Miguel Hernandez University (SPAIN)
About this paper:
Appears in: INTED2013 Proceedings
Publication year: 2013
Pages: 3074-3082
ISBN: 978-84-616-2661-8
ISSN: 2340-1079
Conference name: 7th International Technology, Education and Development Conference
Dates: 4-5 March, 2013
Location: Valencia, Spain
Robotics has become a very important field of study today in engineering-related degrees. It is important that students learn strategies for controlling robot manipulators and mobile robots to ease certain tasks in industrial environments. To do this, the robots must be equipped with the necessary sensors to be able to acquire information from the environment to know where they are located and how to move to reach the destination points.

Currently, computer vision has spread with this goal, as cameras offer very rich information. In the field of mobile robotics, it is usual to mount a camera on the robot, which acquires images from the environment where the robot moves. Using the information provided by this camera, it is possible to build a map of an unknown environment. Once this map is built, the robot can compute its position within it, using also the information from the images, the control strategy necessary to move to reach an objective.

There are different strategies to extract the necessary information from the images. One of them consists in working with the whole images without extracting landmarks or regions. They are known as ‘appearance based techniques’, and currently they are widely studied and applied to the resolution of real problems.

The resource presented in this paper is designed for students in a master subject where they learn techniques for map building and localization of mobile robots using the appearance-based information extracted from the images captured by the camera the robot carries on it.

We have developed a software tool to be used by the students in this subject. With this tool, the students can fully understand the appearance-based approach in robotics mapping, with the next features:
- Some databases with panoramic images (both grey-scale and colour) of several real environments are included. With these images, the student can test the algorithms they have learned to build the map.
- We have implemented a method to compress the information of the images, based in the discrete Fourier Transform of images.
- We have implemented an algorithm to build a map using an approach based on a set of forces created by some virtual springs among the images the robot has captured along the environment. Students can test how some parameters affect the final map this algorithm computes.
- The student can test how the degree of compression of the visual information affects to the final map.
- The tool is fully interactive. It shows the map building process step by step graphically and, at the end, it shows the layout of the final map and it gives a measure of the error.

This way, we provide students with a tool that allows them to freely test and improve the algorithms they learn in the classroom and it will definitely help them to better understand these algorithms and design new ones.