The aim of KI-SecAssist is the development of autonomous assistance modules based on cooperative task management and various UAV and UGV systems with integrated multi-sensor Payload. The development of AI-based solution approaches enables cooperative multimodal interaction strategies between several UAVs ("Fixed Wing" and "Multi-Rotor" systems) and UGVs and thus an intelligent interaction of the individual systems into one Optimized assistance for emergency services geared towards special application scenarios. The UAV- / UGV- Systems have different performance parameters as well as one different sensors, geared to the requirements of the individual scenarios and enable near real-time on-board Situation analysis. A cooperative task management is administered Tasks and goals, prioritized and generated on the basis of situation Changes to new tasks and delegates the autonomous processing of tasks to the UAV / UGV systems. The result from KI-SecAssist is a modular proof-of-concept functional demonstrator, incl. Tests, exercises and evaluation related to the functional, Performance and practical suitability for an optimized assistance service for emergency services in crisis and disaster scenarios.

In order to increase trust in robot systems and reduce cognitive load, the project aims to develop well-founded methods for measuring trust in assistance systems and the cognitive load caused by their use. Furthermore, options for intervention in (1) the design of the user interface for input and output, (2) the degree of autonomy and (3) the transparency of decisions by the robot that allow an improvement of these parameters are to be examined. The primary innovation of the project is that trust and the cognitive load as well as measures to improve them are thoroughly investigated in an interdisciplinary team (psychologists, visualization experts, robotics, emergency services). The planned direct coupling of the assessment of trust and cognitive load with possible changes in the interaction design and the behavior of the robot will provide new insights into the nature of trust in assistance robots and enable the development of improved assistance systems. The immediate practical benefit of this knowledge is evaluated in realistic field tests with emergency services.

In this project, research will be carried out to document thermal engineering applications in which system improvements can be achieved through innovative control approaches. In doing so, not only methods known from control and system engineering will be considered, but also artificial intelligence (AI) methods in particular. To substantiate the potential for further research activities regarding AI in thermal engineering, a comparison between conventional control strategies and AI-based methods is aimed at.

Automated robot systems that are able to navigate in remote and challenging environments like alpine regions be a significant help end users mountain or constructors or of infrastructure (e.g paths or installation for protection). Such robots can perform automated transport of materials, tools, and persons as well as the automated execution of construction or maintenance actions (although the development of the actual manipulation actions is beyond the scope of this project). Endurance and payload issues renders the deployment of ground robots more realistically. Two main issues arise when deploying such robots in remote and difficult terrain. First in contrast to humans robots usually need a rather detailed maps of their environment to perform navigation; deriving and execution an efficient and safe path to a given goal. In engineered environments like urban areas or highways such detailed maps are available. In remote or unstructured areas these maps needed to be generated beforehand either by the robot itself or by other means like airborne systems. The fact that detailed maps for remote areas do not exist and the expensive pre-mapping step are obstacle for fast and efficient deployment. Second humans are capable to navigate in a challenging environment even with a less detailed map and a rough given route because of their superior perception and motion skills. Robots in contrat still need very detailed map and a high accuracy in their localization to perform challenging navigation task. In order to allow a ground robot to navigate efficiently and safely in remote areas to support end use activities RoboNav will aim at three main goals. First in close cooperation with the end users use cases will be defined that are relevant for the users but are also realistic and helpful for the participating users. The definition of promising use cases andrealistic requirements will maintain realistic expectations and acceptance by the users. The second goal of RoboNav is the development of a pipeline to convert earth observation data into routing data that can be used for the navigation. The important goal is here to avoid extensive preparation campaigns such as detailed mapping of the environment with the robot system itself or other systems like UAVs. Animportant innovation is here that the obtained routing data will be generated depending on the robot’s locomotion capabilities in order to allow broad and easy application of the approach. The third goal of RoboNav is to develop an integrated navigation concept that is suitable for automated navigation of a robot in the envisioned challenging environments. In order to achieve this goal the views and competences of two research disciplinesneed to be combined: geodesy and robotics. A suitable navigation concept including localization, routing and guidance will be replicated for the purpose of an automatically moving robot. The proposed navigation system will be implemented and integrated into a robot platform demonstrator. The integrated system will be evaluated in realistic field trials defined in cooperation with the end users. Deployments in the field but will also form a base for an economic exploitation by young participating companies from both disciplines.

