• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.345-348
• /
• 2005

Because the current web search engine estimates the similarity of documents, using the frequency of words, many documents irrespective of the user query are provided. To solve these kinds of problems, the semantic web is appearing as a future web. It is possible to provide the service based on the semantic web through ontology which specifies the knowledge in a special domain and defines the concepts of knowledge and the relationships between concepts. In this paper to search the information of potential customers for home-delivery marketing, we model the specific domain for generating the ontology. And we research how to retrieve the information, using the ontology. Therefore, in this paper, we generate the ontology to define the domain about potential customers and develop the search robot which collects the information of customers.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.11
• /
• pp.2152-2156
• /
• 2011

In this paper, we propose the novel behavior control algorithm by using the efficient searching method based on the characteristic of the swarm robots in unknown space. The proposed method consists of identifying the position and moving state of a robot by the dynamic modelling of a wheel drive vehicle, and planing behavior control rules of the swarm robots based on the sensor range zone. The cooperative search for unknown space is carried out by the proposed behavior control. Finally, some experiments show the effectiveness and the feasibility of the proposed method.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.8 no.3
• /
• pp.220-224
• /
• 2008

This paper presents the polygon-based Q-leaning and Parallel SVM algorithm for object search with multiple robots. We organized an experimental environment with one hundred mobile robots, two hundred obstacles, and ten objects. Then we sent the robots to a hallway, where some obstacles were lying about, to search for a hidden object. In experiment, we used four different control methods: a random search, a fusion model with Distance-based action making (DBAM) and Area-based action making (ABAM) process to determine the next action of the robots, and hexagon-based Q-learning, and dodecagon-based Q-learning and parallel SVM algorithm to enhance the fusion model with Distance-based action making (DBAM) and Area-based action making (ABAM) process. In this paper, the result show that dodecagon-based Q-learning and parallel SVM algorithm is better than the other algorithm to tracking for object.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.4
• /
• pp.27-34
• /
• 2013

Mobile robot has the exploration function in order to perform its own task. Robot exploration can be used in many applications such as surveillance, rescue and resource detection. The workspace that robots performed in was complicated or quite wide, the multi search using the several mobile robots was mainly used. In this paper, we proposed a scheme that all areas are searched for by using one robot. The method to be proposed extract a area that can be explored in the workspace then the robot investigates the area and updates the map at the same time. The explored area is saved as a hybrid map that combines the nice attributes of the grid and topological maps. The robot can produce the safe navigation route without the obstacles by using hybrid map. The proposed hybrid map uses less memory than a grid map, but it can be used for complete coverage with the same efficiency of a topological map. Experimental results show that the proposed scheme can generate a map of an environment with only 6% of the memory that a grid map requires.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.2
• /
• pp.131-137
• /
• 2006

In swarm robot systems, each robot must behaves by itself according to the its states and environments, and if necessary, must cooperates with other robots in order to carry out a given task. Therefore it is essential that each robot has both learning and evolution ability to adapt the dynamic environments. In this paper, the new learning and evolution method based on reinforcement learning having delayed reward ability and distributed genetic algorithms is proposed for behavior learning and evolution of collective autonomous mobile robots. Reinforcement learning having delayed reward is still useful even though when there is no immediate reward. And by distributed genetic algorithm exchanging the chromosome acquired under different environments by communication each robot can improve its behavior ability. Specially, in order to improve the performance of evolution, selective crossover using the characteristic of reinforcement learning is adopted in this paper. we verify the effectiveness of the proposed method by applying it to cooperative search problem.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1939-1944
• /
• 2003

