Search

In the last decades, the focus has shifted towards mobile robots to link predictions, imagination, and expectations to human life in different aspects. A tremendous amount of research on mobile robots indicates their importance in various industrial and non-industrial fields such as production, medicine and agriculture. Despite all of these innovations in the field of robotics, intelligent mobile robots are facing challenges in processing the vast amount of sensory data from their sensory inputs. Due to the increasing amount of sensory data, a new demand is to process sensory inputs in an understandable form for both humans and robots. One approach to processing sensory data in a way that is understandable for both robots and humans is through the use of semantic technology, which is a major technology for building semantic knowledge bases in a machine-readable form. The success of semantic technology is highly reliant on ontologies which are considered the semantic knowledge representation. The huge amount of research in this field proves the undeniable impact of ontologies in the field of robotics. Yet, the work concerning the conversion of the sensory inputs from a mobile robot into semantic information in real-time are scarce. This transformation becomes more challenging when converting the sensory input of multiple sensors to a single semantic statement. The collection of semantic information for real-time ontology population is another challenge. In this regard, there is also a lack of work in transferring and using this information for natural language communication between humans and robots. This work addresses these challenges and employs semantic technology in the field of robotics to enable a mobile robot to create semantic information during exploration. In addition, the resulted semantic information is used for communicating information as well as facilitating communication between other robots and humans in a natural language.

Modernization of living environments and human activities have severe effects on many parameters and factors such as climate change and global warming, an increase of incidence and the severity of wildfires, land surfaces and ice sheets, ecological imbalance, change of fertility of the soil, flow of energy, food security, etc. In addition, human modernization has had a negative impact on biodiversity and the natural environment. An integral component of modernization is agriculture that associates with the outdoor environment and relevant issues. Automation of agricultural activities contributes to reducing the dependency on human labor and the harmful effects on the natural environment. The correct identification of plants in outdoor environments has been neglected and many critical environmental and non-environmental limits and factors, such as weather conditions, time, viewpoint, lighting conditions (illuminations and light intensity), distance, etc., have not been considered in existing plant recognition systems and technologies. Hence, there is a demand to develop mobile and real-time systems for plant recognition in natural environments. This paper addresses these challenges and introduces the application of autonomous mobile robot and semi-robots for recognition of natural plant species in outdoor environments. Furthermore, the proposed system presents the use of employing low-cost cameras, such as iPhone 6s, Canon EOS 600D and Samsung Galaxy Note 4, for plant recognition system in real-time. The performance of the system has been tested with a number of experiments in different years, 2017 and 2018, and at different times of day, morning and evening. The proposed system is a combination of new technologies involving deep learning concepts and an autonomous field robot to carry out precise plant recognition in challenging environments. The final accuracy of the mobile real-time system is 84.1666%.

The leaf, as the vital part of plants, can be affected by physical and physiological factors which might lead to changes in its shape, color and size. These unique parts play an essential role in the design and implementation of plant recognition systems, as the shapes of leaves vary among different plants. Weather type and related factors, such as light intensity, humidity, temperature and wind-speed, may have effects on the number of leaves that grow on a plant, the amount of fresh and dried leaves, the deformation of leaves, color of leaves, positions of leaves on branches, etc. In addition, photographing in outdoor environments with different weather conditions has undesired impacts on images. For instance, light scattering changes severely when there are water droplets during photographing which influences the images captured in rainy weather. Despite the importance of the proposed factors and the relevant effects on the plants, leaves and images taken from plants, a plant recognition system should be independent from all environmental and non-environmental factors to be practically useful and applicable for identifying plant species in uncontrolled outdoor environments. Moreover, changes in the time of day (morning, noon and evening), the distance between camera and plant species as well as the angle and illumination of the object and environment when the images are taken should be considered in the process of plant recognition. For instance, in a windy weather condition, for an observer even from a short distance, it is challenging to distinguish all single leaves and identify the plant type from the shape of its leaf. Furthermore, the unstructured background of the images is another challenge which affects the images captured in fields and outdoor environments. These are only some difficulties for identification of plants in natural environments such as farms, forests, etc. A consideration of mentioned factors contributes to developing a novel, efficient and accurate system for plant recognition that can be used in various uncontrolled outdoor environments. In the real-life, the images of the plants captured with the presence of these factors are very challenging for recognizing plant species and it is a desire to develop an efficient and accurate system that can be used in various natural conditions and uncontrolled situations. This paper presents the development and implementation of a convolutional neural network for automatic plant recognition in uncontrolled outdoor environments. The deep network has been used to recognize four different natural plant species. The proposed system brings the opportunity and transformative potential of deep neural networks to the plant recognition field. This fully-automatic system is efficient and generalized for recognition of plants in outdoor environments like forests and farms, and its the accuracy is 99.5%. Meanwhile, the final system has the functionality of being applied as a real-time one.

