Search

Topology optimization (TO) has found applications across a wide range of disciplines but remains underutilized in practice. Key barriers to broader adoption include the absence of versatile commercial software, the need for specialized expertise, and high computational demands. Additionally, challenges such as ensuring manufacturability, optimizing hyper-parameters, and integrating subjective design elements like aesthetics further hinder its widespread use. Emerging technologies like augmented reality (AR) and virtual reality (VR) offer transformative potential for TO. By enabling intuitive, gesture-based human-computer interactions, these immersive tools bridge the gap between human intuition and computational processes. They provide the means to integrate subjective human judgment into optimization workflows in real time, creating a paradigm shift toward interactive and immersive design. Here we introduce the concept of immersive topology optimization (ITO) as a novel design paradigm that leverages AR environments for TO. To demonstrate this concept, we present ARCADE: Augmented Reality Computational Analysis and Design Environment. Developed in Swift for the Apple Vision Pro mixed reality headset, ARCADE enables users to define, manipulate, and solve structural optimization problems within an augmented reality setting. By incorporating real-time human interaction and visualization of the design in its intended target location, ARCADE has the potential to reduce lead times, enhance manufacturability, and improve design integration. Although initially developed for structural optimization, ARCADE's framework could be extended to other disciplines, paving the way for a new era of interactive and immersive computational design., Comment: 9 pages, 5 figures

The appearance of surface impurities (e.g., water stains, fingerprints, stickers) is an often-mentioned issue that causes degradation of automated visual inspection systems. At the same time, synthetic data generation techniques for visual surface inspection have focused primarily on generating perfect examples and defects, disregarding impurities. This study highlights the importance of considering impurities when generating synthetic data. We introduce a procedural method to include photorealistic water stains in synthetic data. The synthetic datasets are generated to correspond to real datasets and are further used to train an anomaly detection model and investigate the influence of water stains. The high-resolution images used for surface inspection lead to memory bottlenecks during anomaly detection training. To address this, we introduce Sequential PatchCore - a method to build coresets sequentially and make training on large images using consumer-grade hardware tractable. This allows us to perform transfer learning using coresets pre-trained on different dataset versions. Our results show the benefits of using synthetic data for pre-training an explicit coreset anomaly model and the extended performance benefits of finetuning the coreset using real data. We observed how the impurities and labelling ambiguity lower the model performance and have additionally reported the defect-wise recall to provide an industrially relevant perspective on model performance.

As dual combs play a significant role in numerous high-precision measurements, their efficient generation has been widely researched. Although the single-cavity dual-comb generation can avoid the complex active stabilization methods, achieving and maintaining stable dual-comb mode locking within a single cavity remains a critical challenge. To break through this constraint, a two-part evaluation criterion containing a fitness function and a CNN-Transformer network is employed to achieve mode locking and classify the dual-comb mode-locked state. Simulated time-stretch dispersive Fourier transform (DFT) spectra are used as datasets, which simplifies the optimization process and does not rely on specific experimental data. A developed evolutionary algorithm (EA) for paddle-based motorized polarization controllers (MPCs) is proposed, enabling the intelligent attainment of dual-comb mode-locked states. A real-time library stores fitness and MPC angles, facilitating mode-locked state achievement within 2 seconds. Finally, long term running of dual-comb mode locking is ensured by a random collision algorithm utilizing an evaluation criterion of weak soliton peaks., Comment: 10 pages, 8 figures

Artificial intelligence (AI) is driving transformative changes across numerous fields, revolutionizing conventional processes and creating new opportunities for innovation. The development of mechatronic systems is undergoing a similar transformation. Over the past decade, modeling, simulation, and optimization techniques have become integral to the design process, paving the way for the adoption of AI-based methods. In this paper, we examine the potential for integrating AI into the engineering design process, using the V-model from the VDI guideline 2206, considered the state-of-the-art in product design, as a foundation. We identify and classify AI methods based on their suitability for specific stages within the engineering product design workflow. Furthermore, we present a series of application examples where AI-assisted design has been successfully implemented by the authors. These examples, drawn from research projects within the DFG Priority Program \emph{SPP~2353: Daring More Intelligence - Design Assistants in Mechanics and Dynamics}, showcase a diverse range of applications across mechanics and mechatronics, including areas such as acoustics and robotics., Comment: 23 pages, 9 figures, joint publication of the priority programme SPP 2353

This paper is devoted to an intrinsic geometrical classification of three-mirror telescopes. The problem is formulated as the study of the connected components of a semi-algebraic set. Under first order approximation, we give the general expression of the transfer matrix of a reflexive optical system. Thanks to this representation, we express the semi-algebraic set for focal telescopes and afocal telescopes as the set of non-degenerate real solutions of first order optical conditions. Then, in order to study the topology of these sets, we address the problem of counting and describe their connected components. In a same time, we introduce a topological invariant which encodes the topological features of the solutions. For systems composed of three mirrors, we give the semi-algebraic description of the connected components of the set and show that the topological invariant is exact., Comment: 31 pages,7 figures

Machine learning and deep learning advancements have boosted Brain-Computer Interface (BCI) performance, but their wide-scale applicability is limited due to factors like individual health, hardware variations, and cultural differences affecting neural data. Studies often focus on uniform single-site experiments in uniform settings, leading to high performance that may not translate well to real-world diversity. Deep learning models aim to enhance BCI classification accuracy, and transfer learning has been suggested to adapt models to individual neural patterns using a base model trained on others' data. This approach promises better generalizability and reduced overfitting, yet challenges remain in handling diverse and imbalanced datasets from different equipment, subjects, multiple centres in different countries, and both healthy and patient populations for effective model transfer and tuning. In a setting characterized by maximal heterogeneity, we proposed P300 wave detection in BCIs employing a convolutional neural network fitted with adaptive transfer learning based on Poison Sampling Disk (PDS) called Active Sampling (AS), which flexibly adjusts the transition from source data to the target domain. Our results reported for subject adaptive with 40% of adaptive fine-tuning that the averaged classification accuracy improved by 5.36% and standard deviation reduced by 12.22% using two distinct, internationally replicated datasets. These results outperformed in classification accuracy, computational time, and training efficiency, mainly due to the proposed Active Sampling (AS) method for transfer learning.

