Search

Achieving the UN Sustainable Development Goals (SDGs) demands adequate levels of awareness and actions to address sustainability challenges. Software systems will play an important role in moving towards these targets. Sustainability skills are necessary to support the development of software systems and to provide sustainable IT-supported services for citizens. While there is a growing number of academic bodies, including sustainability education in engineering and computer science curricula, there is not yet comprehensive research on the competencies and skills required by IT professionals to develop such systems. This study aims to identify the industrial sustainability needs for education and training from software engineers' perspective. We conducted interviews and focus groups with experts from twenty-eight organisations with an IT division from nine countries to understand their interests, goals and achievements related to sustainability, and the skills and competencies needed to achieve their goals. Our findings show that organisations are interested in sustainability, both idealistically and increasingly for core business reasons. They seek to improve the sustainability of processes and products but encounter difficulties, like the trade-off between short-term financial profitability and long-term sustainability goals. To fill the gaps, they have promoted in-house training courses, collaborated with universities, and sent employees to external training. The acquired competencies make sustainability an integral part of software development. We conclude that educational programs should include knowledge and skills on core sustainability concepts, system thinking, soft skills, technical sustainability, sustainability impact and measurements, values and ethics, standards and legal aspects, and advocacy and lobbying.

Needle positioning is essential for various medical applications such as epidural anaesthesia. Physicians rely on their instincts while navigating the needle in epidural spaces. Thereby, identifying the tissue structures may be helpful to the physician as they can provide additional feedback in the needle insertion process. To this end, we propose a deep neural network that classifies the tissues from the phase and intensity data of complex OCT signals acquired at the needle tip. We investigate the performance of the deep neural network in a limited labelled dataset scenario and propose a novel contrastive pretraining strategy that learns invariant representation for phase and intensity data. We show that with 10% of the training set, our proposed pretraining strategy helps the model achieve an F1 score of 0.84 whereas the model achieves an F1 score of 0.60 without it. Further, we analyse the importance of phase and intensity individually towards tissue classification.

Visual analytics tools can help illustrate the spread of infectious diseases and enable informed decisions on epidemiological and public health issues. To create visualisation tools that are intuitive, easy to use, and effective in communicating information, continued research and development focusing on user-centric and methodological design models is extremely important. As a contribution to this topic, this paper presents the design and development process of the visual analytics application ESID (Epidemiological Scenarios for Infectious Diseases). ESID is a visual analytics tool aimed at projecting the future developments of infectious disease spread using reported and simulated data based on sound mathematical-epidemiological models. The development process involved a collaborative and participatory design approach with project partners from diverse scientific fields. The findings from these studies, along with the guidelines derived from them, played a pivotal role in shaping the visualisation tool., Comment: 7 pages, 4 images and 2 table, IEEE VIS Workshop on Visualization for Pandemic and Emergency Responses 2023 (Vis4PandEmRes)

Twenty-six years ago a small committee report, building on earlier studies, expounded a compelling and poetic vision for the future of astronomy, calling for an infrared-optimized space telescope with an aperture of at least $4m$. With the support of their governments in the US, Europe, and Canada, 20,000 people realized that vision as the $6.5m$ James Webb Space Telescope. A generation of astronomers will celebrate their accomplishments for the life of the mission, potentially as long as 20 years, and beyond. This report and the scientific discoveries that follow are extended thank-you notes to the 20,000 team members. The telescope is working perfectly, with much better image quality than expected. In this and accompanying papers, we give a brief history, describe the observatory, outline its objectives and current observing program, and discuss the inventions and people who made it possible. We cite detailed reports on the design and the measured performance on orbit., Comment: Accepted by PASP for the special issue on The James Webb Space Telescope Overview, 29 pages, 4 figures

