Generative design interfaces increasingly expose semantic controls that let users steer output with concepts such as "more elegant" or "more minimalist," typically encoded by a vision-language model (VLM). A practical question is whether state-of-the-art VLMs represent objects consistently in terms of the same concept. We audit 6 VLMs by ranking untextured 3D objects along Kansei adjective pairs, where Kansei describes affective impressions of product form, with each axis defined as the difference between the text representations of its two poles. Geometric pairs serve as positive controls, and pairs of unrelated adjectives establish an empirical null. Across 10 categories of ShapeNet database, affective axes converge above the null (mean pairwise rank correlation 0.36 vs. 0.14) but below the geometric ceiling (0.44). The agreement between models is partial and highly uneven: on the three axes shared by all categories, mean convergence ranges from 0.21 for bookshelves to 0.51 for jars. Convergence depends primarily on whether a category's representational variation aligns with the semantic direction being evaluated, rather than simply on how much the objects vary in shape overall. Cross-model convergence does not imply agreement with human judgments. Based on our findings, we implement a UI prototype that shows how the audit can inform which Kansei descriptors to expose as controls for a given object class and which to withhold.

Biological neural networks (BNNs) have been established as a powerful and adaptive substrate that offer the potential for incredibly energy and data efficient information processing with distinct learning mechanisms. Yet a core challenge to utilizing BNN for neurocomputation is determining the optimal encoding and decoding mechanisms between the traditional silicon computing interface and the living biology. Here, we propose an Embodied Neurocomputation framework as a systems-level approach to this multi-variable optimization encoding/decoding problem. We operationalize this approach through the first large-scale parameter optimization of encoding configurations for a BNN agent performing closed-loop navigation along an odor-style gradient in a simulated grid-world. Despite the relative simplicity of the task, the biological interactions gave rise to a massive multi-combinatorial search space for optimal parameters. By considering how the components of the system are interconnected and parameterized, we evaluated approximately 1,300 parameter combinations, over 4,000 hours of real-time agent-environment interactions, to identify 12 configurations that consistently demonstrated learning across multiple episodes. These configurations achieved significantly higher task performances than optimized silicon-based DQN agents under the same interaction budget. These findings represent an initial step toward robust and scalable goal-oriented learning using BNNs. Our framework establishes a foundation for applying task-driven neurocomputing and supports the development of field-wide benchmarks. In the long term, this work supports the development of hybrid bio-silicon architectures capable of efficient, adaptive and real-time computation, including the potential for robotic control applications.

The dynamic capacitated arc routing problem (DCARP) aims to update the service paths of vehicles in the capacitated arc routing problem when uncertain factors deteriorate the current schedule of vehicles' services. A DCARP scenario comprises a series of DCARP instances that share similarities with each other. Therefore, optimisation experience gained from solving the former DCARP instance can potentially facilitate the optimisation for a new DCARP instance. However, existing optimisation algorithms for solving DCARP seldom consider such optimisation experience and instead re-optimise the DCARP instance from scratch. This paper proposes a dynamic optimisation framework with a solution building block adaptation strategy (DO-SBBA) that extracts the optimisation experience from the former optimisation process to facilitate the optimisation of the next DCARP instance. The framework introduces the concept of building blocks for extracting the valuable experience contained in historical solutions. The building block-based constructive heuristic is proposed to handle DCARP scenarios with cost- or task-changing dynamic events, and an insertion heuristic is proposed to handle task-changing dynamic events. Experimental studies demonstrate the effectiveness of DO-SBBA for extracting and utilising optimisation experience in DCARP scenarios, significantly improving the performance of dynamic optimisation compared to state-of-the-art DCARP methods.

Dynamic multiobjective optimization problems (DMOPs) with a changing number of objectives (NObjs) may have Pareto-optimal set (PS) manifold expanding or contracting over time. Knowledge transfer has been used for solving DMOPs, since it can transfer useful information from solving one problem instance to solve another related problem instance. However, we show that the state-of-the-art transfer approach based on heuristic lacks diversity on problem with extremely strong bias and loses convergence on problems with multimodality and variable correlation, after the NObjs increases and decreases, respectively. Therefore, we propose a novel transfer strategy based on learning, called learning to expand and contract PS (denoted as LEC) for enhancing diversity and convergence after NObj increases and decreases, respectively. It first learns potentially good directions for expansion and contraction separately via principal component analysis. Then, the most promising expansion and contraction directions are selected from their candidates according to whether they help diversity and convergence, respectively. Finally, PS is learned to be expanded and contracted based on these most promising directions. Comprehensive studies using 13 DMOP benchmarks with a changing NObjs demonstrate that our proposed LEC is effective on improving solution quality, not only right after changes but also after optimization of different generations, compared to state-of-the-art algorithms.