Creating realistic VR experiences is challenging due to the labor-intensive process of accurately replicating real-world details into virtual scenes, highlighting the need for automated methods that maintain spatial accuracy and provide design flexibility. In this paper, we propose AURORA, a novel method that leverages RGB-D images to automatically generate both purely virtual reality (VR) scenes and VR scenes combined with real-world elements. This approach can benefit designers by streamlining the process of converting real-world details into virtual scenes. AURORA integrates advanced techniques in image processing, segmentation, and 3D reconstruction to efficiently create realistic and detailed interior designs from real-world environments. The design of this integration ensures optimal performance and precision, addressing key challenges in automated indoor design generation by uniquely combining and leveraging the strengths of foundation models. We demonstrate the effectiveness of our approach through experiments, both on self-captured data and public datasets, showcasing its potential to enhance virtual reality (VR) applications by providing interior designs that conform to real-world positioning., Comment: 8 pages, 4 figures

This paper presents evS2CP, an optimization-based framework for simultaneous speed and charging planning designed for connected electric vehicles (EVs). With EVs emerging as competitive alternatives to internal combustion engine vehicles, overcoming challenges such as limited charging infrastructure is crucial. evS2CP addresses these issues by minimizing the travel time, charging time, and energy consumption, providing practical solutions for both human-operated and autonomous vehicles. This framework leverages V2X communication to integrate essential EV planning data, including route geometry, real-time traffic conditions, and charging station availability, while simulating dynamic driving environments using open-web API services. The speed and charging planning problem was initially formulated as a nonlinear programming model, which was then convexified into a quadratic programming model without charging-stop constraints. Additionally, a mixed-integer programming approach was employed to optimize charging station selection and minimize the frequency of charging events. A mixed-integer quadratic programming implementation exhibited exceptional computational efficiency and scalability, effectively solving trip plans over distances exceeding 700 km in a few seconds. Simulations conducted using open-source and commercial solvers validated the framework's near-global optimality, demonstrating its robustness and feasibility for real-world applications in connected EV ecosystems., Comment: 15 pages, 9 figures, 2 tables

This study explores the suitability of hydrogen-based plasma in direct power extraction (DPE) as a non-conventional electricity generation method. We apply computational modeling and principles in physics and chemistry to estimate different thermal and electric properties of a water-vapor/nitrogen/cesium-vapor (H2O/N2/Cs) gas mixture with different levels of cesium (Cs) at a fixed temperature of 2300 K (2026.85 {\deg}C). This gas mixture and temperature are selected because they resemble the stoichiometric combustion of hydrogen with air, followed by the addition of the alkali metal element cesium to allow ionization, thus converting the gas mixture into electrically conducting plasma. We vary the cesium mole fraction in the gas mixture by two orders of magnitude, from a minute amount of 0.0625% (1/1600) to a major amount of 16% (0.16). We use these results to further estimate the theoretical upper limit of the electric power output from a unit volume of a high-speed magnetohydrodynamic (MHD) channel, with the plasma accelerated inside it to twice the local speed of sound (Mach number 2) while subject to an applied magnetic field of 5 T (5 teslas). We report that there is an optimum cesium mole fraction of 3%, at which the power output is maximized. Per 1 m3 of plasma volume, the estimated theoretical electric power generation at 1 atm (101.325 kPa) pressure of the hydrogen-combustion mixture is extraordinarily high at 360 MW/m3, and the plasma electric conductivity is 17.5 S/m. This estimated power generation even reaches an impressive level of 1.15 GW/m3 (11500 MW/m3) if the absolute pressure can be decreased to 0.0625 atm (6.333 kPa), at which the electric conductivity exceeds 55 S/m (more than 10 times the electric conductivity of seawater)., Comment: 20 pages, 6 figures, 3 tables, published journal article, open access

We apply several weighted sum of gray gases models (WSGGMs) to calculate the radiative absorption coefficient for gas mixtures containing H2O and CO2. Our main objectives are to analyze and compare four WSGGMs which have been recently developed for oxy-fuel combustion. The models are compared with the widely-used air-fuel WSGGM of Smith et al. In addition to direct comparison of the absorption coefficients, we compare finite-volume solutions of the radiative equation of transfer in a 2m x 2m x 4m box with a specified inhomogeneous temperature field and a homogeneous mixture of the H2O, CO2 and N2. Calculations using a spectral line-based WSGGM (SLW) are used as a reference solution to estimate the accuracy. For each WSGGM, we apply two interpolation methods for determining the model coefficients at arbitrary H2O-to-CO2 ratios. For wet-recycle oxy-fuel combustion, we found that the deviation of the air-fuel WSGGM was not significantly larger than several of the newer models. However, with dry recycle (90 vol%-CO2) the air-fuel WSGGM model underpredicts the radiative flux and radiative heat source in contrast to the other models which overpredict these fields. Piecewise linear interpolation consistently improves the predictions of the air-fuel WSGGM, but only has a modest effect on the predictions of the oxy-fuel WSGGM's., Comment: 14 pages, 5 figures, 7 tables, published conference article, not open access but the copyright is not held by the publisher

According to a recent U.S. Greenhouse Gas Emissions Inventory (1), about 42% of 2008 CO$_2$ (a greenhouse gas) emissions in the US were from burning fossil fuels (especially coal) to generate electricity. The 2010 U.S. International Energy Outlook (2) predicts that the world energy generation using coal and natural gas will continue to increase steadily in the future. This results in increased concentrations of atmospheric CO$_2$, and calls for serious efforts to control its emissions from power plants through carbon capture technologies. Oxy-fuel combustion is a carbon capture technology in which the fossil fuel is burned in an atmosphere free from nitrogen, thereby significantly reducing the relative amount of N$_2$ in the flue-gas and increasing the mole fractions of H$_2$O and CO$_2$. This low concentration of N$_2$ facilitates the capture of CO$_2$. The dramatic change in the flue composition results in changes in its thermal, chemical, and radiative properties. From the modeling point of view, existing transport, combustion, and radiation models that have parameters tuned for air-fuel combustion (where N$_2$ is the dominant gaseous species in the flue) may need revision to improve the predictions of numerical simulations of oxy-fuel combustion. In this chapter, we consider recent efforts done to revise radiation modeling for oxy-fuel combustion, where five new radiative-property models were proposed to be used in oxy-fuel environments. All these models use the weighted-sum-of-gray-gases model (WSGGM). We apply and compare their performance in two oxy-fuel environments. Both environments consist of only H$_2$O and CO$_2$ as mixture species, and thus there is no N$_2$ dilution, but the environments vary in the mole fractions of these two species., Comment: 20 pages, 16 tables, 6 figures (but Figure 3 is omitted as it may require third-party permission), invited book chapter