Paranasal anomalies are commonly discovered during routine radiological screenings and can present with a wide range of morphological features. This diversity can make it difficult for convolutional neural networks (CNNs) to accurately classify these anomalies, especially when working with limited datasets. Additionally, current approaches to paranasal anomaly classification are constrained to identifying a single anomaly at a time. These challenges necessitate the need for further research and development in this area. In this study, we investigate the feasibility of using a 3D convolutional neural network (CNN) to classify healthy maxillary sinuses (MS) and MS with polyps or cysts. The task of accurately identifying the relevant MS volume within larger head and neck Magnetic Resonance Imaging (MRI) scans can be difficult, but we develop a straightforward strategy to tackle this challenge. Our end-to-end solution includes the use of a novel sampling technique that not only effectively localizes the relevant MS volume, but also increases the size of the training dataset and improves classification results. Additionally, we employ a multiple instance ensemble prediction method to further boost classification performance. Finally, we identify the optimal size of MS volumes to achieve the highest possible classification performance on our dataset. With our multiple instance ensemble prediction strategy and sampling strategy, our 3D CNNs achieve an F1 of 0.85 whereas without it, they achieve an F1 of 0.70. We demonstrate the feasibility of classifying anomalies in the MS. We propose a data enlarging strategy alongside a novel ensembling strategy that proves to be beneficial for paranasal anomaly classification in the MS.

This paper addresses optimal control problems governed by history-dependent EVIs with viscosity. One of the prominent properties of the state system is its non-smooth nature, so that the application of standard adjoint calculus is excluded. We extend the results from [7] by showing that history-dependent EVIs with viscosity can be formulated as non-smooth ODEs in Hilbert space in a general setting. The Hadamard directional differentiability of the solution map is investigated. Based on previous results, this allows us to establish strong stationary conditions for two different viscous damage models with fatigue., Comment: 25 pages. arXiv admin note: text overlap with arXiv:2302.05627

Autonomous vehicles (AVs) are being rapidly introduced into our lives. However, public misunderstanding and mistrust have become prominent issues hindering the acceptance of these driverless technologies. The primary objective of this study is to evaluate the effectiveness of a driving simulator to help the public gain an understanding of AVs and build trust in them. To achieve this aim, we built an integrated simulation platform, designed various driving scenarios, and recruited 28 participants for the experiment. The study results indicate that a driving simulator effectively decreases the participants' perceived risk of AVs and increases perceived usefulness. The proposed methodologies and findings of this study can be further explored by auto manufacturers and policymakers to provide user-friendly AV design.

Entropy production is the hallmark of nonequilibrium physics, quantifying irreversibility, dissipation, and the efficiency of energy transduction processes. Despite many efforts, its measurement at the nanoscale remains challenging. We introduce a variance sum rule for displacement and force variances that permits us to measure the entropy production rate $\sigma$ in nonequilibrium steady states. We first illustrate it for directly measurable forces, such as an active Brownian particle in an optical trap. We then apply the variance sum rule to flickering experiments in human red blood cells. We find that $\sigma$ is spatially heterogeneous with a finite correlation length and its average value agrees with calorimetry measurements. The VSR paves the way to derive $\sigma$ using force spectroscopy and time-resolved imaging in living and active matter., Comment: 5 pages and 4 figures. It also contains Supp. Info. with 6 additional figures and 4 tables

We derive a bound for entropy production in terms of the mean of normalizable path-antisymmetric observables. The optimal observable for this bound is shown to be the signum of entropy production, which is often easier determined or estimated than entropy production itself. It can be preserved under coarse graining by use of a simple path grouping algorithm. We demonstrate this relation and its properties using a driven network on a ring, for which the bound saturates for short times for any driving strength. This work can open a way to systematic coarse graining of entropy production., Comment: 5 pages, 2 figures

Motivated by fatigue damage models, this paper addresses optimal control problems governed by a non-smooth system featuring two non-differentiable mappings. This consists of a coupling between a doubly non-smooth history-dependent evolution and an elliptic PDE. After proving the directional differentiability of the associated solution mapping, an optimality system which is stronger than the one obtained by classical smoothening procedures is derived. If one of the non-differentiable mappings becomes smooth, the optimality conditions are of strong stationary type, i.e., equivalent to the primal necessary optimality condition., Comment: 31 pages

