This paper presents S-RGM ^* , a sampling-based approach utilizing a geometric model specifically adapted for path planning in unmanned aerial manipulators designed for pick-and-place applications. As the demand for autonomous aerial systems grows in sectors such as inspection, delivery, and maintenance, efficient trajectory planning for manipulators mounted on unmanned aerial vehicles (UAVs) becomes crucial. The proposed approach leverages a geometric model to enhance the accuracy and reliability of path planning, addressing key challenges related to obstacle avoidance, accessibility, and precise object manipulation. Through simulations, S-RGM ^* demonstrates superior performance compared to traditional methods in navigating complex environments and achieving precise manipulator positioning for pick-and-place tasks. This work represents a significant advancement in enhancing the autonomy and operational scope of unmanned aerial manipulators, paving the way for more versatile and efficient aerial robotic systems.
Power grids have become valuable targets for both physical and cyber-attacks. A huge corpus of research and engineering best practices exist with regard to threat modeling. As robustness alone is considered inadequate to counter today’s attack vectors, resilience has become the focus of research. In this vein, learning agents, e. g., based on deep reinforcement learning, have shown a lot of promise both in deriving attack vectors and providing resilience against those. Pure model-free approaches would start training from scratch and need to re-discover already known attacks. Offline reinforcement learning provides a suitable alternative to this. However, the generation of an offline training dataset that reflects the threat model at hand while still providing an extensive dataset to train on is a research gap. Moreover, power grid simulations usually feature time series, which introduce stationarity issues that could invalidate an agent’s policy. In this paper, we apply state machines as tools to generate data based on a well-known attack. We further show how to verify the impact of the environment’s non-stationarity.
We propose a hybrid approach combining population- and trajectory-based metaheuristics to solve continuous optimization problems efficiently. We utilize a Self-Adaptive Binary Space Partitioning (SA-BSP) tree to divide the search space of continuous problems, guiding the hybrid framework toward the most promising subregions. To address the issue of premature convergence, we implement a “Finder-Tracker agents” mechanism. The hybrid framework is structured in three main phases. In the first phase, the SA-BSP tree serves as a memory unit within the population-based algorithm, capturing critical information about the explored areas, building the fitness landscape, and partitioning the search space. In the second phase, an intelligent controller is introduced to balance exploration and exploitation through the combined efforts of population- and trajectory-based algorithms. In the third phase, the search is confined to the most promising sub-region identified earlier. The trajectory-based algorithm then leverages the best solution’s fitness value and position to effectively explore this restricted search space. We compare the proposed approach with various metaheuristics in ten well-established unimodal and multimodal continuous optimization benchmarks. The results highlight the ability of the new hybrid approach to identify global optima while reducing execution time.
In this paper we expand on a previously presented method to autonomously create a reduced model to describe aspects of a computational fluid dynamics (CFD) simulation. We are trying to reduce the particle tracking of the CFD simulation so that we can determine the focal points of each particle simply by its initial injection parameters. In order to do so autonomously we utilize a Gaussian process (GP) which has the main advantages of also being able to depict random effects through a confidence of the model. While we exemplify this method through the case of the particle tracks in our Aerosol-on-Demand (AoD) jet-printhead, we see the CFD model as the ground truth for the purposes of validation. Our goal is to have the reduced model be as close as possible to the computationally expensive CFD simulation so that the reduced model can be used inline in future use and rapid iteration to improve the printing process.
The optimization of job-shop scheduling problems, such as those found in the semiconductor industry, is an NP-hard challenge. Research has demonstrated that agent-based modeling of production plants can effectively plan tasks, maximize productivity (utilization and timeliness), and minimize production delays. This bottom-up optimization approach especially addresses the computational challenges associated with traditional, centrally calculated optimization methods. In this context, we focus on a dynamic semiconductor production plant, modeling both machines and products as agents. We propose two variants of the Artificial Bee Colony algorithm for scheduling from the bottom up. Variant (1) emphasizes decentralization and batch processing to enhance production speed, while Variant (2) aims to predict production times to reduce queuing delays, achieving reductions in Flow Factor and Tardiness across most lots, though with a slight increase in Makespan for a few cases. Both algorithmic variants are evaluated within the SwarmFabSim framework, which is designed in NetLogo, specifically addressing the job-shop scheduling problem in the semiconductor industry. Through this study, we analyze the effectiveness of the bottom-up algorithms that rely on low-effort local calculations.