Random Forest (RF) and Gradient Boosting Regression Trees (GBRT) regression models along with three cheminformatics data sets (RDkit, Mordred, Morgan) have been used to predict the power conversion efficiency (PCE) of organic solar cells (OSCs). The data consists of cheinformatics descriptors of the electron donor used in 433 OSCs for which the experimental PCE (target variable) is reported in the literature. The donor is either a polymer or a small organic molecule, and the acceptor the fullerene derivatives PCBM or PC71BM. Unlike previous methods, our ML approach considers the type of donor and the acceptor by adding four extra donor's features using the one-hot encoder tool. It is demonstrated that this additional information improves the prediction performance up to 34%. We have also exploited this feature to theoretically forecast the PCE of new OSCs by evaluating the ML model for a different acceptor. It is predicted that more than 50% of the OCSs obtained by exchanging the acceptor would have higher experimental PCE. The prediction accuracy of a given ML approach is analyzed for different PCE intervals. RF using RDkit descriptors resulted in the best ML approach with a Pearson's correlation coefficient for the training and testing sets equal to 0.96 and 0.62, respectively., Comment: 12 pages, 4 Figures, 1 Table

As humans venture deeper into space, the need for a lunar settlement, housing the first group of settlers, grows steadily. By means of new technologies such as in situ resource utilisation (ISRU) as well as computational design, this goal can be implemented in present years. Providing the first arrivals with an immediate underground habitat safe from radiation and other environmental constraints is of crucial importance to initialise a prolonged mission on the Moon. The project's proposal revolves around the idea of establishing a base which provides an immediately habitable space with the possibility for future expansion. Advanced construction methods and sustainable practices lay the groundwork for a permanent human presence, predominantly based on ISRU. This paper outlines a two-phase initiative aimed at the foundation of the Lunar Subterra, followed by an extension of the habitat above ground. Following our collaboration with the PoliSpace Sparc Student Association group, a Virtual Reality (VR) reproduction of the proposed habitat enabled quick iterative testing of the habitable space with the use of a Meta Quest 2 headset. This not only allowed an evaluation of the environment and its impact on human residents but also eradicated the need for tangible models to conceptualise the idea, enabling rapid user-centred design and implementation in the future of space exploration., Comment: 75th International Astronautical Congress (IAC), Milan, Italy, 14-18 October 2024

The use of machine learning (ML) methods for development of robust and flexible visual inspection system has shown promising. However their performance is highly dependent on the amount and diversity of training data. This is often restricted not only due to costs but also due to a wide variety of defects and product surfaces which occur with varying frequency. As such, one can not guarantee that the acquired dataset contains enough defect and product surface occurrences which are needed to develop a robust model. Using parametric synthetic dataset generation, it is possible to avoid these issues. In this work, we introduce a complete pipeline which describes in detail how to approach image synthesis for surface inspection - from first acquisition, to texture and defect modeling, data generation, comparison to real data and finally use of the synthetic data to train a defect segmentation model. The pipeline is in detail evaluated for milled and sandblasted aluminum surfaces. In addition to providing an in-depth view into each step, discussion of chosen methods, and presentation of ML results, we provide a comprehensive dual dataset containing both real and synthetic images., Comment: Initial preprint, 21 pages, 21 figures, 6 tables

The use of eXtended Reality (XR) technologies in the space domain has increased significantly over the past few years as it can offer many advantages when simulating complex and challenging environments. Space agencies are currently using these disruptive tools to train astronauts for Extravehicular Activities (EVAs), to test equipment and procedures, and to assess spacecraft and hardware designs. With the Moon being the current focus of the next generation of space exploration missions, simulating its harsh environment is one of the key areas where XR can be applied, particularly for astronaut training. Peculiar lunar lighting conditions in combination with reduced gravity levels will highly impact human locomotion especially for movements such as walking, jumping, and running. In order to execute operations on the lunar surface and to safely live on the Moon for an extended period of time, innovative training methodologies and tools such as XR are becoming paramount to perform pre-mission validation and certification. This research work presents the findings of the experiments aimed at exploring the integration of XR technology and parabolic flight activities for astronaut training. In addition, the study aims to consolidate these findings into a set of guidelines that can assist future researchers who wish to incorporate XR technology into lunar training and preparation activities, including the use of such XR tools during long duration missions., Comment: 75th International Astronautical Congress (IAC), Milan, Italy, 14-18 October 2024

Purpose: This paper aims to enhance bearing fault diagnosis in industrial machinery by introducing a novel method that combines Graph Attention Network (GAT) and Long Short-Term Memory (LSTM) networks. This approach captures both spatial and temporal dependencies within sensor data, improving the accuracy of bearing fault detection under various conditions. Methodology: The proposed method converts time series sensor data into graph representations. GAT captures spatial relationships between components, while LSTM models temporal patterns. The model is validated using the Case Western Reserve University (CWRU) Bearing Dataset, which includes data under different horsepower levels and both normal and faulty conditions. Its performance is compared with methods such as K-Nearest Neighbors (KNN), Local Outlier Factor (LOF), Isolation Forest (IForest) and GNN-based method for bearing fault detection (GNNBFD). Findings: The model achieved outstanding results, with precision, recall, and F1-scores reaching 100\% across various testing conditions. It not only identifies faults accurately but also generalizes effectively across different operational scenarios, outperforming traditional methods. Originality: This research presents a unique combination of GAT and LSTM for fault detection, overcoming the limitations of traditional time series methods by capturing complex spatial-temporal dependencies. Its superior performance demonstrates significant potential for predictive maintenance in industrial applications.

We predict the development and propagation of the fluctuations in a perturbed ideally-expanded air jet. A non-propagating harmonic perturbation in the density, axial velocity, and pressure is introduced at the inflow with different frequencies to produce coherent structures in the airflow, which are synchronized with the applied frequency. Then, the fluctuations and acoustic fields are predicted for each frequency by integrating the axisymmetric linearized Euler equations. We investigate the effect of the perturbation frequency on different characteristics of the pressure and velocity waves. The perturbation frequency can be used to alter the propagation pattern and intensity of the waves and mitigate the noise levels at certain zones., Comment: 23 pages, 16 figures, journal paper