Generative AI (GenAI) has achieved remarkable success across a range of domains, but its capabilities remain constrained to statistical models of finite training sets and learning based on local gradient signals. This often results in artifacts that are more derivative than genuinely generative. In contrast, Evolutionary Computation (EC) offers a search-driven pathway to greater diversity and creativity, expanding generative capabilities by exploring uncharted solution spaces beyond the limits of available data. This work establishes a fundamental connection between EC and GenAI, redefining EC as Natural Generative AI (NatGenAI) – a generative paradigm governed by exploratory search under natural selection. We demonstrate that classical EC with parent-centric operators mirrors conventional GenAI, while disruptive operators enable structured evolutionary leaps, often within just a few generations, to generate out-of-distribution artifacts. Moreover, the methods of evolutionary multitasking provide an unparalleled means of integrating disruptive EC (with cross-domain recombination of evolved features) and moderated selection mechanisms (allowing novel solutions to survive), thereby fostering sustained innovation. By reframing EC as NatGenAI, we emphasize structured disruption and selection pressure moderation as essential drivers of creativity. This perspective extends the generative paradigm beyond conventional boundaries and positions EC as crucial to advancing exploratory design, innovation, scientific discovery, and open-ended generation in the GenAI era.

Different from most other dynamic multi-objective optimization problems (DMOPs), DMOPs with a changing number of objectives usually result in expansion or contraction of the Pareto front or Pareto set manifold. Knowledge transfer has been used for solving DMOPs, since it can transfer useful information from solving one problem instance to solve another related problem instance. However, we show that the state-of-the-art transfer algorithm for DMOPs with a changing number of objectives lacks sufficient diversity when the fitness landscape and Pareto front shape present nonseparability, deceptiveness or other challenging features. Therefore, we propose a knowledge transfer dynamic multi-objective evolutionary algorithm (KTDMOEA) to enhance population diversity after changes by expanding/contracting the Pareto set in response to an increase/decrease in the number of objectives. This enables a solution set with good convergence and diversity to be obtained after optimization. Comprehensive studies using 13 DMOP benchmarks with a changing number of objectives demonstrate that our proposed KTDMOEA is successful in enhancing population diversity compared to state-of-the-art algorithms, improving optimization especially in fast changing environments.

Meta-heuristic algorithms, especially evolutionary algorithms, have been frequently used to find near optimal solutions to combinatorial optimization problems. The evaluation of such algorithms is often conducted through comparisons with other algorithms on a set of benchmark problems. However, even if one algorithm is the best among all those compared, it still has difficulties in determining the true quality of the solutions found because the true optima are unknown, especially in dynamic environments. It would be desirable to evaluate algorithms not only relatively through comparisons with others, but also in absolute terms by estimating their quality compared to the true global optima. Unfortunately, true global optima are normally unknown or hard to find since the problems being addressed are NP-hard. In this paper, instead of using true global optima, lower bounds are derived to carry out an objective evaluation of the solution quality. In particular, the first approach capable of deriving a lower bound for dynamic capacitated arc routing problem (DCARP) instances is proposed, and two optimization algorithms for DCARP are evaluated based on such a lower bound approach. An effective graph pruning strategy is introduced to reduce the time complexity of our proposed approach. Our experiments demonstrate that our approach provides tight lower bounds for small DCARP instances. Two optimization algorithms are evaluated on a set of DCARP instances through the derived lower bounds in our experimental studies, and the results reveal that the algorithms still have room for improvement for large complex instances.

How can a robot provide unobtrusive physical support within a group of humans? We present Attentive Support, a novel interaction concept for robots to support a group of humans. It combines scene perception, dialogue acquisition, situation understanding, and behavior generation with the common-sense reasoning capabilities of Large Language Models (LLMs). In addition to following user instructions, Attentive Support is capable of deciding when and how to support the humans, and when to remain silent to not disturb the group. With a diverse set of scenarios, we show and evaluate the robot's attentive behavior, which supports and helps the humans when required, while not disturbing if no help is needed.