Motivated by the residual type neural networks (ResNet), this paper studies optimal control problems constrained by a non-smooth integral equation. Such non-smooth equations, for instance, arise in the continuous representation of fractional deep neural networks (DNNs). Here the underlying non-differentiable function is the ReLU or max function. The control enters in a nonlinear and multiplicative manner and we additionally impose control constraints. Because of the presence of the non-differentiable mapping, the application of standard adjoint calculus is excluded. We derive strong stationary conditions by relying on the limited differentiability properties of the non-smooth map. While traditional approaches smoothen the non-differentiable function, no such smoothness is retained in our final strong stationarity system. Thus, this work also closes a gap which currently exists in continuous neural networks with ReLU type activation function.

For decades, motorsport has been an incubator for innovations in the automotive sector and brought forth systems like disk brakes or rearview mirrors. Autonomous racing series such as Roborace, F1Tenth, or the Indy Autonomous Challenge (IAC) are envisioned as playing a similar role within the autonomous vehicle sector, serving as a proving ground for new technology at the limits of the autonomous systems capabilities. This paper outlines the software stack and approach of the TUM Autonomous Motorsport team for their participation in the Indy Autonomous Challenge, which holds two competitions: A single-vehicle competition on the Indianapolis Motor Speedway and a passing competition at the Las Vegas Motor Speedway. Nine university teams used an identical vehicle platform: A modified Indy Lights chassis equipped with sensors, a computing platform, and actuators. All the teams developed different algorithms for object detection, localization, planning, prediction, and control of the race cars. The team from TUM placed first in Indianapolis and secured second place in Las Vegas. During the final of the passing competition, the TUM team reached speeds and accelerations close to the limit of the vehicle, peaking at around 270 km/h and 28 ms2. This paper will present details of the vehicle hardware platform, the developed algorithms, and the workflow to test and enhance the software applied during the two-year project. We derive deep insights into the autonomous vehicle's behavior at high speed and high acceleration by providing a detailed competition analysis. Based on this, we deduce a list of lessons learned and provide insights on promising areas of future work based on the real-world evaluation of the displayed concepts., Comment: 37 pages, 18 figures, 2 tables

With the continued growth in field-programmable gate array (FPGA) capacity and their incorporation into new environments such as datacenters, we have witnessed the introduction of a new class of reconfigurable acceleration devices (RADs) that go beyond conventional FPGA architectures. These devices combine a reconfigurable fabric with coarse-grained domain-specialized accelerator blocks all connected via a high-performance packet-switched network-on-chip (NoC) for efficient system-wide communication. However, we lack the tools necessary to efficiently explore the huge design space for RADs, study the complex interactions between their different components and evaluate various combinations of design choices. In this work, we develop RAD-Sim, a cycle-level architecture simulator that allows rapid application-driven exploration of the design space of novel RADs. To showcase the capabilities of RADSim, we map and simulate a state-of-the-art deep learning (DL) inference overlay on a RAD instance incorporating an FPGA fabric and a complex of hard matrix-vector multiplication engines, communicating over a system-wide NoC. Through this example, we show how RAD-Sim can help architects quantify the effect of changing specific architecture parameters on end-to-end application performance., Comment: Published in the 2022 proceedings of the International Conference on Field-Programmable Logic and Applications (FPL)

Resonance expansions are an intuitive approach to capture the interaction of an optical resonator with light. Here, we present a quasinormal mode expansion approach for quadratic observables exploiting the rigorous Riesz projection method. We demonstrate the approach by a numerical implementation of a state-of-the-art quantum light source and emphasize the ability of the approach to provide modal expansions outside the underlying nanophotonic resonator.