The usefulness of Large Language Models (LLM) is being continuously tested in various fields. However, their intrinsic linguistic characteristic is still one of the limiting factors when applying these models to exact sciences. In this article, a novel approach to use General Pre-Trained Transformers to assist in the design phase of data acquisition systems will be presented. The solution is packaged in the form of an application that retains the conversational aspects of LLMs, in such a manner that the user must provide details on the desired project in order for the model to draft both a system-level architectural diagram and the block-level specifications, following a Top-Down methodology based on restrictions. To test this tool, two distinct user emulations were used, one of which uses an additional GPT model. In total, 4 different data acquisition projects were used in the testing phase, each with its own measurement requirements: angular position, temperature, acceleration and a fourth project with both pressure and superficial temperature measurements. After 160 test iterations, the study concludes that there is potential for these models to serve adequately as synthesis/assistant tools for data acquisition systems, but there are still technological limitations. The results show coherent architectures and topologies, but that GPTs have difficulties in simultaneously considering all requirements and many times commits theoretical mistakes., Comment: 8 pages

This paper presents a novel conversational AI-enabled active ideation interface as a creative idea-generation tool to assist novice designers in mitigating the initial latency and ideation bottlenecks that are commonly observed. It is a dynamic, interactive, and contextually responsive approach, actively involving a large language model (LLM) from the domain of natural language processing (NLP) in artificial intelligence (AI) to produce multiple statements of potential ideas for different design problems. Integrating such AI models with ideation creates what we refer to as an Active Ideation scenario, which helps foster continuous dialogue-based interaction, context-sensitive conversation, and prolific idea generation. A pilot study was conducted with thirty novice designers to generate ideas for given problems using traditional methods and the new CAI-based interface. The key parameters of fluency, novelty, and variety were used to compare the outcomes qualitatively by a panel of experts. The findings demonstrated the effectiveness of the proposed tool for generating prolific, diverse and novel ideas. The interface was enhanced by incorporating a prompt-engineered structured dialogue style for each ideation stage to make it uniform and more convenient for the designers. The resulting responses of such a structured CAI interface were found to be more succinct and aligned towards the subsequent design stage, namely conceptualization. The paper thus established the rich potential of using Generative AI (Gen-AI) for the early ill-structured phase of the creative product design process., Comment: 21 pages, 16 figures, AIEDAM Journal Article

In this study, a new $\Delta$-evaluation method is introduced for solving a column permutation problem defined on a sparse binary matrix with the consecutive ones property. This problem models various $\mathcal{NP}$-hard problems in graph theory and industrial manufacturing contexts. The computational experiments compare the processing time of the $\Delta$-evaluation method with two other methods used in well-known local search procedures. The study considers a comprehensive set of instances of well-known problems, such as Gate Matrix Layout and Minimization of Open Stacks. The proposed evaluation method is generally competitive and particularly useful for large and dense instances. It can be easily integrated into local search and metaheuristic algorithms to improve solutions without significantly increasing processing time., Comment: technical report

The aim of this paper is threefold. We inform the AI practitioner about the human visual system with an extensive literature review; we propose a novel biologically motivated neural network for image classification; and, finally, we present a new plug-and-play module to model context awareness. We focus on the effect of incorporating circuit motifs found in biological brains to address visual recognition. Our convolutional architecture is inspired by the connectivity of human cortical and subcortical streams, and we implement bottom-up and top-down modulations that mimic the extensive afferent and efferent connections between visual and cognitive areas. Our Contextual Attention Block is simple and effective and can be integrated with any feed-forward neural network. It infers weights that multiply the feature maps according to their causal influence on the scene, modeling the co-occurrence of different objects in the image. We place our module at different bottlenecks to infuse a hierarchical context awareness into the model. We validated our proposals through image classification experiments on benchmark data and found a consistent improvement in performance and the robustness of the produced explanations via class activation. Our code is available at https://github.com/gianlucarloni/CoCoReco., Comment: ECCV 2024 - HCV Workshop, Accepted for presentation, Submitted Manuscript Version (adapted to include author names, Acknowledgements, and reference DOIs): the version of the manuscript improved after peer review will appear in the Proceedings later

This study aims to investigate, through neuroscientific methods, the effects of particular architectural elements on pedestrian spatial cognition and experience in the analysis and design of walking street spaces. More precisely, this paper will describe the impact of the density variation of storefront signs on the brainwaves of passersby in East Asian city walking streets, providing strategies and guidelines for urban development and renewal. Firstly, the paper summarizes the research method through the review of research questions and related literature; secondly, the paper establishes experiments via this path, analyzing results and indicators through data processing; finally, suggestions for future pedestrian street design are proposed based on research and analysis results., Comment: 10 pages, 10 figures, This paper has been accepted at the eCAADe 2024 Conference

Interior space design significantly influences residents' daily lives. However, the process often presents high barriers and complex reasoning for users, leading to semantic losses in articulating comprehensive requirements and communicating them to designers. This study proposes the Mental-Gen design method, which focuses on interpreting users' spatial design intentions at neural level and expressing them through generative AI models. We employed unsupervised learning methods to detect similarities in users' brainwave responses to different spatial features, assess the feasibility of BCI commands. We trained and refined generative AI models for each valuable design command. The command prediction process adopted the motor imagery paradigm from BCI research. We trained Support Vector Machine (SVM) models to predict design commands for different spatial features based on EEG features. The results indicate that the Mental-Gen method can effectively interpret design intentions through brainwave signals, assisting users in achieving satisfactory interior space designs using imagined commands., Comment: 18 pages, 8 figures

Sensitive information detection is crucial in content moderation to maintain safe online communities. Assisting in this traditionally manual process could relieve human moderators from overwhelming and tedious tasks, allowing them to focus solely on flagged content that may pose potential risks. Rapidly advancing large language models (LLMs) are known for their capability to understand and process natural language and so present a potential solution to support this process. This study explores the capabilities of five LLMs for detecting sensitive messages in the mental well-being domain within two online datasets and assesses their performance in terms of accuracy, precision, recall, F1 scores, and consistency. Our findings indicate that LLMs have the potential to be integrated into the moderation workflow as a convenient and precise detection tool. The best-performing model, GPT-4o, achieved an average accuracy of 99.5\% and an F1-score of 0.99. We discuss the advantages and potential challenges of using LLMs in the moderation workflow and suggest that future research should address the ethical considerations of utilising this technology., Comment: 2024 Oz CHI conference

Due to domain shift, deep learning image classifiers perform poorly when applied to a domain different from the training one. For instance, a classifier trained on chest X-ray (CXR) images from one hospital may not generalize to images from another hospital due to variations in scanner settings or patient characteristics. In this paper, we introduce our CROCODILE framework, showing how tools from causality can foster a model's robustness to domain shift via feature disentanglement, contrastive learning losses, and the injection of prior knowledge. This way, the model relies less on spurious correlations, learns the mechanism bringing from images to prediction better, and outperforms baselines on out-of-distribution (OOD) data. We apply our method to multi-label lung disease classification from CXRs, utilizing over 750000 images from four datasets. Our bias-mitigation method improves domain generalization and fairness, broadening the applicability and reliability of deep learning models for a safer medical image analysis. Find our code at: https://github.com/gianlucarloni/crocodile., Comment: MICCAI 2024 UNSURE Workshop, Accepted for presentation, Submitted Manuscript Version, 10 pages