The aim of ROBO-MOLE is to increase the safety for responder and civilians in tunnels or other sub-terrain buildings by the detection and identification of hazard materials, providing an actual situation map and to improve the efficiency of disaster response missions. For instance after a accident with a dangerous goods transporter in a tunnel responder are faced with severe and dangerous challenges due to heat, structural danger, smoke or exposure to hazard material. Thus, a semi-autonomous robot for supporting analyzing tasks will be developed, that is equipped with a broad range of sensors (position, imaging, hazard material). The information of these sensors will be fused to allow safe navigation and control of the robot under challenging conditions (smoke, heat, debris) and to detect and map hazards.

The increasing digitalization and automation through the use of Artificial Intelligence (AI) of the working world (industry 4.0, Smart Logistics, Big Data, etc.) and our everyday life(assistance systems, smart devices, social media, etc.) posts great challenges for society and education. This ranges from building awareness, increasing acceptance and teaching thefoundations of the technology, to fostering a meaningful, creative usage as well as an assessment of threats, risks as well as opportunities and potentials. The program area ischaracterized by a few urban centers and a large number of rural regions. To prevent a brain drain from the program area as well as to ensure a sustainable and responsible usageof technology, young people with skills to understand and use these new technologies are required. AI applications in particular allow an added value away from urban centers orwithout access to natural resources. Stimulating enthusiasm as well as facilitating a basic understanding has to be done at an early age. This provides a sound basis for youngpeople’s decision to pursue a career (job, training, study) in an AI related sector. The project addresses these challenges at two levels: On the one hand, fostering young people’s(aged 10-14) interest in AI and facilitating a basic technical understanding at an early age. In this context, the integration of teachers and instructors, using a train-the-trainerapproach is the key and ensures a broad and sustainable dissemination. On the other hand, building awareness regarding social, economic and technical aspects and potentials of AIamong the general public (children, parents, apprentices, working persons, etc.) using open, low-threshold activities. Since the described challenges concern the entire program area,a cross-border project implementation is vital.

This project aims to investigate the possibilities for a passive infrastructure-less self-localization by vehicles for navigation purposes. Such localization is an essential precondition for the half-autonomous control of convoys, which was raised by the military user. Up to here autonomous car navigation in nearly all variants is supported by global navigation satellite systems (GNSS) and / or active sensors (radar, lidar). For reasons of defilade active means must be waived. Off-road driving conditions do not offer any infrastructure. And GNSS must be waived, too, since it aggressively may be jammed or spoofed. The remaining means are mainly camera based localization, inertial navigation and the evaluation of the vehicle’s sensor data. It is now necessary to investigate by which algorithms and methods a reliable localization is possible, based on only these reduced means. These are now the goals of the project, to reach an automated vehicle’s localization under the above mentioned conditions. Firstly it is necessary to obtain realistic data sets from cameras, inertial measurement unit (IMU) and from the vehicle’s sensors and to emulate autonomous driving conditions. For this purpose drive-by-wire capabilities of the test vehicles will be implemented, which up to here is prohibited in road traffic. Using drive-by-wire omits those characteristics of the vehicle’s control, which are generated by the driver’s subjective impressions. Especially in off- road conditions reflexive reactions by the driver may be significant. In a totally new approach the data from the cameras, from the IMU and from the vehicle’s sensors will be used to generate a map of the driven path and to estimate the vehicle’s location with respect to the map. Obstacles will be recognized and the vehicle will be stopped. Technology readiness level 1 (TRL 1), the proof of the basic principle, is already given and is the starting point of the project. With the successful experimental proof finally TRL 3 will be prepared and reached. According to the low TRL, some simplifying conditions will be established, like a speed limit of 30 kilometers per hour or constant vegetation conditions. Target goals and findings are the successful implementation of a demonstrator of principle. For validation purposes a reference trajectory with all available means (GNSS, etc.) will be acquired, too. The found trajectory in comparison with the reference trajectory finally shall reach an accuracy which is acceptable for the targeted application. Challenges in the methods shall be recognized and shall be accordingly be addressed. Visual localization, inertial navigation and also the evaluation of the vehicle’s sensor data are affected by systematic inaccuracies, which is to be eliminated by data fusion techniques as much as possible. The concrete project results are the algorithms for determining the trajectory, which are openly explained and documented in the project’s reports. Further the acquired data sets and their analyses are part of the project results and the documentation of the experimental setup.

