Bo-Yi Li

Implementation of the chess game artificial intelligent using mobile robots

The article develops the decision rules to win each set of the Chinese chess game using artificial intelligent and evaluation algorithm, and presents the movement scenarios of the chesses using mobile robots on the grid based platform. Artificial intelligent is often applied in computer chess game, and programs the movement method to win each set for a player (red side or black side). We play the Chinese chess game using the mouse according to the game rules on the user interface. The supervised computer controls mobile robots according to the programmed motion paths of the chess moving on the platform via wireless radio frequency (RF) interface, and selects which chess moving to the best position to win the set using evaluation algorithm and artificial intelligent method. Then we use simulation method to display the motion paths of the assigned chesses on the user interface. The supervised computer implements the simulation results on the chessboard platform using mobile robots. Mobile robots move on the chessboard platform to be guided to move on the centre line of the corridor, and avoid the obstacles (chesses), and detect the cross point of the platform using three reflective infrared (IR) modules.

Speech-based formation control of the multi-robot system

The article presents multiple pattern formation control of the multi-robot system using A* searching algorithm, and avoids the collision points moving on the motion platform. We use speech recognition algorithm to decide the various pattern formations, and program mobile robots to present the movement scenario on the grid-based motion platform. We have been developed some pattern formations to be applied in game applications, such as long snake pattern formation, phalanx pattern formation, crane wing pattern formation, sword pattern formation, cone pattern formation and so on. The mobile robot contains a controller module, three IR sensor modules, a voice module, a wireless RF module, a compass module, and two DC servomotors. The controller of the mobile robot can acquire the detection signals from reflect IR sensor modules and the compass module, and decide the cross points of the aisle. The mobile robot receives the command from the supervised computer, and transmits the status of environment to the supervised computer via wireless RF interface. We develop the user interface of the multi-robot system to program motion paths for various pattern formation exchanges using the minimum displacement. Users can use speech to control the multiple mobile robots to execut pattern formation exchange. In the experimental results, users can speak the pattern formation. The speech recognition system receives the signal to decide the pattern formation. The multiple mobile robots can receive the pattern formation command from the supervised computer, and arrange the assigned pattern formation on the motion platform, and avoid other mobile robots.

Task Assignment and Route Programming for Pattern Reformation on Grid Plane

Pattern reformation problem on a grid plane is an interesting problem. Suppose there is a group of mobile robots on a square grid plane with the number of robots equaling to the number of columns/rows of the grid plane. The mobile robots are commanded to change to another formation as soon as possible. Any one of them has to prevent himself from colliding with other mobile robots during the moving of reformation process. In this paper, we will provide a systematic process on task assignment of route programming for the pattern reformation problem on a square grid plane. We will also provide a checking process to check if the suggested program is really good or not.

Programming of the Fire Escaping Paths Using Bayesian Estimated Algorithm

The paper develops a fire monitoring and escaping system that is applied in the intelligent home and uses mobile robots with flame sensor to detect fire sources. The supervised computer receives the locations of the detected fire sources and calculates the risk values of the cross points of the motion platform using joint probability. Then the supervised computer programs motion paths and escaping paths, and controls mobile robots to guide the human leaving the fire field. Mobile robots contain two types moving in the platform. One is the fire detection robot using ultraviolet sensor to search fire sources. The other represents the human walking in the motion platform autonomously. The controller of the two type mobile robot is STCMCS-51 microchip. The fire detection robots receive the motion command from the supervised compute via wireless RF interface. Each mobile robot transmits ID code, position and orientation, positions of detected fire sources and obstacles to the supervised computer via wireless RF interface, too. We classified three steps for fire detection process. The supervised computer controls fire detection robots to search fire sources, uses Gaussian distribution function to present the risk values of the detected fire source, and combines with joint probability to compute the relation risk for multiple fire sources in the first step. In the second step, A searching algorithm and the relation risk values were used as a basis to program the motion paths from the human, and a fire detection robot was assigned to guide the human leaving the fire field. The supervised computer re-programs the escaping routs to avoid detected fire sources and obstacles for the fire detection robots in the third step and controls mobile robots to present the movement scenario step by step.

Motion Planning of Multi-docking System for Intelligent Mobile Robots

The article develops a multi-docking system with a mobile robot and three docking stations. The docking structure is designed with one active degree of freedom and two passive degrees of freedom. The controller of the power detection devices is HOLTEK microchip, and acquires measurement values of the real-time current and voltage of the mobile robot and the docking stations. The power detection devices contain three power detection systems and one power detection module. The power detection system is embedded in the docking station and monitors the real-time information for the charging process. The controller of the mobile robot receives these measurement values from the power detection module via RS232 interface. The article focuses on the searching process using multiple sensors and a laser range finder for the mobile robot. The laser range finder searches the landmark of each docking station, and guides the mobile robot moving to the assigned docking station. In the experimental results, the power of the mobile robot is under the threshold value. The mobile robot selects the free and nearest docking station according to the received information from each docking station via wireless RF interfaces. The laser range finder guides the mobile robot moving approach to the assigned docking station. The power of the mobile robot is enough to be detected by the power detection module. The docking station turns off the charging current, and trigs the mobile robot leaving the docking station via wireless RF interface.