algorithm to make global path planning. For further explaining the effectiveness of the combined algorithm implementation, this paper compares the different effects in path planning of the traditional ant colony algorithm and the combined ant colony-particle swarm optimization from three aspects, which are the iteration number of searching the optimal solution, the shortest path length and the running time. It is found that the integrated ant colony-particle algorithm enhances the search efficiency of the optimal solution and reduces the number of iterations of the search, so as to complete the optimal path of the security robot from the start point to the end point.
Show more

7 Read more

Ant Colony Optimization Algorithm for Robot Path Planning

Ant Colony Optimization Algorithm for Robot Path Planning

Pheromone initialization plays an important role in ACO algorithm. In this research, after the obstacles are added, the pheromones in the network are re-initialized. Two different re-initialization schemes, namely, the global initialization and the local initialization are tested and their performances are compared. In global initialization, all the pheromones in the entire network are uniformly reset back to the original pheromone level, which is 0.1. With local initialization, a "gradient" of pheromones is initialized around the object. The value of half the highest pheromone levels in the network is applied directly to the points that are next to the object. The pheromone levels are then decreased by a fraction (e.g., 50%) as the points move outward in a "circle" around the object. Fig. 3 shows the optimal path found in a 40X40 grid with obstacles using the local initialization method.
Show more

5 Read more

Ant Colony Optimization Resource Allocation for Software Release Planning

Ant Colony Optimization Resource Allocation for Software Release Planning

We describe a release plan x and the associated resource allocation u by the combined vector (x, u). We also use the terms “assignment” for x and “detailed schedule” for u. The composite set of all feasible assignments and detailed schedules1 (x, u) is denoted by the Cartesian product X, Uor just (X, U). We note that the part of the problem related to detailed schedules does not directly influence the stated objective of planning but is part of the constraint set that needs to be fulfilled. We can say that the schedule “enables” the features. The objective is to maximize the stated utility function F, which is based on the value parameters v (n, k) introduced in Section 2.1.2. The problem ANTRASORP is formally stated as Maximize {F(x)=
Show more

6 Read more

Path Planning of Mobile Robot Based on Genetic Bee Colony Algorithm

Path Planning of Mobile Robot Based on Genetic Bee Colony Algorithm

When the algorithm run to the later period, the food source has been nearly optimal. The effective number of the location has a smaller difference, which leads to the slower speed of the search. Therefore, it is very necessary to improve the ability of the search and the convergence rate of the algorithm. In the process of solving GBCA, the algorithm will produce many benefits of different food source at the stage of the scout. The benefits of new food source are sorted by the value of the benefits.

6 Read more

Two Dimension Path Planning Method Based on Improved Ant Colony Algorithm

Two Dimension Path Planning Method Based on Improved Ant Colony Algorithm

Nowadays, path planning has become an important field of research focus. Considering that the ant colony algorithm has numerous advantages such as the distributed computing and the cha- racteristics of heuristic search, how to combine the algorithm with two-dimension path planning effectively is much important. In this paper, an improved ant colony algorithm is used in resolving this path planning problem, which can improve convergence rate by using this improved algo- rithm. MAKLINK graph is adopted to establish the two-dimensional space model at first, after that the Dijkstra algorithm is selected as the initial planning algorithm to get an initial path, imme- diately following, optimizing the select parameters relating on the ant colony algorithm and its improved algorithm. After making the initial parameter, the authors plan out an optimal path from start to finish in a known environment through ant colony algorithm and its improved algo- rithm. Finally, Matlab is applied as software tool for coding and simulation validation. Numerical experiments show that the improved algorithm can play a more appropriate path planning than the origin algorithm in the completely observable.
Show more

8 Read more

A Cellular Ant Colony Algorithm for Path Planning Using Bayesian Posterior Probability

A Cellular Ant Colony Algorithm for Path Planning Using Bayesian Posterior Probability

Abstract. In order to solve the problem of slow convergence rate in traditional ant colony algorithm for UAV path planning, a new cellular ant colony algorithm is proposed. First, we construct a sector prediction area in grid environment map. Then we build heuristic and obstacle repulsion functions of target nodes in the prediction area. Using these functions, we can get the Bayesian conditional probability and posterior estimation of target nodes. In the end, we select the node with the largest posterior estimation as the next path node. The simulation results show that the new algorithm has better global search ability. Furthermore, using the sector prediction area makes the planned path more consistent with the UAV flight characteristics. And the designed functions in the sector prediction area speeds up the path search process.
Show more

8 Read more

Optimal Placement of Phasor Measurement Unit  Using Ant Colony Optimization

Optimal Placement of Phasor Measurement Unit Using Ant Colony Optimization

Efficient and reliable Wide Area Monitoring System (WAMS) is crucial in preventing outages and cascading failures in the smart grid. Since Phasor measurement units (PMU)s are the critical part of the WAMS, the questions of the arrangement and number of PMUs to use and place in order to evaluate risk must be addressed. This paper presents the optimal placement of PMU, ensuring system observability. An Ant Colony Optimization (ACO) method for Optimal Placement of PMU (OPP) problems is suggested which is a probability-based searching method. The proposed method is applied to the OPP problem in IEEE 9–Bus, 14- Bus and 30-bus test systems to show its effectiveness. Results obtained using ACO has been compared to the results of PSO, SA, GA and other methods and it has been found that it is computationally robust and takes lesser time than other optimization algorithms.
Show more