The immense complexity of semiconductor production demands for advanced dispatching strategies that transcend traditional rule-based systems. This paper introduces a novel approach to dispatching rules derived from swarm intelligence techniques, specifically designed to tackle the intricate dynamics of large-scale semiconductor manufacturing processes. Our approach integrates simulation and optimization methods to investigate and enhance operational efficiency, addressing both the scalability of schedules and their practical implementation. We employ a customizable simulation framework to model a semiconductor manufacturing environment, wherein various dispatching rules as well as our proposed swarm intelligence-driven method are assessed. The effectiveness of these dispatching rules is quantitatively evaluated through a series of simulations that measure key performance indicators such as work-in-progress levels, throughput, and operational variability across different production scenarios. This study not only elucidates the potential of swarm intelligence techniques in refining production dispatching strategies, but also provides a simulation-based evaluation framework that can assist in the further development of intelligent dispatching systems.
This paper models consensus formation processes using multi-agents simulations. The use of artefacts in the formation of consensus is investigated. This approach allows the study of complex team dynamics. We found that through the consensus process there are phases characterised by the efficiency of team meetings and the productivity of team members. We show that artefacts can play a significant role to improve the time to reach consensus. Furthermore, teams that use artefacts can significantly reduce the effects of bad team structure. Different team structures are investigated and characterized based on how well it supports the consensus formation process.
Both simulation and optimization have diverse applications with many different techniques and algorithms. In optimization, there are many different techniques and algorithms, especially a huge number of nature-inspired algorithms in recent years. Though these nature-inspired algorithms can be effective in practice, there are not many rigorous methods for analyzing such algorithms. This work first outlines the main components of optimization process and the related challenges in optimization and simulation. Then, some fundamental ideas in nature-inspired algorithms are reviewed, and different perspectives of algorithm analysis are discussed. Some open problems are then presented so as to inspire further research in these important areas.
Removing ground echoes from weather radar images is a critical task due to their substantial influence on the accuracy of processed meteorological data. These echoes often obscure the true atmospheric signals, particularly precipitation, which is essential for weather forecasting and analysis. In this study, we aim to develop advanced methods that not only eliminate ground echoes but also preserve precipitation signals, ensuring accurate meteorological observations. To achieve this, we explore the use of Local Descriptors based on Weber’s Law Descriptor (WLD) and combine it with the Local Binary Pattern (WLBP) descriptor, as well as introducing two novel descriptors: Local Directional Pattern (LDP) and Local Optimal-Oriented Pattern (LOOP). These descriptors are employed to capture various local features and patterns within the radar images that are crucial for distinguishing between ground echoes and precipitation. To automate the classification of these echo types, we leverage Support Vector Machine (SVM) classifiers, which have proven to be effective in high-dimensional pattern recognition tasks. Our proposed methods are rigorously tested at the Setif and Bordeaux sites, allowing for comprehensive evaluation under different weather conditions. The results from these tests demonstrate the effectiveness of the proposed techniques in accurately identifying and eliminating ground echoes while preserving precipitation. Specifically, the integration of LDP and LOOP significantly enhances the ability to differentiate between echoes, improving the robustness of the classifier in challenging environments. The outcomes indicate that these methods show considerable promise for practical applications in meteorological data processing, providing a reliable solution for improving the quality of weather radar data and supporting more accurate weather predictions.
In high-stakes professions such as that of negotiators and pilots, simulations are frequently employed as a risk-free training tool to facilitate the refinement of skills and decision-making abilities. While traditional simulations are effective, they are resource-intensive. In contrast, computer-based simulations offer scalability but may lack realism and sensory engagement. This study examines the potential of mobile phones in simulation-based learning, with a particular focus on a 3D hostage-taking scenario designed to enhance immersion through realistic interactions. By integrating a detailed environment and interactive elements, this approach demonstrates the potential of mobile technology to enhance the realism and engagement of training. Furthermore, the emergence of Large Language Models (LLMs) has transformed digital narration by moving beyond the limitations of rigid, time-consuming conversational trees. The traditional methods, which required a considerable degree of multidisciplinary expertise, frequently resulted in disrupted dialogue coherence due to the constraints imposed on the pathways available for communication. However, LLMs enable the creation of dynamic virtual personas from simple descriptions, thereby streamlining content creation and enhancing immersion through their expansive conversational capabilities. This publication reports on a digital hostage-taking simulation that utilised both mobile phones for communication and LLMs for character simulation, thereby highlighting advancements in feasibility and immersion.