We present a numerical investigation of directly fiber-coupled hybrid circular Bragg gratings (CBGs) featuring electrical control for operation in the application relevant wavelength regimes around 930 nm as well as the telecom O- and C-band. We use a surrogate model combined with a Bayesian optimization approach to perform numerical optimization of the device performance which takes into account robustness with respect to fabrication tolerances. The proposed high-performance designs combine hCBGs with a dielectric planarization and a transparent contact material, enabling >86% direct fiber coupling efficiency (up to >93% efficiency into NA 0.8) while exhibiting Purcell Factors >20. Especially the proposed designs for the telecom range prove robust and can sustain expected fiber efficiencies of more than $(82.2\pm4.1)^{+2.2}_{-5.5}$% and expected average Purcell Factors of up to $(23.2\pm2.3)^{+3.2}_{-3.0}$ assuming conservative fabrication accuracies. The wavelength of maximum Purcell enhancement proves to be the most affected performance parameter by the deviations. Finally, we show that electrical field strengths suitable for Stark-tuning of an embedded quantum dot can be reached in the identified designs., Comment: Main text including Method section, (15 pages, 5 figures, and 50 references). The data sets and used code in this work is available on Zenodo (see reference in the main text)

In this paper, we present a novel method for integrating 3D LiDAR depth measurements into the existing ORB-SLAM3 by building upon the RGB-D mode. We propose and compare two methods of depth map generation: conventional computer vision methods, namely an inverse dilation operation, and a supervised deep learning-based approach. We integrate the former directly into the ORB-SLAM3 framework by adding a so-called RGB-L (LiDAR) mode that directly reads LiDAR point clouds. The proposed methods are evaluated on the KITTI Odometry dataset and compared to each other and the standard ORB-SLAM3 stereo method. We demonstrate that, depending on the environment, advantages in trajectory accuracy and robustness can be achieved. Furthermore, we demonstrate that the runtime of the ORB-SLAM3 algorithm can be reduced by more than 40 % compared to the stereo mode. The related code for the ORB-SLAM3 RGB-L mode will be available as open-source software under https://github.com/TUMFTM/ORB SLAM3 RGBL., Comment: Accepted at ICCCR 2023

Deep learning (DL) algorithms can be used to automate paranasal anomaly detection from Magnetic Resonance Imaging (MRI). However, previous works relied on supervised learning techniques to distinguish between normal and abnormal samples. This method limits the type of anomalies that can be classified as the anomalies need to be present in the training data. Further, many data points from normal and anomaly class are needed for the model to achieve satisfactory classification performance. However, experienced clinicians can segregate between normal samples (healthy maxillary sinus) and anomalous samples (anomalous maxillary sinus) after looking at a few normal samples. We mimic the clinicians ability by learning the distribution of healthy maxillary sinuses using a 3D convolutional auto-encoder (cAE) and its variant, a 3D variational autoencoder (VAE) architecture and evaluate cAE and VAE for this task. Concretely, we pose the paranasal anomaly detection as an unsupervised anomaly detection problem. Thereby, we are able to reduce the labelling effort of the clinicians as we only use healthy samples during training. Additionally, we can classify any type of anomaly that differs from the training distribution. We train our 3D cAE and VAE to learn a latent representation of healthy maxillary sinus volumes using L1 reconstruction loss. During inference, we use the reconstruction error to classify between normal and anomalous maxillary sinuses. We extract sub-volumes from larger head and neck MRIs and analyse the effect of different fields of view on the detection performance. Finally, we report which anomalies are easiest and hardest to classify using our approach. Our results demonstrate the feasibility of unsupervised detection of paranasal anomalies from MRIs with an AUPRC of 85% and 80% for cAE and VAE, respectively.

Motorsport has always been an enabler for technological advancement, and the same applies to the autonomous driving industry. The team TUM Auton-omous Motorsports will participate in the Indy Autonomous Challenge in Octo-ber 2021 to benchmark its self-driving software-stack by racing one out of ten autonomous Dallara AV-21 racecars at the Indianapolis Motor Speedway. The first part of this paper explains the reasons for entering an autonomous vehicle race from an academic perspective: It allows focusing on several edge cases en-countered by autonomous vehicles, such as challenging evasion maneuvers and unstructured scenarios. At the same time, it is inherently safe due to the motor-sport related track safety precautions. It is therefore an ideal testing ground for the development of autonomous driving algorithms capable of mastering the most challenging and rare situations. In addition, we provide insight into our soft-ware development workflow and present our Hardware-in-the-Loop simulation setup. It is capable of running simulations of up to eight autonomous vehicles in real time. The second part of the paper gives a high-level overview of the soft-ware architecture and covers our development priorities in building a high-per-formance autonomous racing software: maximum sensor detection range, relia-ble handling of multi-vehicle situations, as well as reliable motion control under uncertainty.