The Project RoboCar aims at a new approach in the development of autonomous driving vehicles based on the integration of an existing highly flexible prototype research vehicle as well as object recognition and vehicle control algorithms from robotic science. The prototype vehicle is driven by four independent hub motors that provide manoeuvrability and driving function far beyond automotive standards. Enhanced Know-how from robotic disciplines comprises sensor technology, navigation algorithms and the autonomous vehicle control system. With the integrated research vehicle, several autonomous driving testing scenarios will be carried out at a university campus to enable comprehensive evaluation and potential assessment of the technology. In this way, the potentials of new technological approaches are assessed and analysed by support of objective and rational evaluation of strengths and weaknesses to facilitate decision-making processes for strategic technological determinations in view of future R&D projects.

The future development of the economy, prosperity and quality of life in Europe will strongly depend on the following factors. Modern processes and methods are crucial for competitive products on a global scale. Smart production as the interplay of robotics, computer science and artificial intelligence (AI) will become more and more important. Furthermore, novel and innovative products and services will be necessary to develop the economy sustainably. In order to enable such products young people with knowledge and skills in robotics and AI will be needed. An appropriate developed labour market will significantly contribute to the strategic goals (smart, sustainable, inclusive growth) given by the underlying cooperation programme. Novel ideas and improved human capital enable companies to generate qualitative jobs in the project region. All this will contribute to the strategic goals as well as the operative goal of strengthening the labour market. In order to achieve this we propose to establish a standardized training and certification system for young people in the areas of robotics and AI. The training will be on a high professional level allowing the young people to develop an exceptional and satisfying career. A professional certification system similar to the ECDL as well as the involvement of stakeholders (educational institutions, public institutions, companies, …) in the project development will foster a great acceptance of the provided training system and will also allow companies and educational institutions to recognize the obtained skills of young people. The "train the trainer" approach will allow to roll out the system in the entire project region. Because the above problems exist in all areas of the project region such a project needs to be developed in a cross-border fashion.

TU Graz works togehter in Styria to evaluate the possibility of autonomous driving on streets in downtown Graz.

It is predicted that over 50 billion intelligent objects - smart things - will communicate with each other in the Internet of Things by 2020, allowing for numerous everyday applications. For example, cars will be able to communicate with each other on the streets to prevent accidents, and tailor-made furniture will be able to tell industrial production machines what exactly needs to be done to them. One day, the Internet of Things will be as important as the power grid is today. There is, however, still much research to be done, especially regarding the reliability of the Internet of Things. In particular, critical applications in health, traffic and production need to function perfectly at all times. Lead project researchers in the Field of Expertise Information, Communication & Computing at TU Graz are working on fundamental aspects that will enable computers embedded into everyday objects to function reliably, even under the most difficult conditions.

follows - wird nachgereicht (20140813 SG)

First Responder frequently face critical situations whose reconnaissance and handling is significantly afflicted with personal risks. Modern robot technology can help to reduce these risks. Because of different technical and economic reasons such technology is hardly used by first responder nowadays. The aim of this project is to develop a model that allows first responder to request robot technology and experts easily and quickly in a crisis situation. The advantage of this model is that first responder to not have to hold available such complex and expensive technology and that it remains with an external specialized organization for training, maintenance and operation. First Responder frequently face critical situations whose reconnaissance and handling is significantly afflicted with personal risks. Moreover, due to critical weather situations and increased use of technology in daily life there are situation in which even response experts do not have access anymore (mudslide, hazard materials). Modern robot technology can help to reduce these risks and restrictions. Because of different technical and economic reasons such technology is hardly used by first responder nowadays. The aim of this project is to develop a model that allows first responder to request robot technology and experts easily and quickly in a crisis situation. Similar models already exist to request experts in chemistry or geology. The advantage of this model is that first responder to not have to hold available such complex and expensive technology and that it remains with an external specialized organization like an university or a company for training, maintenance and operation. In order to establish such a model realistic use cases have to be identified in cooperation with first responder. Based on these use cases tactical, technical and juridical requirements have to be defined to allow for an effective and save integration of external robots and experts into daily routine. Moreover, regulations for the external technology partner in terms of maintenance, documentation, training and standby service have to be defined in order to guarantee continuous technical quality and fast response times. The declared aim of the project is to develop a workable and well-founded model for the provision of robot technology to first responder. Moreover, the model has to be mature in order to be deployed in real missions without further development.

