Combining intelligent techniques for sensor fusion

Sensors are used in mobile robots to provide them the necessary information about the environment and allowing its suitable representation. However, sensors data are usually incomplete, inconsistent or inaccurate. Sensor fusion has been successfully employed to enhance the accuracy of sensor measures. In this work, artificial intelligence techniques are investigated for sensor fusion, aiming the improvement of the accuracy and reliability of the distance measure between a robot and an object in its work environment, based on measures obtained from different sensors. The artificial intelligence techniques consist of Machine Learning (ML) algorithms and their combination in committees. The results obtained suggest the potential of combining different sensor fusion techniques in committees.