Maintenance decisions range from the simple detection of faults to ultimately predicting future failures and solving the problem. These traditionally human decisions are nowadays increasingly supported by data and the ultimate aim is to make them autonomous. This paper explores the challenges encountered in data driven maintenance, and proposes to consider four aspects in a maturity framework: data / decision maturity, the translation from the real world to data, the computability of decisions (using models) and the causality in the obtained relations. After a discussion of the theoretical concepts involved, the exploration continues by considering a practical fault detection and identification problem. Two approaches, i.e. experience based and model based, are compared and discussed in terms of the four aspects in the maturity framework. It is observed that both approaches yield the same decisions, but still differ in the assignment of causality. This confirms that a maturity assessment not only concerns the type of decision, but should also include the other proposed aspects., Comment: in Proceedings of the 8th European Conference of the Prognostics and Health Management Society 2024

This work develops a robust and efficient framework of the adjoint gradient-based aerodynamic shape optimization (ASO) using high-order discontinuous Galerkin methods (DGMs) as the CFD solver. The adjoint-enabled gradients based on different CFD solvers or solution representations are derived in detail, and the potential advantage of DG representations is discovered that the adjoint gradient computed by the DGMs contains a modification term which implies information of higher-order moments of the solution as compared with finite volume methods (FVMs). A number of numerical cases are tested for investigating the impact of different CFD solvers (including DGMs and FVMs) on the evaluation of the adjoint-enabled gradients. The numerical results demonstrate that the DGMs can provide more precise adjoint gradients even on a coarse mesh as compared with the FVMs under coequal computational costs, and extend the capability to explore the design space, further leading to acquiring the aerodynamic shapes with more superior aerodynamic performance., Comment: 38 pages, 25 figures, submitted to AIAA Journal on 2024-07-01

This paper introduces the Structural Optimization gym (SOgym), a novel open-source Reinforcement Learning (RL) environment designed to advance machine learning in Topology Optimization (TO). SOgym enables RL agents to generate physically viable and structurally robust designs by integrating the physics of TO into the reward function. To enhance scalability, SOgym leverages feature-mapping methods as a mesh-independent interface between the environment and the agent, allowing efficient interaction with the design variables regardless of mesh resolution. Baseline results use a model-free Proximal Policy Optimization agent and a model-based DreamerV3 agent. Three observation space configurations were tested. The TopOpt game-inspired configuration, an interactive educational tool that improves students' intuition in designing structures to minimize compliance under volume constraints, performed best in terms of performance and sample efficiency. The 100M parameter version of DreamerV3 produced structures within 54% of the baseline compliance achieved by traditional optimization methods and a 0% disconnection rate, an improvement over supervised learning approaches that often struggle with disconnected load paths. When comparing the learning rates of the agents to those of engineering students from the TopOpt game experiment, the DreamerV3-100M model shows a learning rate approximately four orders of magnitude lower, an impressive feat for a policy trained from scratch through trial and error. These results suggest RL's potential to solve continuous TO problems and its capacity to explore and learn from diverse design solutions. SOgym provides a platform for developing RL agents for complex structural design challenges and is publicly available to support further research in the field.

Optimal mean shift vector (OMSV)-based importance sampling methods have long been prevalent in yield estimation and optimization as an industry standard. However, most OMSV-based methods are designed heuristically without a rigorous understanding of their limitations. To this end, we propose VIS, the first variational analysis framework for yield problems, enabling a systematic refinement for OMSV. For instance, VIS reveals that the classic OMSV is suboptimal, and the optimal/true OMSV should always stay beyond the failure boundary, which enables a free improvement for all OMSV-based methods immediately. Using VIS, we show a progressive refinement for the classic OMSV including incorporation of full covariance in closed form, adjusting for asymmetric failure distributions, and capturing multiple failure regions, each of which contributes to a progressive improvement of more than 2x. Inheriting the simplicity of OMSV, the proposed method retains simplicity and robustness yet achieves up to 29.03x speedup over the state-of-the-art (SOTA) methods. We also demonstrate how the SOTA yield optimization, ASAIS, can immediately benefit from our True OMSV, delivering a 1.20x and 1.27x improvement in performance and efficiency, respectively, without additional computational overhead., Comment: 2024 43rd ACM/IEEE International Conference on Computer-Aided Design (ICCAD)

Quantum computing has made significant progress in recent years, attracting immense interest not only in research laboratories but also in various industries. However, the application of quantum computing to solve real-world problems is still hampered by a number of challenges, including hardware limitations and a relatively under-explored landscape of quantum algorithms, especially when compared to the extensive development of classical computing. The design of quantum circuits, in particular parameterized quantum circuits (PQCs), which contain learnable parameters optimized by classical methods, is a non-trivial and time-consuming task requiring expert knowledge. As a result, research on the automated generation of PQCs, known as quantum architecture search (QAS), has gained considerable interest. QAS focuses on the use of machine learning and optimization-driven techniques to generate PQCs tailored to specific problems and characteristics of quantum hardware. In this paper, we provide an overview of QAS methods by examining relevant research studies in the field. We discuss main challenges in designing and performing an automated search for an optimal PQC, and survey ways to address them to ease future research.

We provide effective methods to construct and manipulate trilinear birational maps $\phi:(\mathbb{P}^1)^3\dashrightarrow \mathbb{P}^3$ by establishing a novel connection between birationality and tensor rank. These yield four families of nonlinear birational transformations between 3D spaces that can be operated with enough flexibility for applications in computer-aided geometric design. More precisely, we describe the geometric constraints on the defining control points of the map that are necessary for birationality, and present constructions for such configurations. For adequately constrained control points, we prove that birationality is achieved if and only if a certain $2\times 2\times 2$ tensor has rank one. As a corollary, we prove that the locus of weights that ensure birationality is $\mathbb{P}^1\times\mathbb{P}^1\times\mathbb{P}^1$. Additionally, we provide formulas for the inverse $\phi^{-1}$ as well as the explicit defining equations of the irreducible components of the base loci. Finally, we introduce a notion of "distance to birationality" for trilinear rational maps, and explain how to continuously deform birational maps., Comment: 30 pages, 12 figures