The current advances in generative AI for learning large neural network models with the capability to produce essays, images, music and even 3D assets from text prompts create opportunities for a manifold of disciplines. In the present paper, we study the potential of deep text-to-3D models in the engineering domain, with focus on the chances and challenges when integrating and interacting with 3D assets in computational simulation-based design optimization. In contrast to traditional design optimization of 3D geometries that often searches for the optimum designs using numerical representations, such as B-Spline surface or deformation parameters in vehicle aerodynamic optimization, natural language challenges the optimization framework by requiring a different interpretation of variation operators while at the same time may ease and motivate the human user interaction. Here, we propose and realize a fully automated evolutionary design optimization framework using Shap-E, a recently published text-to-3D asset network by OpenAI, in the context of aerodynamic vehicle optimization. For representing text prompts in the evolutionary optimization, we evaluate (a) a bag-of-words approach based on prompt templates and Wordnet samples, and (b) a tokenisation approach based on prompt templates and the byte pair encoding method from GPT4. Our main findings from the optimizations indicate that, first, it is important to ensure that the designs generated from prompts are within the object class of application, i.e. diverse and novel designs need to be realistic, and, second, that more research is required to develop methods where the strength of text prompt variations and the resulting variations of the 3D designs share causal relations to some degree to improve the optimization.

Recent advancements in machine learning comprise generative models such as autoencoders (AE) for learning and compressing 3D data to generate low-dimensional latent representations of 3D shapes. Learning latent representations that disentangle the underlying factors of variations in 3D shapes is an intuitive way to achieve generalization in generative models. However, it remains an open problem to learn a generative model of 3D shapes such that the latent variables are disentangled and represent different interpretable aspects of 3D shapes. In this paper, we propose Split-AE, which is an autoencoder-based architecture for partitioning the latent space into two sets, named as content and style codes. The content code represents global features of 3D shapes to differentiate between semantic categories of shapes, while style code represents distinct visual features to differentiate between shape categories having similar semantic meaning. We present qualitative and quantitative experiments to verify feature disentanglement using our Split-AE. Further, we demonstrate that, given a source shape as an initial shape and a target shape as a style reference, the trained Split-AE combines the content of a source and style of a target shape to generate a novel augmented shape, that possesses the distinct features of the target shape category yet maintains the similarity of the global features with the source shape. We conduct a qualitative study showing that the augmented shapes exhibit a realistic interpretable mixture of content and style features across different shape classes with similar semantic meaning.

The capacitated arc routing problem (CARP) is a challenging combinatorial optimization problem abstracted from many real-world applications, such as waste collection, road gritting, and mail delivery. However, few studies considered dynamic changes during the vehicles’ service, which can cause the original schedule infeasible or obsolete. The few existing studies are limited by the dynamic scenarios considered, and by overly complicated algorithms that are unable to benefit from the wealth of contributions provided by the existing CARP literature. In this article, we first provide a mathematical formulation of dynamic CARP (DCARP) and design a simulation system that is able to consider dynamic events while a routing solution is already partially executed. We then propose a novel framework which can benefit from the existing static CARP optimization algorithms so that they could be used to handle DCARP instances. The framework is very flexible. In response to a dynamic event, it can use either a simple restart strategy or a sequence transfer strategy that benefits from the past optimization experience. Empirical studies have been conducted on a wide range of DCARP instances to evaluate our proposed framework. The results show that the proposed framework significantly improves over state-of-the-art dynamic optimization algorithms.

The Capacitated Arc Routing Problem (CARP) aims at assigning vehicles to serve tasks which are located at different arcs in a graph. However, the originally planned routes are easily affected by different dynamic events like newly added tasks. This gives rise to Dynamic CARP (DCARP) instances, which need to be efficiently optimized for new high-quality service plans in a short time. However, it is unknown which dynamic events make DCARP instances especially hard to solve. Therefore, in this paper, we provide an investigation of the influence of different dynamic events on DCARP instances from the perspective of fitness landscape analysis based on a recently proposed hybrid local search (HyLS) algorithm. We generate a large set of DCARP instances based on a variety of dynamic events and analyze the fitness landscape of these instances using several different measures such as fitness correlation length. From the empirical results we conclude that cost-related events have no significant impact on the difficulty of DCARP instances, but instances which require more new vehicles to serve the remaining tasks are harder to solve. These insights improve our understanding of the DCARP instances and pave the way for future work on improving the performance of DCARP algorithms.