Today, thanks to the advancement of robotics and intelligent new technologies, robots are entering more and more into different areas of human life. In doing so, the interaction between humans and robots, involving solving tasks both supervised and collaborative, becomes increasingly important as they both rely on smart approaches for communication. Throughout the human-robot and robot-robot communication, the utilized technology has to be able to describe information that is semantically rich, structurally efficient concerning description and time efficient regarding the retrieval of information. This work utilizes the resource description framework (RDF), as one of the core technologies of the semantic web to describe the navigation of a mobile robot semantically in an ontology which is populated in real-time. This research proposes a new and efficient way of expressing semantic relationships within the navigation ontology by using helper nodes. In contrast to existing approaches, it could be shown that the use of helper nodes can cut down the generation of nodes by a factor of two, improving the storage but also the utilization for a time efficient communication.

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. In den letzten Jahren hat sich die Verbindung mobiler Roboter mit diversen menschlichen Aktivitäten deutlich intensiviert und sie beginnen die in sie gesetzten Erwartungen und Vorstellungen zunehmend zu erfüllen. Die tsunamiartig wachsende Zahl an Forschungsarbeiten im Bereich der mobiler Robotik spiegelt ihre Bedeutung in verschiedenen Bereichen wider, z. B. in der Industrie, der Landwirtschaft und der Medizin. Zusammen mit neuen Entwicklungen in der Sensorik erleben wir, wie immer intelligentere mobile Roboter anspruchsvolle Aufgaben lösen, indem sie große Mengen an Daten verarbeiten, die von verschiedenen Sensoren erfasst werden. Die Flut der Sensordaten erhöht die Notwendigkeit der Verarbeitung sensorischer Eingaben in einer für Mensch und Roboter verständlichen Form. Ein Ansatz für eine verständliche Weiterverarbeitung der Sensordaten ist die Verwendung von semantischer Technologie. Die semantische Technologie spielt eine zentrale Rolle beim Aufbau semantischer Wissensbasen in maschinengeeigneter Form. Für diesen Zweck sind Ontologien eine ausgereifte, flexible und wohluntersuchte Form der Realisierung. Eine beträchtliche Anzahl an Untersuchungen zeigt den Einfluss von Ontologien auf dem Gebiet der Robotik. Es fehlt jedoch immer noch an Arbeiten, die sich mit der semantischen Echtzeit-Wissenserfassung gespeist aus den Sensoren mobiler Roboter befassen. Ebensowenig ist es bisher üblich Ontologien in Echtzeit aus Sensordaten zu erzeugen bzw. sie mit solchen zu befüllen und damit letztendlich eine Kommunikation zwischen Mensch und Roboter in natürlicher Sprache zu ermöglichen. Diese Arbeit wendet semantische Methoden auf die mobile Robotik an. Dies dient dem besseren Verständnis der Umgebung, die durch Sensoren und Navigation im Roboter abgebildet wird, und der mitlaufenden Erzeugung semantischer Informationen aus diesen Daten, um mit anderen Robotern und Menschen zu kommunizieren. In dieser Studie wird das Resource Description Framework (RDF), ein semantischer Web-Standard, für die sofortige Erzeugung semantischer Informationen aus den sensorischen Daten während der Navigation mit einem mobilen Roboter verwendet. Ein neuer Ansatz für die Modellierung komplexer RDF-Beziehungen wird vorgestellt. Verschiedene Sensordaten des mobilen Roboters werden kombiniert, um damit komplexe RDF-Aussagen zu erzeugen. Diese repräsentieren Inter-Objekt-Relationen zwischen Orientierungspunkten in einer Art und Weise, wie Sie ein Mensch aufstellen würde, während sich der Roboter in der Umgebung bewegt. Diese Aussagen werden gesammelt und in einer Ontologie gespeichert. Infolgedessen wird eine neuartige, effiziente Ontologie geschaffen, die in Echtzeit besetzt und getestet wird. Das hier entwickelte Konzept beinhaltet eine natürlich sprachliche Schnittstelle, die es Menschen erlaubt in gewohnter Weise mit Robotern über räumliche Vorgänge zu "sprechen". Um das System zu evaluieren, wurde ein mobiler Roboter simuliert und mit verschiedenen Sensoren ausgestattet. Dieser Roboter wurde in einer simulierten Umgebung platziert, um in dieser zu navigieren und diese zu erforschen. Während der Navigation werden Sensordaten gesammelt und verarbeitet, um semantische Informationen zu erzeugen, welche die Strecke und die Wahrnehmung der Umgebung repräsentieren. Die vordefinierte Ontologie wird dann mit diesen Informationen in Echtzeit gefüllt. Sie wird vom System verwendet, um die Kommunikation mit dem Roboter bezüglich seiner Umgebung zu erleichtern. Die in Echtzeit aufgebaute Ontologie -zumeist bestehend aus in RDF-Aussagen gegossene Sensordaten- beschreibt die gefahrene Strecke des mobilen Roboters und die zugehörige Umgebung. Die Effizienz des Systems, Sensordaten in semantische Informationen zu transformieren, die Fähigkeit des mobilen Roboters, seine reale Umgebung semantisch zu beschreiben und die Fähigkeit, Fragen über die Strecke und die Umgebung in natürlicher Sprache zu beantworten, sind Beweis für die Funktionalität des hier vorgestellten Systems.