To better understand the intersections of race, ethnicity, gender identity, and sexual orientation, this report presents data drawn from the California Healthy Kids Survey (2017-2019) regarding high school students' social and emotional well-being, school experiences, engagement, and their perceptions of the supports they received at school. With over 559,120 student responses, results are disaggregated by race and ethnicity as well as by gender identity and sexual orientation. The report also further disaggregates the data for Asian students by Asian group to reveal differences often masked by aggregate data. Educators can use this report to better understand how the provision of key supports may help mitigate disparities in student outcomes and promote positive student experiences in school for LGBTQ students and students of color.

Currently ALS is undergoing an upgrade to ALSU to produce 100 times brighter soft X-ray light. The LLRF system for Accumulator Ring (AR) is composed of two identical LLRF stations, for driving RF amplifiers. The closed loop RF amplitude and phase stability is measured as $< 0.1\%$ and $< 0.1^\circ$ respectively, using the non-IQ digital down conversion together with analog up/down conversion, under a system-on-chip architecture. Realtime interlock system is implemented with $< 2 \mu$s latency, for machine protection against arc flash and unexpected RF power. Control interfaces are developed to enable PLC-FPGA-EPICS communication to support operation, timing, cavity tuning, and interlock systems. The LLRF system handles alignment of buckets to swap beams between AR and Storage Ring by synchronous phase loop ramping between the two cavities. The system also includes an optimization routine to characterize the loop dynamics and determine optimal operating point using a built-in network analyzer feature. A cavity emulator of 31 kHz bandwidth is integrated with the LLRF system to validate the performance of the overall system being developed., Comment: Talk presented at LLRF Workshop 2022 (LLRF2022, arXiv:2208.13680)

Autonomous racing with scaled race cars has gained increasing attention as an effective approach for developing perception, planning and control algorithms for safe autonomous driving at the limits of the vehicle's handling. To train agile control policies for autonomous racing, learning-based approaches largely utilize reinforcement learning, albeit with mixed results. In this study, we benchmark a variety of imitation learning policies for racing vehicles that are applied directly or for bootstrapping reinforcement learning both in simulation and on scaled real-world environments. We show that interactive imitation learning techniques outperform traditional imitation learning methods and can greatly improve the performance of reinforcement learning policies by bootstrapping thanks to its better sample efficiency. Our benchmarks provide a foundation for future research on autonomous racing using Imitation Learning and Reinforcement Learning.

Robot localization is an inverse problem of finding a robot's pose using a map and sensor measurements. In recent years, Invertible Neural Networks (INNs) have successfully solved ambiguous inverse problems in various fields. This paper proposes a framework that solves the localization problem with INN. We design an INN that provides implicit map representation in the forward path and localization in the inverse path. By sampling the latent space in evaluation, Local\_INN outputs robot poses with covariance, which can be used to estimate the uncertainty. We show that the localization performance of Local\_INN is on par with current methods with much lower latency. We show detailed 2D and 3D map reconstruction from Local\_INN using poses exterior to the training set. We also provide a global localization algorithm using Local\_INN to tackle the kidnapping problem.

Deep reinforcement learning (DRL) is a promising method to learn control policies for robots only from demonstration and experience. To cover the whole dynamic behaviour of the robot, DRL training is an active exploration process typically performed in simulation environments. Although this simulation training is cheap and fast, applying DRL algorithms to real-world settings is difficult. If agents are trained until they perform safely in simulation, transferring them to physical systems is difficult due to the sim-to-real gap caused by the difference between the simulation dynamics and the physical robot. In this paper, we present a method of online training a DRL agent to drive autonomously on a physical vehicle by using a model-based safety supervisor. Our solution uses a supervisory system to check if the action selected by the agent is safe or unsafe and ensure that a safe action is always implemented on the vehicle. With this, we can bypass the sim-to-real problem while training the DRL algorithm safely, quickly, and efficiently. We compare our method with conventional learning in simulation and on a physical vehicle. We provide a variety of real-world experiments where we train online a small-scale vehicle to drive autonomously with no prior simulation training. The evaluation results show that our method trains agents with improved sample efficiency while never crashing, and the trained agents demonstrate better driving performance than those trained in simulation., Comment: 7 Pages, 10 Figures, 1 Table