Artificial intelligence (AI) is increasingly used to assist humans in various aspects of everyday life, including high-stakes decision-making.Nevertheless, the question how to design human-AI teams that optimally integrate the strengths of both parties, while mitigating their respective weaknesses, is still open.Machines excel in the analysis of large data sets and the rapid discovery of subtle patterns, while it is a human strength to judge new, uncertain situations based on tacit knowledge, intuition, or creativity.An interesting open research question is, thus, how AI and human decisions can be integrated well such that the resulting human-AI team exhibits better performance than AI or humans alone.Allowing human-AI teams to achieve higher performance requires humans to adopt AI advice when appropriate.Despite numerous works addressing confidence and trust in AI, we still lack a clear view whether humans are willing to rely on recommendations made by an AI or a human being, and what the underlying mechanisms are.Recent research has shown that people often follow recommendations from an AI whether they are accurate or not, and independent of their expertise [1].While a large number of studies has focused on effects of an AI's properties like its accuracy [2,3,4,5,6,7], confidence in predictions [8], model updates [9], accompanying explanations [10,11,12,13,8], or error boundaries [14] on recommendation adoption in AI-assisted decision-making, there are still open questions about the mechanics of how humans' confidence in their own decision influences recommendation adoption in situations of high uncertainty, and how we can leverage such information to best combine human and AI decisions.Closing this gap, our work investigates how different mechanisms for the integration of AI-generated recommendations influence the performance of AI-assisted humans in an online study.To this end, we study the willingness of human participants to revise their decision in an image recognition task, which can be modulated such that it exhibits different levels of difficulty.Participants were exposed to AI-generated recommendations that were either displayed as originating from an AI or other humans.

Real-world optimization scenarios under uncertainty and no-ise are typically handled with robust optimization techniques, which re-formulate the original optimization problem into a robust counterpart, e.g., by taking an average of the function values over different perturbations to a specific input. Solving the robust counterpart instead of the original problem can significantly increase the associated computational cost, which is often overlooked in the literature to the best of our knowledge. Such an extra cost brought by robust optimization might depend on the problem landscape, the dimensionality, the severity of the uncertainty, and the formulation of the robust counterpart. This paper targets an empirical approach that evaluates and compares the computational cost brought by different robustness formulations in Kriging-based optimization on a wide combination (300 test cases) of problems, uncertainty levels, and dimensions. We mainly focus on the CPU time taken to find the robust solutions, and choose five commonly-applied robustness formulations: "mini-max robustness", "mini-max regret robustness", "expectation-based robustness", "dispersion-based robustness", and "composite robustness" respectively. We assess the empirical performance of these robustness formulations in terms of a fixed budget and a fixed target analysis, from which we find that "mini-max robustness" is the most practical formulation w.r.t. the associated computational cost.

Automated Machine Learning (AutoML) frameworks are designed to select the optimal combination of operators and hyperparameters. Classical AutoML-based Bayesian Optimization approaches often integrate all operator search spaces into a single search space. However, a disadvantage of this history-based strategy is that it can be less robust when initialized randomly than optimizing each operator algorithm combination independently. To overcome this issue, a novel contesting procedure algorithm, Divide And Conquer Optimization (DACOpt), is proposed to make AutoML more robust. DACOpt partitions the AutoML search space into a reasonable number of sub-spaces based on algorithm similarity and budget constraints. Furthermore, throughout the optimization process, DACOpt allocates resources to each sub-space to ensure that (1) all areas of the search space are covered and (2) more resources are assigned to the most promising sub-space. Two extensive sets of experiments on 117 benchmark datasets demonstrate that DACOpt achieves significantly better results in 36% of AutoML benchmark datasets: 5% when to compared to TPOT, 8% - to AutoSklearn, 15% - to H20 and 18% - to ATM.

Traditional methods for solving problems within computer science rely mostly upon the application of handcrafted algorithms. As however manual engineering of them can be considered to be a tedious process, it is interesting to consider how far internal mechanisms can be directly learned in an end-to-end manner instead. This is especially tempting to consider for metaheuristic and evolutionary optimization routines which inherently rely upon creating abundant amounts of data during run-time. To implement such an approach for these types of algorithms, it effectively requires a pipeline to first acquire deran-domized algorithm components in a domain-dependent manner and secondly a mapping to select them based upon characteristic features which unveil the black box character of an optimization problem. While in principle, within our prior work we proposed methods for extracting spatial features from metadata, these unfortunately fail to acknowledge the time-dependent nature of it. Thus, fail in scenarios when the inputs generated from initial iterations are not expressive enough. For this reason we specifically develop within this work architectures for spatio-temporal data processing. Particularly, we find that our proposed GCN-GRU and LSTM architectures, which take inspiration from CNN-LSTMs originally proposed for activity recognition in multimedia data-streams, demonstrate high efficiency and most consistent performance on time series of variable length. Further, we can also demonstrate that the class activation map (CAM) for interpretable learning with time series data helps to understand and reflects problem-dependent properties of the search behavior of an optimization algorithm.