Today, thanks to the advancement of robotics and the achievements that are made in the light of the development of automated and intelligent technologies, we are increasingly witnessing the arrival of robotic devices and machines into different areas of human life. With all of the achievements and their intelligence, the degree of their proficiency relies in many cases on their ability to interact with human beings. To do so, for a mobile robot the ability to understand its surroundings and also to describe it in a way that human can easily understand is vitally important. “Above”, “below”, “in front of”, “behind of”, “left of” and “right to” are prepositions that human uses in daily life to describe not only the relationship between objects but also to provide one’s location implicitly. The Resource Description Framework, RDF, as one of the semantic web core components, can be employed for forming those prepositions. The idea is to utilize a smart sensor of a simulated, mobile robot for creating semantic information in RDF format that represents inter-object relations by using the same spatial prepositions that human uses in his daily life to describe his environment.

By the increase of automation, many questions arise about the future of robots in human life, how a robot can communicate with another robot, how it can communicate with a human, and how it can interact with objects of its surrounding-these are some of the critical questions to be answered. For the robot to be able to answer questions and intelligently interact with its environment, it is essential to have a proper understanding of its surrounding; therefore, information must be represented in a way in which a robot can understand them. Semantic technology provides some tools and techniques for expressing information that is understandable by both human and robots. This work presents a novel approach of using Resource Description Framework, RDF, which is a semantic web tool for representing information semantically in the robotics field. For this purpose, a simulated mobile robot equipped with a simulated camera sensor is located in a simulated outdoor environment for navigation. The output of the simulated sensor is collected and converted into a set of statements in RDF format; the obtained statements provide meaning to the detected objects in a way that a robot can understand and utilize.

A 72-year-old right-handed woman presented with a 6-month history of right thoracic wall discomfort. An MRI of the thoracic spine showed a small dumbbell-shaped mass centered within the right T7-8 foramen. The patient was asked to return to clinic for reevaluation to include a new MRI of the thoracic spine in 6 months. She did not comply with this recommendation and 1 year later, she presented with increasing difficulty ambulating and spastic paraparesis. A follow-up MRI of the thoracic spine now demonstrated significant interval growth of the mass with an extra-foraminal component extending into the thoracic cavity. She was taken to the operating room for resection of the epidural tumor. The pathology was consistent with diffuse follicle center lymphoma as cells were immunohistologically positive for CD20, CD 10, BCL-2 and BCL-6. Primary spinal follicle center lymphomas of the spine are rare with the current case being the first diffuse follicle center type reported in the literature.