Researchers from the European Centre for Soft Computing and the UPM’s Facultad de Informática have developed an antonym-based technique for building maps for mobile robots. This technique can be applied to improve current robot navigation systems. Another advantage of the technique is that the low-cost ultrasonic sensors that it uses are built into almost all robotic platforms and produce a smaller volume of data for processing.
An autonomous mobile robot is a robot that is able to navigate its environment without colliding or getting lost. Unmanned robots are also able to recover from spatial disorientation. Conducted by Sergio Guadarrama, researcher of the European Centre for Soft Computing, and Antonio Ruiz, assistant professor at the Universidad Politécnica de Madrid’s Facultad de Informática, and published in the Information Sciences journal, the research focuses on map building. Map building is one of the skills related to autonomous navigation, where a robot is required to explore an unknown environment (enclosure, plant, buildings, etc.) and draw up a map of the environment. Before it can do this, the robot has to use its sensors to perceive obstacles.
The main sensor types used for autonomous navigation are vision and range sensors. Although vision sensors can capture much more information from the environment, this research used range, specifically ultrasonic, sensors, which are less accurate, to demonstrate that the model builds accurate maps from few and imprecise input data.
Once it has captured the ranges, the robot has to map these distances to obstacles on the map. Point clouds are used to draw the map, as the imprecision of the range data rules out the use of straight lines or even isolated points. Even so, the resulting map is by no means an architectural blueprint of the site, because not even the robot’s location is precisely known, and there is no guarantee that each point cloud is correctly positioned. In actual fact, one and the same obstacle can be viewed properly from one robot position, but not from another. This can produce contradictory information -obstacle and no obstacle- about the same area of the map under construction. Which of the two interpretations is correct?
Exploring unknown spaces
The solution is based on linguistic descriptions of the antonyms “vacant” and “occupied” and inspired by computing with words and the computational theory of perceptions, two theories proposed by L.A. Zadeh of the University of California at Berkeley. Whereas other published research views obstacles and empty spaces as complementary concepts, this research assumes that, rather than being complements, obstacles and vacant spaces are a pair of opposites.
For example, we can infer that an occupied space is not vacant, but we cannot infer that an unoccupied space is empty. This space could be unknown or ambiguous, because the robot has limited information about its environment. Also the contradictions between “vacant” and “occupied” are also explicitly represented.
This way, the robot is able to make a distinction between two types of unknown spaces: spaces that are unknown because information is contradictory and spaces that are unknown because they are unexplored. This would lead the robot to navigate with caution through the contradictory spaces and explore the unexplored spaces. The map is constructed using linguistic rules, such as “If the measured distance is short, then assign a high confidence level to the measurement” or “If an obstacle has been seen several times, then increase the confidence in its presence,” where “short,” “high” and “several” are fuzzy sets, subject to fuzzy sets theory. Contradictions are resolved by a greater reliance on shorter ranges and combining multiple measures.
Compared with the results of other methods, the outcomes show that the maps built using this technique better capture the shape of walls and open spaces, and contain fewer errors from incorrect sensor data. This opens opportunities for improving the current autonomous navigation systems for robots.