Although robotics courses are well established in higher education, the courses often focus on theory and sometimes lack the systematic coverage of the techniques involved in developing, deploying, and applying software to real hardware. Additionally, most hardware platforms for robotics teaching are low-level toys aimed at younger students at middle-school levels. To address this gap, an autonomous vehicle hardware platform, called F1TENTH, is developed for teaching autonomous systems hands-on. This article describes the teaching modules and software stack for teaching at various educational levels with the theme of "racing" and competitions that replace exams. The F1TENTH vehicles offer a modular hardware platform and its related software for teaching the fundamentals of autonomous driving algorithms. From basic reactive methods to advanced planning algorithms, the teaching modules enhance students' computational thinking through autonomous driving with the F1TENTH vehicle. The F1TENTH car fills the gap between research platforms and low-end toy cars and offers hands-on experience in learning the topics in autonomous systems. Four universities have adopted the teaching modules for their semester-long undergraduate and graduate courses for multiple years. Student feedback is used to analyze the effectiveness of the F1TENTH platform. More than 80% of the students strongly agree that the hardware platform and modules greatly motivate their learning, and more than 70% of the students strongly agree that the hardware-enhanced their understanding of the subjects. The survey results show that more than 80% of the students strongly agree that the competitions motivate them for the course., Comment: 15 pages, 12 figures, 3 tables

Generating competitive strategies and performing continuous motion planning simultaneously in an adversarial setting is a challenging problem. In addition, understanding the intent of other agents is crucial to deploying autonomous systems in adversarial multi-agent environments. Existing approaches either discretize agent action by grouping similar control inputs, sacrificing performance in motion planning, or plan in uninterpretable latent spaces, producing hard-to-understand agent behaviors. Furthermore, the most popular policy optimization frameworks do not recognize the long-term effect of actions and become myopic. This paper proposes an agent action discretization method via abstraction that provides clear intentions of agent actions, an efficient offline pipeline of agent population synthesis, and a planning strategy using counterfactual regret minimization with function approximation. Finally, we experimentally validate our findings on scaled autonomous vehicles in a head-to-head racing setting. We demonstrate that using the proposed framework significantly improves learning, improves the win rate against different opponents, and the improvements can be transferred to unseen opponents in an unseen environment., Comment: Submitted to 2024 International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2024)

Using deep learning techniques, anomalies in the paranasal sinus system can be detected automatically in MRI images and can be further analyzed and classified based on their volume, shape and other parameters like local contrast. However due to limited training data, traditional supervised learning methods often fail to generalize. Existing deep learning methods in paranasal anomaly classification have been used to diagnose at most one anomaly. In our work, we consider three anomalies. Specifically, we employ a 3D CNN to separate maxillary sinus volumes without anomalies from maxillary sinus volumes with anomalies. To learn robust representations from a small labelled dataset, we propose a novel learning paradigm that combines contrastive loss and cross-entropy loss. Particularly, we use a supervised contrastive loss that encourages embeddings of maxillary sinus volumes with and without anomaly to form two distinct clusters while the cross-entropy loss encourages the 3D CNN to maintain its discriminative ability. We report that optimising with both losses is advantageous over optimising with only one loss. We also find that our training strategy leads to label efficiency. With our method, a 3D CNN classifier achieves an AUROC of 0.85 while a 3D CNN classifier optimised with cross-entropy loss achieves an AUROC of 0.66.

We consider a biased nearest-neighbor random walk on $\Z$ which at each step is trapped for some random time with random, site-dependent mean. We derive a simple formula for the speed function in terms of the model parameters., Comment: 10 pages, 3 figures