The use of mobile robots for teaching automatic control is becoming more popular in engineering curricula. Currently, many robot simulators with high-graphical capabilities can be easily used by instructors to teach control engineering. However, the use of real robots is not as straightforward as simulations. There are many hardware and software details that must be considered before applying control. This paper presents the development of an easy-to-use platform for teaching control of mobile robots. The laboratory has been carefully designed to conceal all technical issues, such as communications or the localization that do not address the fundamental concepts of control engineering. To this end, a position sensor based on computer vision has been developed to provide the positions of the robots on the platform in real time. The Khepera IV robot has been selected for this platform because of its flexibility and advanced built-in sensors but the laboratory could be easily adapted for similar robots. The platform offers the opportunity to perform laboratory practices to test many different control strategies within a real experimental multi-agent environment. A methodology for using the platform in the lab is also provided.INDEX TERMS Robotics education, mobile robot laboratory, vision-based indoor positioning sensor.

No abstract

No abstract

Proximity sensors are broadly used in mobile robots for obstacle detection. The traditional calibration process of this kind of sensor could be a time-consuming task because it is usually done by identification in a manual and repetitive way. The resulting obstacles detection models are usually nonlinear functions that can be different for each proximity sensor attached to the robot. In addition, the model is highly dependent on the type of sensor (e.g., ultrasonic or infrared), on changes in light intensity, and on the properties of the obstacle such as shape, colour, and surface texture, among others. That is why in some situations it could be useful to gather all the measurements provided by different kinds of sensor in order to build a unique model that estimates the distances to the obstacles around the robot. This paper presents a novel approach to get an obstacles detection model based on the fusion of sensors data and automatic calibration by using artificial neural networks.

No abstract