Marine debris poses a significant ecological threat to birds, fish, and other animal life. Traditional methods for assessing debris accumulation involve labor-intensive and costly manual surveys. This study introduces a framework that utilizes aerial imagery captured by drones to conduct remote trash surveys. Leveraging computer vision techniques, our approach detects, classifies, and maps marine debris distributions. The framework uses Grounding DINO, a transformer-based zero-shot object detector, and CLIP, a vision-language model for zero-shot object classification, enabling the detection and classification of debris objects based on material type without the need for training labels. To mitigate over-counting due to different views of the same object, Scale-Invariant Feature Transform (SIFT) is employed for duplicate matching using local object features. Additionally, we have developed a user-friendly web application that facilitates end-to-end analysis of drone images, including object detection, classification, and visualization on a map to support cleanup efforts. Our method achieves competitive performance in detection (0.69 mean IoU) and classification (0.74 F1 score) across seven debris object classes without labeled data, comparable to state-of-the-art supervised methods. This framework has the potential to streamline automated trash sampling surveys, fostering efficient and sustainable community-led cleanup initiatives., Comment: 9 pages, 6 figures, 2 tables, In Proceedings of the 7th ACM SIGCAS/SIGCHI Conference on Computing and Sustainable Societies

While recent advances in deep learning have demonstrated its transformative potential, its adoption for real-world manufacturing applications remains limited. We present an Explanation User Interface (XUI) for a state-of-the-art deep learning-based robot program optimizer which provides both naive and expert users with different user experiences depending on their skill level, as well as Explainable AI (XAI) features to facilitate the application of deep learning methods in real-world applications. To evaluate the impact of the XUI on task performance, user satisfaction and cognitive load, we present the results of a preliminary user survey and propose a study design for a large-scale follow-up study., Comment: 6 pages, 4 figures, accepted at the 2024 CIRP International Conference on Manufacturing Systems (CMS)

This paper introduces YOLOv8-TO, a novel approach for reverse engineering of topology-optimized structures into interpretable geometric parameters using the YOLOv8 instance segmentation model. Density-based topology optimization methods require post-processing to convert the optimal density distribution into a parametric representation for design exploration and integration with CAD tools. Traditional methods such as skeletonization struggle with complex geometries and require manual intervention. YOLOv8-TO addresses these challenges by training a custom YOLOv8 model to automatically detect and reconstruct structural components from binary density distributions. The model is trained on a diverse dataset of both optimized and random structures generated using the Moving Morphable Components method. A custom reconstruction loss function based on the dice coefficient of the predicted geometry is used to train the new regression head of the model via self-supervised learning. The method is evaluated on test sets generated from different topology optimization methods, including out-of-distribution samples, and compared against a skeletonization approach. Results show that YOLOv8-TO significantly outperforms skeletonization in reconstructing visually and structurally similar designs. The method showcases an average improvement of 13.84% in the Dice coefficient, with peak enhancements reaching 20.78%. The method demonstrates good generalization to complex geometries and fast inference times, making it suitable for integration into design workflows using regular workstations. Limitations include the sensitivity to non-max suppression thresholds. YOLOv8-TO represents a significant advancement in topology optimization post-processing, enabling efficient and accurate reverse engineering of optimized structures for design exploration and manufacturing.

In the present work, the ideal shear strength ({\tau}_is) of dilute Ni34XZ ternary alloys (X or Z = Al, Co, Cr, Fe, Mn, Mo, Nb, Si, Ti) are predicted by first-principles calculations based on density functional theory (DFT) in terms of pure alias shear deformations. The {\tau}_is results show that within the concentration up to 8.3% of alloying elements, {\tau}_is increases with composition in binary systems with Mn, Fe, and Co in ascending order, and decreases with composition with Nb, Si, Mo, Ti, Al, and Cr in descending order. The composition dependence of {\tau}_is in binary and ternary systems is modeled using the CALculation of PHAse Diagrams (CALPHAD) approach considering lattice instability, indicating that atomic bonding strength significantly influences {\tau}_is. Correlational analyses further show that lattice constant and elastic constant C11 affect {\tau}_is, the most out of the elemental features.

Over the past decade, deep learning helped solve manipulation problems across all domains of robotics. At the same time, industrial robots continue to be programmed overwhelmingly using traditional program representations and interfaces. This paper undertakes an analysis of this "AI adoption gap" from an industry practitioner's perspective. In response, we propose the BANSAI approach (Bridging the AI Adoption Gap via Neurosymbolic AI). It systematically leverages principles of neurosymbolic AI to establish data-driven, subsymbolic program synthesis and optimization in modern industrial robot programming workflow. BANSAI conceptually unites several lines of prior research and proposes a path toward practical, real-world validation., Comment: 6 pages, 3 figures, accepted at the 2024 CIRP International Conference on Manufacturing Systems (CMS)

A varying number of particles is one of the most relevant characteristics of systems of interest in nature and technology, ranging from the exchange of energy and matter with the surrounding environment to the change of particle number through internal dynamics such as reactions. The physico-mathematical modeling of these systems is extremely challenging, with the major difficulty being the time dependence of the number of degrees of freedom and the additional constraint that the increment or reduction of the number and species of particles must not violate basic physical laws. Theoretical models, in such a case, represent the key tool for the design of computational strategies for numerical studies that deliver trustful results. In this manuscript, we review complementary physico-mathematical approaches of varying number of particles inspired by rather different specific numerical goals. As a result of the analysis on the underlying common structure of these models, we propose a unifying master equation for general dynamical systems with varying number of particles. This equation embeds all the previous models and can potentially model a much larger range of complex systems, ranging from molecular to social agent-based dynamics.

In this work, a cell agglomeration strategy for the cut cells arising in the extended discontinuous Galerkin (XDG) method is presented. Cut cells are a fundamental aspect of unfitted mesh approaches where complex geometries or interfaces separating sub-domains are embedded into Cartesian background grids to facilitate the mesh generation process. In such methods, arbitrary small cells occur due to the intersections of background cells with embedded geometries and lead to discretization difficulties due to their diminutive sizes. Furthermore, temporal evolutions of these geometries may lead to topological changes across different time steps. Both of these issues, i.e., small-cut cells and topological changes, can be addressed with a cell agglomeration technique. In this work, a comprehensive strategy for the typical issues associated with cell agglomeration in three-dimensional and multiprocessor simulations is provided. The proposed strategy is implemented into the open-source software package BoSSS and tested with 2- and 3-dimensional simulations of immersed boundary flows., Comment: 30 pages, 19 figures