This paper presents a global path planning algorithm based on a visibility graph method, and applies additionally various constraints for constructing the reduced visibility graph. The modification algorithm for generating the rounded path is applied to the globally shortest path of the visibility graph using the robot size constraint in order to avoid the obstacle. In order to check the visibility in given 3D map data, 3D CAD data with VRML format is projected to the 2D plane of the mobile robot, and the projected map is converted into an image for easy map analysis. The image processing are applied to this grid map for extracting the obstacles and the free space. Generally, the tree size of visibility graph is proportional to the factorial of the number of the corner points. In order to reduce the tree size and search the shortest path efficiently, the various constraints are proposed. After short paths that crosses the corner points of obstacles lists up, the shortest path among these paths is selected and it is modified to the combination of the line path and the arc path for the mobile robot to avoid the obstacles and follow the rounded path in the environment. The proposed path planning algorithm is applied to the mobile robot LCAR-III.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.1
• /
• pp.119-126
• /
• 2002

In this paper, we present a new approach based on an elitist genetic algorithm for the task of aligning the position of a robot gripper using CCD cameras. The vision-based control scheme for the task of aligning the gripper with the desired position is implemented by image information. The relationship between the camera space location and the robot joint coordinates is estimated using a camera-space parameter modal that generalizes known manipulator kinematics to accommodate unknown relative camera position and orientation. To find the joint angles of a robot manipulator for reaching the target position in the image space, we apply an elitist genetic algorithm instead of a nonlinear least square error method. Since GA employs parallel search, it has good performance in solving optimization problems. In order to improve convergence speed, the real coding method and geometry constraint conditions are used. Experiments are carried out to exhibit the effectiveness of vision-based control using an elitist genetic algorithm with a real coding method.

• Journal of Institute of Control, Robotics and Systems
• /
• v.12 no.3
• /
• pp.208-220
• /
• 2006

Energy of wheeled mobile robot is usually supplied by batteries. In order to extend operation time of mobile robots, it is necessary to minimize the energy consumption. The energy is dissipated mostly in the motors, which strongly depends on the velocity profile. This paper investigates various 3-step (acceleration - cruise - deceleration) speed control methods to minimize a new energy object function which considers the practical energy consumption dissipated in motors related to motor control input, velocity profile, and motor dynamics. We performed an analysis on the energy consumption various velocity profile patterns generated by standard control input such as step input, ramp input, parabolic input, and exponential input. Based on these standard control inputs, we analyzed the six 3-step velocity profile patterns: E-C-E, P-C-P, R-C-R, S-C-S, R-C-S, and S-C-R (S means a step control input, R means a ramp control input, P means a parabolic control input, and E means an exponential control input, C means a constant cruise velocity), and suggested an efficient iterative search algorithm with binary search which can find the numerical solution quickly. We performed various computer simulations to show the performance of the energy-optimal 3-step speed control in comparison with a conventional 3-step speed control with a reasonable constant acceleration as a benchmark. Simulation results show that the E-C-E is the most energy efficient 3-step velocity profile pattern, which enables wheeled mobile robot to extend working time up to 50%.

• The KIPS Transactions:PartD
• /
• v.12D no.3 s.99
• /
• pp.481-492
• /
• 2005

To guide the guiding robot for the visually impaired carefully, the digital map to be used to search a path must be detailed and has some information about dangerous spots. It also has to search not only safe but also short path through the position data by GPS and INS sensors. In this paper, as the difference of the ability that the visually unpaired can recognize, we have developed the localization tracking system so that it can make a movement path and verify position information, and the global navigation system for the visually impaired using the GPS and INS. This system can be used when the visually impaired move short path relatively. We had also verified that the system was able to correct the position as the assistant navigation system of the GPS on the outside.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.37 no.5
• /
• pp.19-28
• /
• 2000

It is not so easy to control the wheeled mobile robot because of some causes like non-holonomic constraints. To overcome these problems, a controller that PD system is combined with fuzzy process is composed of several steps that have each separate algorithm and niche search algorithm and immune algorithm is applied partly. Output term set is changed by search that is performed to get optimal elements and then the rule base is also reformed. The fitness for the altered system is estimated and the surplus elements are removed. After the adjustment of output term set and rule base is finished, input and output membership functions is tuned.