In modern times, closed-loop control systems (CLCSs) play a prominent role in a wide application range, from production machinery via automated vehicles to robots. CLCSs actively manipulate the actual values of a process to match predetermined setpoints, typically in real time and with remarkable precision. However, the development, modeling, tuning, and optimization of CLCSs barely exploit the potential of artificial intelligence (AI). This paper explores novel opportunities and research directions in CLCS engineering, presenting potential designs and methodologies incorporating AI. Combining these opportunities and directions makes it evident that employing AI in developing and implementing CLCSs is indeed feasible. Integrating AI into CLCS development or AI directly within CLCSs can lead to a significant improvement in stakeholder confidence. Integrating AI in CLCSs raises the question: How can AI in CLCSs be trusted so that its promising capabilities can be used safely? One does not trust AI in CLCSs due to its unknowable nature caused by its extensive set of parameters that defy complete testing. Consequently, developers working on AI-based CLCSs must be able to rate the impact of the trainable parameters on the system accurately. By following this path, this paper highlights two key aspects as essential research directions towards safe AI-based CLCSs: (I) the identification and elimination of unproductive layers in artificial neural networks (ANNs) for reducing the number of trainable parameters without influencing the overall outcome, and (II) the utilization of the solution space of an ANN to define the safety-critical scenarios of an AI-based CLCS.

By using the quantum mechanics phenomenon, quantum computers provide a new dimension of computational power that drastically accelerates solving complex and resource-intensive problems. One of the most evolving but, due to the computation power of standard computers, reasonably limited application domain is natural language processing (NLP). NLP seeks to give interactive systems the ability to understand and manipulate human language. Making systems understand and manipulate human languages requires large amounts of data and computational power during learning as well as during the execution of NLP. For handling these amounts of data like text and audio recordings and the complexity of classical NLP algorithms, quantum computation has emerged as a promising solution. This work gives an extensive overview of this new field, known as quantum natural language processing (QNLP). Introducing the basics of quantum computing, we discuss its use in NLP by explaining the different proposed embedding models, quantum algorithms, and other methods of QNLP. As QNLP is still in its infancy, this comprehensive overview is the foundation that points to the upcoming research direction.

For driving the roads of cities into enjoyable and relaxing places with parks, trees, and seating, a paradigm change in everyone’s commuter behavior is needed. Still, individual transport via cars increases, and thus, the space required for parking and driving these cars shapes our cities — not the people. Next to the space needed, vehicles pollute the environment with CO2, diesel particulate, and even electric cars with tire abrasion. Alternative modes of locomotion, like public transportation and shared mobility, are still not attractive to many people. Intelligent intermodal mobility networks can help address these challenges, allowing for efficient use between various transportation modalities. These mobility networks require good databases and simulation combined into digital twins. This paper presents how such a digital twin can be created in the Simulation of Urban Mobility (SUMO) software using data from available and future city sensors. The digital twin aims to simulate, analyze, and evaluate the different behaviors and interactions between traffic participants when changing commuting incentives. Using the city of Osnabrück and its different available sensor types, the data availability is compared with other towns to discuss how the data density can be improved. Creating a static network from open street data and intersection side maps provided by the city of Osnabrück shows how these data can be integrated into SUMO for generating traffic flows and routes in SUMO based on a database of historical and live data. Within the conclusion, the paper discusses how developing a digital twin in SUMO from static and dynamic data can be improved in the future and what common misconceptions need to be overcome.

Technical devices can enhance safety by warning people of unrecognized obstacles, particularly in traffic, wilderness, and industrial settings. This study aims to identify the most effective vibrotactile stimuli for localization tasks by developing and evaluating various types of vibrotactile alerts presented through a tactile vest with visual patterns. The study design involved comparing the time and consistency of interpreting visual stimuli and subsequent tactile stimuli. The tactile stimuli included: a 'point' vibration on the left or right side of the back, a 'column' pattern of five vibrations on one side of the back, and a 'wave' pattern of vibrations running along the back from left to right or vice versa. The results indicated that reaction times to visual stimuli were significantly shorter than to vibration stimuli, suggesting that visual stimuli are suitable for alert systems with low cognitive load. The 'point' and 'column' patterns were recognized significantly faster and more clearly than the'wave' pattern. Consequently, the haptic vest was classified as a potentially effective low cognitive load device in localization performance. The findings could inform the design of early warning systems for obstacle detection in real traffic situations.