This paper introduces iRoCo (intuitive Robot Control) - a framework for ubiquitous human-robot collaboration using a single smartwatch and smartphone. By integrating probabilistic differentiable filters, iRoCo optimizes a combination of precise robot control and unrestricted user movement from ubiquitous devices. We demonstrate and evaluate the effectiveness of iRoCo in practical teleoperation and drone piloting applications. Comparative analysis shows no significant difference between task performance with iRoCo and gold-standard control systems in teleoperation tasks. Additionally, iRoCo users complete drone piloting tasks 32\% faster than with a traditional remote control and report less frustration in a subjective load index questionnaire. Our findings strongly suggest that iRoCo is a promising new approach for intuitive robot control through smartwatches and smartphones from anywhere, at any time. The code is available at www.github.com/wearable-motion-capture, Comment: 7 pages, 7 Figures, 4 Tables, Conference: ICRA

The design optimization of ship hull form based on hydrodynamics theory and simulation-based design (SBD) technologies generally considers ship performance and energy efficiency performance as the design objective, which plays an important role in smart design and manufacturing of green ship. An optimal design of sustainable energy system requires multidisciplinary tools to build ships with the least resistance and energy consumption. Through a systematic approach, this paper presents the research progress of energy-efficient design of ship hull forms based on intelligent optimization techniques. We discuss different methods involved in the optimization procedure, especially the latest developments of intelligent optimization algorithms and surrogate models. Moreover, current development trends and technical challenges of multidisciplinary design optimization and surrogate-assisted evolutionary algorithms for ship design are further analyzed. We explore the gaps and potential future directions, so as to paving the way towards the design of the next generation of more energy-efficient ship hull form., Comment: 30 pages, 8 figures

Bayesian optimization (BO) with Gaussian processes (GP) has become an indispensable algorithm for black box optimization problems. Not without a dash of irony, BO is often considered a black box itself, lacking ways to provide reasons as to why certain parameters are proposed to be evaluated. This is particularly relevant in human-in-the-loop applications of BO, such as in robotics. We address this issue by proposing ShapleyBO, a framework for interpreting BO's proposals by game-theoretic Shapley values.They quantify each parameter's contribution to BO's acquisition function. Exploiting the linearity of Shapley values, we are further able to identify how strongly each parameter drives BO's exploration and exploitation for additive acquisition functions like the confidence bound. We also show that ShapleyBO can disentangle the contributions to exploration into those that explore aleatoric and epistemic uncertainty. Moreover, our method gives rise to a ShapleyBO-assisted human machine interface (HMI), allowing users to interfere with BO in case proposals do not align with human reasoning. We demonstrate this HMI's benefits for the use case of personalizing wearable robotic devices (assistive back exosuits) by human-in-the-loop BO. Results suggest human-BO teams with access to ShapleyBO can achieve lower regret than teams without., Comment: Preprint. Copyright by the authors. 19 pages, 24 figures

This work highlights an approach for incorporating realistic uncertainties into scientific computing workflows based on finite elements, focusing on applications in computational mechanics and design optimization. We leverage Mat\'ern-type Gaussian random fields (GRFs) generated using the SPDE method to model aleatoric uncertainties, including environmental influences, variating material properties, and geometric ambiguities. Our focus lies on delivering practical GRF realizations that accurately capture imperfections and variations and understanding how they impact the predictions of computational models and the topology of optimized designs. We describe a numerical algorithm based on solving a generalized SPDE to sample GRFs on arbitrary meshed domains. The algorithm leverages established techniques and integrates seamlessly with the open-source finite element library MFEM and associated scientific computing workflows, like those found in industrial and national laboratory settings. Our solver scales efficiently for large-scale problems and supports various domain types, including surfaces and embedded manifolds. We showcase its versatility through biomechanics and topology optimization applications. The flexibility and efficiency of SPDE-based GRF generation empower us to run large-scale optimization problems on 2D and 3D domains, including finding optimized designs on embedded surfaces, and to generate topologies beyond the reach of conventional techniques. Moreover, these capabilities allow us to model geometric uncertainties of reconstructed submanifolds, such as the surfaces of cerebral aneurysms. In addition to offering benefits in these specific domains, the proposed techniques transcend specific applications and generalize to arbitrary forward and backward problems in uncertainty quantification involving finite elements., Comment: 38 pages, 21 figures

This chapter explores the practice of conducting user research studies and design assessments in virtual reality (VR). An overview of key VR hardware and software tools is provided, including game engines, such as Unity and Unreal Engine. Qualitative and quantitative research methods, along with their various synergies with VR, are likewise discussed, and some of the challenges associated with VR, such as limited sensory stimulation, are reflected upon. VR is proving particularly useful in the context of space systems development, where its utilisation offers a cost-effective and secure method for simulating extraterrestrial environments, allowing for rapid prototyping and evaluation of innovative concepts under representative operational conditions. To illustrate this, we present a case study detailing the application of VR to aid aerospace engineers testing their ideas with end-users and stakeholders during early design stages of the European Space Agency's (ESA) prospective Argonaut lunar lander. This case study demonstrates the effectiveness of VR simulations in gathering important feedback concerning the operability of the Argonaut lander in poor lighting conditions as well as surfacing relevant ergonomics considerations and constraints. The chapter concludes by discussing the strengths and weaknesses associated with VR-based user studies and proposes future research directions, emphasising the necessity for novel VR interfaces to overcome existing technical limitations.

Space agencies are in the process of drawing up carefully thought-out Concepts of Operations (ConOps) for future human missions on the Moon. These are typically assessed and validated through costly and logistically demanding analogue field studies. While interactive simulations in Virtual Reality (VR) offer a comparatively cost-effective alternative, they have faced criticism for lacking the fidelity of real-world deployments. This paper explores the applicability of passive haptic interfaces in bridging the gap between simulated and real-world ConOps assessments. Leveraging passive haptic props (equipment mockup and astronaut gloves), we virtually recreated the Apollo 12 mission procedure and assessed it with experienced astronauts and other space experts. Quantitative and qualitative findings indicate that haptics increased presence and embodiment, thus improving perceived simulation fidelity and validity of user reflections. We conclude by discussing the potential role of passive haptic modalities in facilitating early-stage ConOps assessments for human endeavours on the Moon and beyond., Comment: CHI'24, May 11-16, 2024, Honolulu, HI, USA

Illumination of scenes is usually generated in computer graphics using polygonal meshes. In this paper, we present a geometric method using projections. Starting from an implicit polynomial equation of a surface in 3-D or a curve in 2-D, we provide a semi-algebraic representation of each part of the construction. To solve polynomial condition systems and find constrained regions, we apply algebraic computational algorithms for computing the Gr{\" o}bner basis and cylindrical algebraic decomposition. The final selection of illuminated and self-shaded components for polynomial surfaces of a degree higher than three is discussed. The text is accompanied by visualizations of illumination of surfaces up to degree eight.

