Autonomous drone technology holds significant promise for enhancing search and rescue operations during evacuations by guiding humans toward safety and supporting broader emergency response efforts. However, their application in dynamic, real-time evacuation support remains limited. Existing models often overlook the psychological and emotional complexity of human behavior under extreme stress. In real-world fire scenarios, evacuees frequently deviate from designated safe routes due to panic and uncertainty. To address these challenges, this paper presents a multi-agent coordination framework in which autonomous Unmanned Aerial Vehicles (UAVs) assist human evacuees in real-time by locating, intercepting, and guiding them to safety under uncertain conditions. We model the problem as a Partially Observable Markov Decision Process (POMDP), where two heterogeneous UAV agents, a high-level rescuer (HLR) and a low-level rescuer (LLR), coordinate through shared observations and complementary capabilities. Human behavior is captured using an agent-based model grounded in empirical psychology, where panic dynamically affects decision-making and movement in response to environmental stimuli. The environment features stochastic fire spread, unknown evacuee locations, and limited visibility, requiring UAVs to plan over long horizons to search for humans and adapt in real-time. Our framework employs the Proximal Policy Optimization (PPO) algorithm with recurrent policies to enable robust decision-making in partially observable settings. Simulation results demonstrate that the UAV team can rapidly locate and intercept evacuees, significantly reducing the time required for them to reach safety compared to scenarios without UAV assistance.

"The collaboration with Festo goes beyond applying classical machine learning by focusing on reinforcement learning, which is currently a very active …

The High-Performance Computing Center Stuttgart (HLRS) has contracted with supercomputer manufacturer Cray, a Hewlett-Packard Enterprise company, to install a new Cray CS-Storm GPU-accelerated supercomputer. The new machine will complement HLRS's current infrastructure for high-performance computing by addressing user demand for processing-intensive applications like machine learning and deep learning. The system is designed for artificial intelligence (AI) applications and includes the Cray Urika-CS AI and Analytics suite, enabling HLRS to accelerate AI workloads, arm users to address complex computing problems, and process more data with higher accuracy. The machine will be used in developing AI models in engineering, automotive, energy, and environmental industries and academia. "As we extend our service portfolio with AI, we require an infrastructure that can support the convergence of traditional high-performance computing applications and AI workloads to better support our users and customers," said Prof. Dr. Michael Resch, director at HRLS. "We've found success working with our current Cray Urika-GX system for data analytics, and we are now at a point where AI and deep learning have become even more important as a set of methods and workflows for the HPC community. Our researchers will use the new CS-Storm system to power AI applications to achieve much faster results and gain new insights into traditional types of simulation results."

SEATTLE, Oct. 24, 2019 (GLOBE NEWSWIRE) -- Global supercomputer leader Cray, a Hewlett Packard Enterprise company (NYSE: HPE), today announced that the High-Performance Computing Center of the University of Stuttgart (HLRS) in Germany has selected a new Cray CS-Stormä GPU-accelerated supercomputer to advance its computing infrastructure in response to user demand for processing-intensive applications like machine learning and deep learning. The new Cray system is tailored for artificial intelligence (AI) and includes the Cray Urika -CS AI and Analytics suite, enabling HLRS to accelerate AI workloads, arm users to address complex computing problems and process more data with higher accuracy of AI models in engineering, automotive, energy, and environmental industries and academia. "As we extend our service portfolio with AI, we require an infrastructure that can support the convergence of traditional high-performance computing applications and AI workloads to better support our users and customers," said Prof. Dr. Michael Resch, director at HRLS. "We've found success working with our current Cray Urika-GX system for data analytics, and we are now at a point where AI and deep learning have become even more important as a set of methods and workflows for the HPC community. Our researchers will use the new CS-Storm system to power AI applications to achieve much faster results and gain new insights into traditional types of simulation results." Supercomputer users at HLRS are increasingly asking for access to systems containing AI acceleration capabilities.

Location management refers to the problem of updating and searching the current location of mobile nodes in a wireless network. To make it efficient, the sum of update costs of location database must be minimized. Previous work relying on fixed location databases is unable to fully exploit the knowledge of user mobility patterns in the system so as to achieve this minimization. The study presents an intelligent location management approach which has interacts between intelligent information system and knowledge-base technologies, so we can dynamically change the user patterns and reduce the transition between the VLR and HLR. The study provides algorithms are ability to handle location registration and call delivery

We describe a unifying method for proving relative loss bounds for online linear threshold classification algorithms, such as the Perceptron and the Winnow algorithms. For classification problems the discrete loss is used, i.e., the total number of prediction mistakes. We introduce a continuous loss function, called the "linear hinge loss", that can be employed to derive the updates of the algorithms. We first prove bounds w.r.t. the linear hinge loss and then convert them to the discrete loss. We introduce a notion of "average margin" of a set of examples. We show how relative loss bounds based on the linear hinge loss can be converted to relative loss bounds i.t.o. the discrete loss using the average margin.

We describe a unifying method for proving relative loss bounds for online linearthreshold classification algorithms, such as the Perceptron and the Winnow algorithms. For classification problems the discrete loss is used, i.e., the total number of prediction mistakes. We introduce a continuous lossfunction, called the "linear hinge loss", that can be employed to derive the updates of the algorithms. We first prove bounds w.r.t. the linear hinge loss and then convert them to the discrete loss. We introduce anotion of "average margin" of a set of examples . We show how relative loss bounds based on the linear hinge loss can be converted to relative loss bounds i.t.o. the discrete loss using the average margin.