In recent years, mobile robots have helped to link predictions, imaginations, and expectations to human life. The tsunami of research on mobile robots mirrors their importance in various fields, such as production, agriculture and medicine. Alongside the innovations in sensory solutions, we are witnessing more intelligent mobile robots performing more challenging tasks by using the massive amount of data gathered from various sensors. The excess of the sensory data increases the demand for processing sensory inputs in an understandable form for both - humans and robots. One approach for developing understandable processing and exchange is the use of semantic technology. Semantic technology is a major technology for building semantic knowledge bases in machine-readable form, with ontologies as a mature, flexible and well researched implementation.
A considerable amount of research shows the existing impact of ontologies in the field of robotics. However, there is still a lack of work in regard to the real-time semantic knowledge acquisition from sensory outputs of different sensors for mobile robots and the use of sensory data for real-time ontology population and consequently natural language communication between humans and robots. This work employs semantic technology in the field of robotics to acquire a better understanding of an environment, navigated and sensed by a mobile robot and to continuously produce semantic information to facilitate communication between other robots and human beings.
In this research, the Resource Description Framework (RDF), which is a semantic web standard, is utilized for the instant creation of semantic information from sensory outputs during navigation with a mobile robot. A novel approach for modeling complex RDF relations has been introduced; it uses a combination of sensory data from various sensors of a mobile robot to model single complex RDF-statements that represent inter-object relations between detected landmarks while exploring the environment with a mobile robot in a way that humans would express it. These statements are then collected and stored in an ontology, hence, a novel, efficient ontology is then designed for the real-time, online population; this is then tested in real-time. The proposed concept utilizes a natural language communication interface to facilitate real-time human-robot communication regarding the navigation and environment that has been explored.
To evaluate the system, a mobile robot has been simulated and equipped with different sensors and placed in a simulated environment to navigate and explore the environment. While exploring, sensory data is collected and processed to model semantic information representing its tour and vision of its environment. The ontology is then populated with this information in real-time and is used by the system to facilitate natural language communication with the robot regarding its tour and the explored environment.
The results show the real-time population of the ontology with RDF-statements created from sensory outputs representing the tour of the mobile robots and the environment in a semantic representation. The efficiency of the system in transforming sensory data into semantic information, the ability of the mobile robot to describe the real-world environment semantically, and also its ability to answer natural language questions regarding its tour and the environment are proof of the soundness of the proposed system.