Smart contracts, as a key component of blockchain technology, play a crucial role in ensuring the automation of transactions and adherence to protocol rules. However, smart contracts are susceptible to security vulnerabilities, which, if exploited, can lead to significant asset losses. This study explores the potential of enhancing smart contract security audits using the GPT-4 model. We utilized a dataset of 35 smart contracts from the SolidiFI-benchmark vulnerability library, containing 732 vulnerabilities, and compared it with five other vulnerability detection tools to evaluate GPT-4's ability to identify seven common types of vulnerabilities. Moreover, we assessed GPT-4's performance in code parsing and vulnerability capture by simulating a professional auditor's auditing process using CoT(Chain of Thought) prompts based on the audit reports of eight groups of smart contracts. We also evaluated GPT-4's ability to write Solidity Proof of Concepts (PoCs). Through experimentation, we found that GPT-4 performed poorly in detecting smart contract vulnerabilities, with a high Precision of 96.6%, but a low Recall of 37.8%, and an F1-score of 41.1%, indicating a tendency to miss vulnerabilities during detection. Meanwhile, it demonstrated good contract code parsing capabilities, with an average comprehensive score of 6.5, capable of identifying the background information and functional relationships of smart contracts; in 60% of the cases, it could write usable PoCs, suggesting GPT-4 has significant potential application in PoC writing. These experimental results indicate that GPT-4 lacks the ability to detect smart contract vulnerabilities effectively, but its performance in contract code parsing and PoC writing demonstrates its significant potential as an auxiliary tool in enhancing the efficiency and effectiveness of smart contract security audits., Comment: 21 pages, 10 figures

We ideate a future design workflow that involves AI technology. Drawing from activity and communication theory, we attempt to isolate the new value large AI models can provide design compared to past technologies. We arrive at three affordances -- dynamic grounding, constructive negotiation, and sustainable motivation -- that summarize latent qualities of natural language-enabled foundation models that, if explicitly designed for, can support the process of design. Through design fiction, we then imagine a future interface as a diegetic prototype, the story of Squirrel Game, that demonstrates each of our three affordances in a realistic usage scenario. Our design process, terminology, and diagrams aim to contribute to future discussions about the relative affordances of AI technology with regard to collaborating with human designers., Comment: 12 pages, 4 figures

Many disciplines of science and engineering deal with problems related to compositions, ranging from chemical compositions in materials science to portfolio compositions in economics. They exist in non-Euclidean simplex spaces, causing many standard tools to be incorrect or inefficient, which is significant in combinatorically or structurally challenging spaces exemplified by Compositionally Complex Materials (CCMs) and Functionally Graded Materials (FGMs). Here, we explore them conceptually in terms of problem spaces and quantitatively in terms of computational feasibility. This work implements several essential methods specific to the compositional (simplex) spaces through a high-performance open-source library nimplex. Most significantly, we derive and implement an algorithm for constructing a novel n-dimensional simplex graph data structure, which contains all discretized compositions and all possible neighbor-to-neighbor transitions as pointer arrays. Critically, no distance or neighborhood calculations are performed, instead leveraging pure combinatorics and the ordering in procedurally generated simplex grids, keeping the algorithm $\mathcal{O}(N)$, so that graphs with billions of transitions take seconds to construct on a laptop. Furthermore, we demonstrate how such graph representations can be combined to express path-planning problem spaces and to incorporate prior knowledge while keeping the problem space homogeneous. This allows for efficient deployment of existing high-performance gradient descent, graph traversal search, and other path optimization algorithms., Comment: 18 pages; 11 figures; software source code at https://github.com/amkrajewski/nimplex and documentation at https://nimplex.phaseslab.org; minor updates in V2

Two studies of a human-AI collaborative design tool were carried out in order to understand the influence design recommendations have on the design process. The tool investigated is based on an evolutionary algorithm attempting to design a virtual car to travel as far as possible in a fixed time. Participants were able to design their own cars, make recommendations to the algorithm and view sets of recommendations from the algorithm. The algorithm-recommended sets were designs which had been previously tested; some sets were simply randomly picked and other sets were picked using MAP-Elites. In the first study 808 design sessions were recorded as part of a science outreach program, each with analytical data of how each participant used the tool. To provide context to this quantitative data, a smaller double-blind lab study was also carried out with 12 participants. In the lab study the same quantitative data from the large scale study was collected alongside responses to interview questions. Although there is some evidence that the MAP-Elites provide higher-quality individual recommendations, neither study provides convincing evidence that these recommendations have a more positive influence on the design process than simply a random selection of designs. In fact, it seems that providing a combination of MAP-Elites and randomly selected recommendations is beneficial to the process. Furthermore, simply viewing recommendations from the MAP-Elites had a positive influence on engagement in the design task and the quality of the final design produced. Our findings are significant both for researchers designing new mixed-initiative tools, and those who wish to evaluate existing tools. Most significantly, we found that metrics researchers currently use to evaluate the success of human-AI collaborative algorithms do not measure the full influence these algorithms have on the design process., Comment: 17 pages

The capability of holography to project three-dimensional (3D) images and correct for aberrations offers much potential to enhance optical control in light-based 3D printing. Notably, multi-beam multi-wavelength holographic systems represent an important development direction for advanced volumetric additive manufacturing (VAM). Nonetheless, searching for the optimal 3D holographic projection is a challenging ill-posed problem due to the physical constraints involved. This work introduces an optimization framework to search for the optimal set of projection parameters, namely phase modulation values and amplitudes, for multi-beam holographic lithography. The proposed framework is more general than classical phase retrieval algorithms in the sense that it can simultaneously optimize multiple holographic beams and model the coupled non-linear material response created by co-illumination of the holograms. The framework incorporates efficient methods to evaluate holographic light fields, resample quantities across coordinate grids, and compute the coupled exposure effect. The efficacy of this optimization method is tested for a variety of setup configurations that involve multi-wavelength illumination, two-photon absorption, and time-multiplexed scanning beam. A special test case of holo-tomographic patterning optimized 64 holograms simultaneously and achieved the lowest error among all demonstrations. This variant of tomographic VAM shows promises for achieving high-contrast microscale fabrication. All testing results indicate that a fully coupled optimization offers superior solutions relative to a decoupled optimization approach., Comment: 18 pages, 9 figures