The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
We develop and analyze an unsupervised and domain-independent method for extracting keywords from single documents. Our approach differs from the previous ones in the way of identifying candidate keywords, pruning the list of candidate keywords with several filtering heuristics and selecting keywords from the list of candidate keywords according to dynamic threshold functions. We were able to obtain...
This paper presents a new method for mobile robots motion planning in dynamic environments based on wave expansion approach is the main issue of this work, which avoids full wave expansion in sudden obstacle case. Full Wave expansion in great scale environments takes considerable amount of time and the process. In this work a new wave expansion algorithm for path finding, local minima, and sudden...
A path planning algorithm of robot is proposed based on ensemble algorithm of the learning classifier system, which design fitness function in dynamic environment. The paper derived and proved that ensemble algorithm is convergence and provided a theoretical guarantee for the path planning algorithm. Simulation results also showed that genetic algorithms and learning classifier system combination...
Mobile robots often need to find a trajectory to another position in their environment, subject to constraints posed by obstacles and the robot's capabilities. Several approaches have been used to address this problem each with some limitations, including state discretizations, planning efficiency, and lack of interleaved execution. Anytime RRTs algorithm is a recently developed algorithm on which...
During simultaneous localization and mapping, geometrical constraints are established between map features. These constraints, introduced through measurements and motion prediction, produce a bending effect in the event of closing a large loop. In this paper we present a discussion of the bending problem for trajectory based representations. Furthermore, we propose a generic approach to reduce the...
This study attempts to make a compact humanoid robot acquire a giant-swing motion without any robotic models by using reinforcement learning; only the interaction with environment is available. Generally, it is widely said that this type of learning method is not appropriated to obtain dynamic motions because Markov property is not necessarily guaranteed during the dynamic task. However, in this study,...
Moving objects are present in many robotic applications. An accurate detection and motion estimation of these objects can be crucial for the success and safety of the robot and people surrounding it. This paper presents a new probabilistic framework for clustering dependent or relational data, applied to the problem of motion clustering and estimation. While conventional techniques such as scan differencing...
An approach of cooperative hunting for multiple mobile targets by multi-robot is presented, which divides the pursuiting process into forming the pursuiting groups and capturing the targets. The data sets of attribute relationship is built by consulting many factors about capturing evaders, then the interesting rules can be found by data mining from the data sets to build the pursuiting groups. Through...
This paper presents a method for detecting people from images taken with a camera mounted on a robot. The purpose of the detection is avoiding people collision while robot is moving within an unknown environment. It combines two algorithms for this purpose. First, the appearance of people is learned using a set of Haar-like features and the Adaboost algorithm. This information is embedded by building...
This paper presents a novel coverage path planning algorithm for a mobile robot in indoor environment. Overall region is divided into several sub-regions based on the virtually extracted doors. The key idea of this method was obtained from the usual way of dividing an indoor environment into sub-regions, i.e., rooms based on the identification of doors. The proposed virtual door algorithm extracts...
Considering path planning for multiobjects in complex environment, the construction of complete graph which reflects the relative distance between objects in real world has great influence on calculating the sequence of objects and the optimal path throughout the optimization and path planning algorithm. This paper describes an approach that integrates the representations of uniform grids and Voronoi...
A new two-level receding horizon multiple robot formation control strategy is proposed in this paper. Where the local GPMN tracking controllers acting on each individual robot system are at the lower level, and at the higher level, the receding horizon optimization is conducted by considering both the full dynamics of each robot system and their local controller. This new algorithm presents some attracting...
This paper proposed a pursuit-evasion algorithm based on the Option method from hierarchical reinforcement learning and applied it into multi-robot pursuit-evasion game in 2D-Dynamic environment. The algorithm efficiency is studied by comparing it with Q-learning. We decompose the complex task with option method, and divide the learning process into two parts: High-level learning and Low-level learning,...
In recent years, anytime algorithms have shown to be a good solution for planning a path in domains with severe restrictions regarding the time for deliberation. They typically operate by quickly finding a highly suboptimal path first, and then improving it until the available time runs out. In this paper, we propose a novel anytime approach called ABUG that performs much more efficiently than the...
In this paper, we propose a new algorithm for a mobile robot that avoids obstacles autonomously by using local information. In this algorithm, a robot follows a preplanned path as much as possible, and if it detects an obstacle on or near the path, it autonomously changes its direction and controls speed to avoid the obstacle. These steering angle and control speed are decided by using the relative...
The thesis presented a heterogeneous players strategy using in RoboCup. The strategy used fuzzy evaluation to obtain the evaluation results of all heterogeneous players on various roles, and constructed a fuzzy inference system to dynamically select equal heterogeneous players for various roles. The simulation experiments and competition results show the application is feasible and effective.
The paper addresses the problem of creating a comprehensive fault injection environment, which integrates and improves various simulation and supplementary functions. This is illustrated with experimental results.
Autonomous robot navigation is an important research field because these robots can solve problems where the human presence is impossible, dangerous, expensive, or uncomfortable. In this paper, a new hybrid autonomous navigation method is introduced. The algorithm is composed of visibility graph based global navigation and simple potential field based local navigation parts. It applies a new automated...
This paper presents a decentralized control algorithm for swarm of robots based on geometric approach. Our objective is to build a swarm that can demonstrate collective behavior. The control algorithm, which is executed by all the members of the swarm, is presented in details. Our simulation results show that group behaviors such as aggregation, obstacle avoidance and flocking are achieved successfully.
This paper describes the experimental results of a high speed robotic system used in an electric autoloader for the Army's 155 man self propelled howitzer. Besides the nonlinear dynamics, the real-time controller also needs to be robust against factors such as unmodelled dynamics, noise, and actuator saturation. This paper also describes the special hardware that was built to handle the electrical...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.