• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.12
• /
• pp.577-582
• /
• 2002

The objective of this paper is to produce a weighted graph map for path-planning of an autonomous mobile robot(AMR) based on the measurements from a single ultrasonic sensor, which are acquired when the autonomous mobile robot explores unknown indoor circumstance. The AMR navigates in th unknown space by following the wall and gathers the range data using the ultrasonic sensor, from which the occupancy grid map is constructed by associating the range data with occupancy certainties. Then, the occupancy grid map is converted to a weighted graph map suing morphological image processing and thinning algorithms. the path- planning for autonomous navigation of a mobile robot can be carried out based on the occupancy grid map. These procedures are implemented and tested using an AMR, and primary results are presented in this paper.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.1132-1135
• /
• 1996

The objective of this paper is to make a model-based map for the localization of an autonomous mobile robot(AMR) from ultrasonic sensor measurements, that are acquired when the AMR explores unknown indoors. First, the AMR navigates on unknown space by wall-following and gathers range data from the ultrasonic sensor. Then, the range data are converted to a wall-marked gird map, from which lines representing the walls are extracted using the Hough transform. This process is implemented on an AMR having an ultrasonic sensor, and a preliminary experimental result is presented.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.400-400
• /
• 2000

This paper purposed that verify the validity of Petri Net method for control progressive increase of system complexity, before extend the realized single robot system to multi-robot system. An autonomous mobile robot(AMR) needs decision making, motion control, path planning, tracking a path, obstacle avoidance, and sensor fusion, to complete its task. An AMR integrates and operates these technics through a consistent command system. An error in a command hierarchy which is like duplication or omission of a control command hierarchy for each module results in serious problems. This paper minimizes the error by modeling each module and whole system using Petri Net graphical representation and applies it to the exploration task of an AMR

• 제어로봇시스템학회:학술대회논문집
• /
• 1995.10a
• /
• pp.464-467
• /
• 1995

Autonomous Mobile Robot(AMR) is a field of study which is under active research along with rapid development of the engineering technology. The main reasons for the high interest in AMR are because of its ability to change work space freely and its capability to replace human being for difficult and dangerous jobs. Also the fact that AMR provides a variety of research fields, such as path planning, navigation algorithm, sensor fusion, image processing, and controller design is part of the reason for its popularity. But relatively few researches are concerned with controller. So in this paper, a control strategy of mobile robot with nonholonomic constraint for tracking ordered discontinuous motion is proposed. The proposed control strategy has been designed as a state feedback shape to allow the AMR to obtain continuous velocity and track the path which is composed of discontinuous motions. In order to design such controller, 3 states have been reduced to 2 states through coordinate projection. These ideas are tested for validity through simulation and simulation result is compared with experiments result.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.50 no.11
• /
• pp.522-531
• /
• 2001

Recently conventional artificial intelligence(AI) approaches have been employed to build action selectors for the autonomous mobile robot(AMR). However, in these approaches, the decision making process to choose an action from multiple competence modules is still an open question. Many researches have been focused on the reactive planning systems such as the biological immune system. In this paper, we attempt to construct an action selector for an AMR based on the artificial immune network and internet. The information from vision sensors is used for antibody. We propose a learning method for artificial immune network using evolutionary algorithm to produce antibody automatically. The internet environment for an AMR action selector shows the usefulness of the proposed learning artificial immune network application.

• Proceedings of the KIEE Conference
• /
• 2003.07e
• /
• pp.38-41
• /
• 2003

An Autonomous Mobile Robot(AMR) performs duty by sensing a recognized situation and controlling suitably. The existing algorithm has some advantages that it is possible to express the obstacle exactly and the robot is sensitive to the change of environment. However, this algorithm needs to control repeatedly according to the modelling and working environment that requires a great quantity of calculations. In this paper, We supplement shortcoming and designed direction algorithm of AMR using fuzzy controller. Fuzzy controller does not derive special quality spinning expression for system, and uses rules by value expressed by language. It is used extensively to non-linear, plant which mathematical modelling is difficult etc... Fuzzy control algorithm of AMR that is used by this research applies obstacle position, distance of obstacle, Progress direction of robot, speed of robot, Perception area of sensor, etc... by fuzzy control and decide steering angle of robot.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.52 no.12
• /
• pp.679-688
• /
• 2003

In order to navigate the mobile robots safely in unknown environments, many researches have been studied to devise navigational algorithms for the mobile robots. In this paper, we propose a navigational algorithm that consists of an obstacle-avoidance behavior module, a goal-approach behavior module and a radial basis function network(RBFN) supervisor. In the obstacle-avoidance behavior module and goal-approach behavior module, the fuzzy-artificial immune networks are used to select a proper steering angle which makes the autonomous mobile robot(AMR) avoid obstacles and approach the given goal. The RBFN supervisor is employed to combine the obstacle-avoidance behavior and goal-approach behavior for reliable and smooth motion. The outputs of the RBFN are proper combinational weights for the behavior modules and velocity to steer the AMR appropriately. Some simulations and experiments have been conducted to confirm the validity of the proposed navigational algorithm.

• Proceedings of the KIEE Conference
• /
• 1994.11a
• /
• pp.345-348
• /
• 1994

A real-time collision avoidance algorithm for an AMR (Autonomous Mobile Robot) using the Distance Transform and Vector Field Histogram is studied. This approach enables AMR to find a collision-free path with the unknown obstacles. All system parameters including positions of the obstacles can be accepted using a mouse icon and all the obtained trajectories can be displayed on a computer monitor in graphics.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2588-2590
• /
• 2003

The part of manipulators is normally studied with regularized environmental conditions. however, it is the most difficult that the part of AMR must be studied with uncertainty in the environmental conditions. The part of AMR has skelton, sensor fusion, path planning etc. This paper is the research of the local pass planning that gathers information about external environment using neural network from each sensors and designs the algorithm which can determine which correct direction the robot can find. As the result of the research, AMR has been able to drive similarly as if the expert does and has been able to observe it acting without any control.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.138.4-138
• /
• 2001

The purpose of this research is to build a quality-improved occupancy grid map for path-planning of an autonomous mobile robot(AMR) based on the measurements from a single ultrasonic sensor, which are acquired when the autonomous mobile robot explores unknown indoor environment. The AMR navigates in the unknown space by following the wall and gathers the range data using the ultrasonic sensor, from which the occupancy grid map is constructed by associating the range data with occupancy certainties. In order to increase the quality of the map we modify the Bayesian probability updating rule, reject non-systematic measurement errors and correct the predictable error of the AMR itself. These procedures are implemented and tested using an AMR, and primary results are presented in this paper.