11 Read more

Robot Path Planning in a Dynamic and Unknown Environment Based on Colonial Competitive Algorithm (CCA) and Fuzzy Logic

Robot Path Planning in a Dynamic and Unknown Environment Based on Colonial Competitive Algorithm (CCA) and Fuzzy Logic

Fuzzy theory was first introduced by Zade in 1965 [23]. There are three significant steps in fuzzy logic. The first step is fuzzification of input, the Second step is creating fuzzy rules table which is usually determined by specialists and the final step is called the defuzzification step [24]. For Path planning in fuzzy logic, at any moment, the next node will be selected from among the eight available options by using the angle difference to the target and its distance to the nearest obstacle. Afterward, a selective preference coefficient is obtained as the next node, for each of those eight available nodes. After applying fuzzy logic, a defuzzified or final output is created for the inputs of each node. Eventually, when the node has the most defuzzification preference coefficient, it will be the next selective node in that procedure. Membership functions have been demonstrated in Fig. 1 for two inputs and fuzzy output (selective preference coefficient). In addition, a number of fuzzy rules for this issue are specified in Table I.
Show more

6 Read more

Fuzzy Logic Based Path Navigation for Robot using Matlab

Fuzzy Logic Based Path Navigation for Robot using Matlab

A robot is a programmable machine, able to extract information from its surrounding using different kinds of sensors or web camera to plan and execute collision free path by avoiding the obstacle in front of robot within its environment without human intervention. Navigation is a crucial issue for robots. A navigation system can be divided into two layers: High level global planning and Low-level reactive/local control. In high-level planning, a prior knowledge of environment is available and the robot workspace is completely or partially known. Using the world model, the global planner can determine the robot motion direction and generates shortest paths towards the target in the presence of complex obstacles. However, since it is not capable of changing the motion direction in presence of unforeseen or moving obstacles, it fails to reach target or it may collide with the obstacle which came in their path. In contrast, in low-level local path planning, the robot work space is unknown and dynamic (presence of moving obstacle). It generates control commands based on coding given to the microcontroller, in which the robot uses current sensory information to take appropriate actions without planning process. Thus, it has a quick response in reacting to unforeseen obstacles and uncertainties with changing the motion direction [3].6
Show more

6 Read more

Robot path planning in a dynamic and unknown environment based on Colonial Competitive Algorithm (CCA) and fuzzy logic

Robot path planning in a dynamic and unknown environment based on Colonial Competitive Algorithm (CCA) and fuzzy logic

Robot path planning in a trajectory has been one of the interesting areas for many Machine Learning and Pattern Recognition researchers from the past till date. Robot path planning can be simple and somewhat complex. The obstacles which are passed by the robot are either movable or fixed. Automated robot path planning for only one environment is one of the unsolved robotic challenges. Several methods that have been presented to solve these issues should be considered in two: classic and heuristic categories [1, 2]. In the first twenty years of the advent of this field, scientists generally used classic routing method. But, this method had a notable problem named NP-Complete for robot path planning [3]. Thus, in order to overcome this issue, evolutionary method was designed. Evolutionary method is not performable in spite of its popularity because, in the beginning, all the paths are not accessible for the unknown environment with a movable obstacle. The method based on fuzzy logic is much appropriate for this type of problem. On the other hand, the table of the fuzzy rules has many rows in most of the cases.
Show more

7 Read more

Ant Colony Optimization algo

Ant Colony Optimization algo

• Virtual “trail” accumulated on path segments • Starting node selected at random.. • Path selected at random.[r]

34 Read more

Ant Colony Optimization Algorithm

Ant Colony Optimization Algorithm

Abstract -Hybrid algorithm is proposed to solve combinatorial optimization problem by using Ant Colony and Genetic programming algorithms. Evolutionary process of Ant Colony Optimization algorithm adapts genetic operations to enhance ant movement towards solution state. The algorithm converges to the optimal final solution, by accumulating the most effective sub-solutions.

6 Read more

Reactive Fuzzy Logic Controller Simulation for Robot Motion Planning

Reactive Fuzzy Logic Controller Simulation for Robot Motion Planning

1645 | P a g e The authors formulate an approach which attempts to overcome this tendency of fuzzy algorithms with a “layered, goal-oriented” navigation strategy. Two layers are proposed: long-range versus short-range information assessment. The first layer uses long-range sensor data and the global goal angle to determine a direction that is both traversable (free of obstacles) and desirable (toward the goal). The qualities of directional traversability and desirability are represented as fuzzy sets and fused to produce a way-point along the path to the goal. Sensors are positioned at intervals around the perimeter the robot body and detect distant obstacles. The signal strength of each sensor indicates the relative nearness of an obstacle. This strength is fuzzified through a collection of trapezoidal fuzzy sets for angles of -180 0 (left) to +180 0 (right). Where adjacent sensors detect an obstacle with strengths of  1 and  2 , an untraversable area τ i is the composed fuzzy set found by the
Show more

7 Read more

Show all 10000 documents...