The choice of design representations, as of search operators, is central to the performance of evolutionary optimization algorithms, in particular, for multitask problems. The multitask approach pushes further the parallelization aspect of these algorithms by solving simultaneously multiple optimization tasks using a single population. During the search, the operators implicitly transfer knowledge between solutions to the offspring, taking advantage of potential synergies between problems to drive the solutions to optimality. Nevertheless, in order to operate on the individuals, the design space of each task has to be mapped to a common search space, which is challenging in engineering cases without clear semantic overlap between parameters. Here, we apply a 3-D point cloud autoencoder to map the representations from the Cartesian to a unified design representation: the latent space of the autoencoder. The transfer of latent space features between design representations allows the reconstruction of shapes with interpolated characteristics and maintenance of common parts, which potentially improves the performance of the designs in one or more tasks during the optimization. Compared to traditional representations for shape optimization, such as free-form deformation, the latent representation enables more representative design modifications, while keeping the baseline characteristics of the learned classes of objects. We demonstrate the efficiency of our approach in an optimization scenario where we minimize the aerodynamic drag of two different car shapes with common underbodies for cost-efficient vehicle platform design.

Abstract In automotive digital development, 3D prototype creation is a team effort of designers and engineers, each contributing with ideas and technical evaluations through means of computer simulations. To support the team in the 3D design ideation and exploration task, we propose an interactive design system for assisted design explorations and faster performance estimations. We utilize the advantage of deep learning-based autoencoders to create a low-dimensional latent manifold of 3D designs, which is utilized within an interactive user interface to guide and strengthen the decision-making process.

The dynamic capacitated arc routing problem (DCARP) aims at re-scheduling the service plans of agents, such as vehicles in a city scenario, when dynamic events deteriorate the quality of the current schedule. Various algorithms have been proposed to solve DCARP instances in different dynamic scenarios. However, most existing work evaluated their algorithms' performance based on artificially constructed dynamic environments instead of using more realistic traffic simulations which are built on actual traffic data. In this paper, we constructed a novel DCARP benchmarking framework based on the Simulation of Urban MObility (SUMO) transportation simulation software, which allows to include real-world traffic environments for generating a set of DCARP instances from dynamic events, such as road congestion or task changes. The flexibility of the framework allows to develop DCARP optimization algorithms and evaluate their effectiveness more comprehensively. We use the benchmarking framework to generate 12 different dynamic instances using real-world traffic data of Dublin City. We then demonstrate the value of our framework by using these instances to compare our previously proposed hybrid local search algorithm (HyLS) with a state-of-the-art meta-heuristic optimization algorithm. The generated benchmark scenarios indicate that HyLS is a very effective optimizer on DCARP scenarios with real traffic data for reducing the total service cost. They also demonstrate the importance of our DCARP benchmarking framework for the development and benchmarking of optimization algorithms in more realistic scenarios.

In automotive digital development, engineers utilize multiple virtual prototyping tools to design and assess the performance of 3D shapes. However, accurate performance simulations are computationally expensive and time-consuming, which may be prohibitive for design optimization tasks. To address this challenge, we envision a 3D design assistance system for design exploration with performance assessment in the automotive domain. Recent advances in deep learning methods for learning geometric data are a promising step towards realizing such systems. Deep learning-based (variational) autoencoder models have been used for learning and compressing 3D data allowing engineers to generate low-dimensional representations of 3D designs. Finding representations in a data-driven fashion results in representations that are agnostic to downstream tasks performed on these representations and are believed to capture relevant design features. In this paper, we evaluate whether such data-driven representations contain relevant information about the input data and whether representations are meaningful in performance prediction tasks for the input data. We use machine learning-based surrogate models to predict the performances of car shapes based on the low-dimensional representation learned by 3D point cloud (variational) autoencoders. Furthermore, we exploit the stochastic nature of the representation learned by variational autoencoders to augment the training data for our surrogate models, since the limited amount of data is usually a challenge for surrogate modeling in engineering. We demonstrate that augmenting training with generated shapes improves prediction accuracy. In sum, we find that geometric deep learning approaches offer powerful tools to support the engineering design process.