Silva-2008b

Master thesis

Sensor fusion and behaviours are two of the modules required in the implementation of software agents able to play soccer. CAMBADA is the MSL RoboCup robotic soccer team created by the ATRI group, part of the IEETA research unit at Aveiro University.
This thesis provides an overview of the CAMBADA team architecture over which the described work was implemented. The motion of the robot is a low level control problem, in this case solved by a PID controller; an overview on low level control is presented in this document.
The CAMBADA team robots are completely autonomous and thus they possess their own perception sensors. The information provided by those sensors is raw and has to be processed to provide better quality information for the agent. Sensor fusion techniques provide the means to achieve this information enhancement and some are discussed in this document. An implementation of a Kalman filter was created and tested to estimate the ball position from the noisy measurements and to detect changes on the ball path, based on a comparison between predicted values and measured values. Also, a linear regression was implemented for estimation of the ball and robot velocities. Due to changes in the MSL rules, that turned the field symmetric from the vision point of view, a new electronic compass was integrated providing a means to verify the results of the position tracking algorithm and hence enhance localisation.
The information resulting from the sensor fusion is kept in a description of the state of the world used by the robot. Some developments were made in this world state representation. Algorithms were created and implemented to allow the agent to check for a set of conditions that are used by the high level decision module.
The developments on sensor fusion and world state representation supported the implementation of new behaviours. The behaviours define “reactions” to a set of conditions, that can be verified through the information of the state of the world, and are the responsibles for defining the commands to be sent down to the low level controllers of the actuators. The intelligent combination of these behaviours allows the robot to act in a defined way on the field. Work at the behaviour level provides better action capabilities, important for the development of effective game strategies. Two new interception behaviours were implemented that allow the robot to intercept the ball by reasoning over its path and the robot capabilities. Also a new algorithm for ball avoidance was developed, for situations like kickoff, throwin and other situations when the game is stopped. In these situations the robots have to reposition themselves on the field without touching the ball. The created algorithm improves the performance by reducing the necessary deviation.
The velocity estimation of the ball was greatly improved and is now much more reliable in game situations. The new behaviours brought a new dynamic to the game and the tools to manipulate the state of the world provided a simplification and improved the modularity of the high level code. In a general way, the developments achieved in the work described by the thesis have improved the overall performance of the team in competition.