In this project we investigate how automated testing and diagnosis can be used to improve the dependability of service robots in industrial envinronments. In particular the project focuses on the reuse of models and the integration into the development process.

folgt

If an autonomous robot has to robustly act in a dynamic real world environment, it has to be able to autonomously cope with unexpected, unforeseen or ambiguous situations. A common reason for such situations is that the current state of the world is inconsistent with the internal belief or knowledge base of the robot. For instance the robot believes that it is in a different office as it is in reality. Usually this is caused by uncertainties in the robots acting and sensing or by exogenous events the robot is not able to perceive or to control. If a robot is not aware of such situations it is doomed to fail in fulfill its task because the decision making of the robot relies on a consistent belief. Due to its reasoning capabilities humans are very good in handling such phenomena. They use common sense reasoning to detect such inconsistencies. Moreover, they are able to perform actions in order to reduce inconsistencies. For instance if a person does not exactly know in which floor of a building it may go back to the elevator or stair case and look for the right floor. In the project we propose a reasoning approach which allows a robot to detect inconsistencies in its belief (abstract knowledge base) and to derive repair actions which remove or at least reduce inconsistencies in its belief. The approach uses a background model (common sense knowledge) about how the robot and its environment should work and methods of model-based diagnosis to detect inconsistencies in the belief and to locate the root cause for the inconsistency, e.g., facts which are wrong or uncertain. Furthermore, the approach automatically generates repair plans the robot is able to perform in order to reduce the inconsistency by confirming or deleting facts from the knowledge base.

Diagnose von Förderanlagen

The aim of this project is to integrate runtime diagnosis of hardware and software of autonomous robot systems in a unified way. For this, a common model needs to be developed on which to apply model-based diagnosis techniques. Autonomous mobile robots represent a particularly well suited application for diagnosis tasks. Their autonomous nature implies that they need to reason about their state as there might not always be a supervising human operator. A robot should at all times aim to maintain functionality or try to retain as much system functionality as possible. Repair actions might lead to a fully functioning state after a fault has been diagnosed. Reconfiguration might retain functionality to a certain degree. In the worst case, the robot might reconfigure itself to switch to a fail-safe mode to avoid further damage or threats to nearby people. For example, diagnosis that the vision sensor is malfunctioning could lead to a reconfiguration where other sensors, e.g., a laser range scanner, are used. This might also require to use a different mode of operation, i.e., software reconfiguration. If, however, the video device driver causes problems while the actual video device is still fully functioning, a restart of the video device driver and all dependand services might be a sufficient repair action to restore normal behaviour. As can be seen from this example hardware and software are tightly coupled and need to be modeled together. In this project the feasibility of a unified diagnosis approach is to be evaluated. The modular robotic platform created at Graz Technical University will serve as a test-platform for case-studies on modelling hardware, software, interfaces between hardware and software and interfaces between the abstract control and diagnosis layers. These robots are used for office delivery tasks and robotic soccer, and will serve as target for a case-study. Diagnosis on these models is to be integrated with repair and reconfiguration.

Erstellung von prototypischer Software, die für die Erfüllung der Machbarkeitsstudie notwendig ist. Durchführung praktischer Tests der Software basierend auf bereitgestellter Hardware. Spezifikation von Sensoren

Erstellung von prototypischer Software, die für die Erfüllung der Machbarkeitsstudie notwendig ist. Durchführung praktischer Tests der Software basierend auf bereitgestellter Hardware. Spezifikation von Sensoren

The Robot Soccer World Cup (known as the RoboCup) Games and Conferences are a series of competitions and events designed to promote the full integration of AI and robotics research. Robotic soccer provides a good test-bed for evaluation of various research, e.g. artificial intelligence, robotics, image processing, system engineering and multi-agent systems. In the Middle Size League (MSL) teams of fully autonomous robots with a size of up to 50cm x 50cm x 80 cm play soccer against each other. The MSL provides a serious challenge for many research disciplines including multi-robot cooperative teams, autonomous navigation, sensor fusion, vision-based perception, automatic reasoning, and mechanical design, to name only a few. All these topics have to be tackled in order to solve the RoboCup challenge. Therefore, RoboCup needs truly interdisciplinary research. Furthermore, approaches developed in the MSL will find their way to applications in other domains like service robots. As mentioned above research in the field of autonomous mobile robots is a very interdisciplinary and wide area. Therefore, hardly any group is able to achieve high quality research in all topics. Our group concentrates its work on flexible, symbol-based and robust approaches for the control of autonomous mobile robots in a wide area of domains and for various tasks. We subsume this under the name "Robust Intelligent Control for Autonomous Systems". The main research topics of our group are: robust abstarct control for mobile robots, model-based diagnosis for autonomous systems and sensor-based navigation.