Optimization in the railway domain is essential for using resources efficiently while maintaining service quality and reliably meeting passenger demand. Most decision makers in this area rely on mathematical programming methods. Although, evolutionary algorithms have been applied to related railway problems, most existing work assumes static or average demand, offering limited resilience to real world stochastic fluctuations. Robustness, a crucial aspect of modern operations, is therefore often overlooked. This paper introduces a constrain aware hybrid evolutionary framework for robust demand balancing, through station-route assignment, directly addressing this gap. The method determines which stations should be served by which routes, so that passenger loads are evenly distributed across the network, supporting both service quality and demand satisfaction under peak and uncertain conditions. Candidate assignments are evaluated using a single robustness focused objective measuring balance across multiple time varying demand scenarios. Selection is driven by worst case performance, embedding robustness directly into the evolutionary search. Experiments on simulated networks show that the approach yields resilient, well balanced route structures and consistently outperforms baseline strategies under variable demand. The work demonstrates how established evolutionary principles can effectively address contemporary stochastic transport challenges, providing a practical and scalable decision support tool for railway planning.

As AI systems increasingly shape decision-making in creative design contexts, understanding how humans engage with these tools has become a critical challenge for interactive intelligent systems research. This article contributes a challenge to rethink how to evaluate human–AI collaborative systems, advocating for a more nuanced and multidimensional approach. Findings from one of the largest field studies to date ( n = 808) of a human–AI co-creative system, The Genetic Car Designer, complemented by a controlled lab study ( n = 12), are presented. The system is based on an interactive evolutionary algorithm where participants were tasked with designing a simple 2D representation of a car. Participants were exposed to galleries of design suggestions generated by an intelligent system, MAP–Elites, and a random control. Results indicate that exposure to galleries generated by MAP–Elites significantly enhanced both cognitive and behavioral engagement, leading to higher-quality design outcomes. Crucially for the wider community, the analysis reveals that conventional evaluation methods, which often focus on solely behavioral and design quality metrics, fail to capture the full spectrum of user engagement. By considering the human–AI design process as a changing emotional, behavioral, and cognitive state of the designer, we propose evaluating human–AI systems holistically and considering intelligent systems as a core part of the user experience—not simply a back-end tool.

3D representations of large-scale and urban scenes are crucial across various industries, including autonomous driving, urban planning, natural resource supervision and many more. Large-scale industrial reconstructions are inherently complex and multifaceted. Many existing surveys primarily focus on academic progressions and often neglect the intricate and diverse needs of industry. This survey aims to bridge this gap by providing a comprehensive analysis of 3D reconstruction methods, with a focus on industrial requirements such as scalability and integration of human interaction. Our approach involves utilizing Affinity Diagramming to systematically analyze qualitative data gathered from industrial partners. This methodology enables us to gain deep insights into how recent literature addresses these specific industrial needs. The survey encompasses various aspects, including input and reconstruction modalities, architectural models, datasets, evaluation metrics, and the incorporation of prior knowledge. We further discuss practical implications derived from our analysis, highlighting key considerations for future advancements in 3D reconstruction methods tailored for large-scale applications.

Results from a triple-blind mixed-method user study into the effectiveness of mixed-initiative tools for the procedural generation of game levels are presented. A tool which generates levels using interactive evolutionary optimization was designed for this study which 1) is focused on supporting the designer to explore the design space and 2) only requires the designer to interact with it by designing levels. The tool identifies level design patterns in an initial hand-designed map and uses that information to drive an interactive optimization algorithm. A rigorous user study was designed which compared the experiences of designers using the mixed-initiative tool to designers who were given a tool which provided completely random level suggestions. The designers using the mixed-initiative tool showed an increased engagement in the level design task, reporting that it was effective in inspiring new ideas and design directions. This provides significant evidence that procedural content generation can be used as a powerful tool to support the human design process. support for the research of this article.