Hasil untuk "Communities. Classes. Races"

Marcello Cellina, Matteo Corno, Sergio Matteo Savaresi

Autonomous racing provides a controlled environment for testing the software and hardware of autonomous vehicles operating at their performance limits. Competitive interactions between multiple autonomous racecars however introduce challenging and potentially dangerous scenarios. Accurate and consistent vehicle detection and tracking is crucial for overtaking maneuvers, and low-latency sensor processing is essential to respond quickly to hazardous situations. This paper presents the LiDAR-based perception algorithms deployed on Team PoliMOVE's autonomous racecar, which won multiple competitions in the Indy Autonomous Challenge series. Our Vehicle Detection and Tracking pipeline is composed of a novel fast Point Cloud Segmentation technique and a specific Vehicle Pose Estimation methodology, together with a variable-step Multi-Target Tracking algorithm. Experimental results demonstrate the algorithm's performance, robustness, computational efficiency, and suitability for autonomous racing applications, enabling fully autonomous overtaking maneuvers at velocities exceeding 275 km/h.

Sahil Joshi, Agniva Chowdhury, Amar Kanakamedala et al.

Softmax Attention has a quadratic time complexity in sequence length, which becomes prohibitive to run at long contexts, even with highly optimized GPU kernels. For example, FlashAttention-2/3 (exact, GPU-optimized implementations of Softmax Attention) cannot complete a single forward-backward pass of a single attention layer once the context exceeds ~4 million tokens on an NVIDIA GH200 (96 GB). We introduce Repeated Arrays-of-Count Estimators (RACE) Attention, a kernel-inspired alternative to Softmax Attention that is strictly linear in sequence length and embedding size. RACE Attention replaces the exponential kernel with a sharpened angular similarity, and approximates attention outputs via Gaussian random projections and soft Locality-Sensitive Hashing (LSH), avoiding construction of the full attention matrix. Across language modeling, masked language modeling, and text/image classification, RACE Attention matches or outperforms strong baselines up to 64K seqeuence length while reducing wall-clock time and memory usage. In addition, we conduct a controlled scaling study on a single attention layer and demonstrate processing of up to 12 million tokens on an NVIDIA GH200 GPU and 75 million tokens on an Intel Xeon Gold 5220R CPU in a single forward-backward pass, which is well beyond the capabilities of current state-of-the-art attention implementations. RACE Attention thus offers a practical and theoretically grounded mechanism for long-context training on today's hardware. We release our code at https://github.com/sahiljoshi515/RACE_Attention.

Haocheng Zhao, Niklas Schlüter, Lukas Brunke et al.

Autonomous drone racing presents a challenging control problem, requiring real-time decision-making and robust handling of nonlinear system dynamics. While iterative learning model predictive control (LMPC) offers a promising framework for iterative performance improvement, its direct application to drone racing faces challenges like real-time compatibility or the trade-off between time-optimal and safe traversal. In this paper, we enhance LMPC with three key innovations: (1) an adaptive cost function that dynamically weights time-optimal tracking against centerline adherence, (2) a shifted local safe set to prevent excessive shortcutting and enable more robust iterative updates, and (3) a Cartesian-based formulation that accommodates safety constraints without the singularities or integration errors associated with Frenet-frame transformations. Results from extensive simulation and real-world experiments demonstrate that our improved algorithm can optimize initial trajectories generated by a wide range of controllers with varying levels of tuning for a maximum improvement in lap time by 60.85%. Even applied to the most aggressively tuned state-of-the-art model-based controller, MPCC++, on a real drone, a 6.05% improvement is still achieved. Overall, the proposed method pushes the drone toward faster traversal and avoids collisions in simulation and real-world experiments, making it a practical solution to improve the peak performance of drone racing.

Benedict Hildisch, Edoardo Ghignone, Nicolas Baumann et al.

Autonomous racing presents unique challenges due to its non-linear dynamics, the high speed involved, and the critical need for real-time decision-making under dynamic and unpredictable conditions. Most traditional Reinforcement Learning (RL) approaches rely on extensive simulation-based pre-training, which faces crucial challenges in transfer effectively to real-world environments. This paper introduces a robust on-board RL framework for autonomous racing, designed to eliminate the dependency on simulation-based pre-training enabling direct real-world adaptation. The proposed system introduces a refined Soft Actor-Critic (SAC) algorithm, leveraging a residual RL structure to enhance classical controllers in real-time by integrating multi-step Temporal-Difference (TD) learning, an asynchronous training pipeline, and Heuristic Delayed Reward Adjustment (HDRA) to improve sample efficiency and training stability. The framework is validated through extensive experiments on the F1TENTH racing platform, where the residual RL controller consistently outperforms the baseline controllers and achieves up to an 11.5 % reduction in lap times compared to the State-of-the-Art (SotA) with only 20 min of training. Additionally, an End-to-End (E2E) RL controller trained without a baseline controller surpasses the previous best results with sustained on-track learning. These findings position the framework as a robust solution for high-performance autonomous racing and a promising direction for other real-time, dynamic autonomous systems.

Cole Cappello, Andrew Hoegh

Tire degradation plays a critical role in Formula 1 race strategy, influencing both lap times and optimal pit-stop decisions. This paper introduces a Bayesian state-space modeling framework for estimating the latent degradation dynamics of Formula 1 tires using publicly available timing data from the FastF1 Python API. Lap times are modeled as a function of fuel mass and latent tire pace, with pit stops represented as state resets. Several model extensions are explored, including compound-specific degradation rates, time-varying degradation dynamics, and a skewed t observation model to account for asymmetric driver errors. Using Lewis Hamilton's performance in the 2025 Austrian Grand Prix as a case study, the proposed framework demonstrates superior predictive performance over an ARIMA(2,1,2) baseline, particularly under the skewed t specification. Although compound-specific degradation differences were not statistically distinct, the results show that the state-space approach provides interpretable, probabilistic, and computationally efficient estimates of tire degradation. This framework can be generalized to multi-race or multi-driver analyses, offering a foundation for real-time strategy modeling and performance prediction in Formula 1 racing.

Mulugeta Girma, Zelalem Mulatu

Corridor development refers to the strategic planning, building, and operation of transportation infrastructure that connects key metropolitan areas within a city. This study aims to assess the effects of corridor development initiatives in Addis Ababa. Data were collected through on-site observations and interviews with key informants from relevant offices, alongside secondary data. Thematic analysis was employed to interpret the data. The study’s findings indicate that corridor development initiatives have decreased traffic congestion, enhanced pedestrian and bicycle access, and improved mobility, making commuting more enjoyable and efficient. Furthermore, it promotes sustainability through improving green spaces, open public areas, and non-motorized transportation infrastructure. Overall, the study found that the corridor development project has significantly boosted the city’s image. Finally, the study recommends using Addis Ababa’s corridor development as a model for urban planning and financial investment in transportation infrastructure, which can enhance the city’s quality of life. Besides, to address the city’s mobility challenges and promote a smart city, the study advocates for implementing integrated transit systems, vehicle sharing, traffic calming measures, and parking fees as part of the city’s ongoing development efforts.

Muhammad Abdul Mubdi Bindar, Muhammad Zainal Ibad, Goldie Melinda Wijayanti et al.

This paper studies the commuting patterns of students and staff at the Sumatera Institute of Technology (ITERA), a rapidly growing university located in a peri-urban area of Lampung Province, Indonesia. The research is grounded in the understanding that peri-urban commuters face unique mobility challenges shaped by transitional land use, limited infrastructure, and high motorcycle dependency. Using both statistical and spatial analyses, the article analyzed distinct travel behaviors and their socioeconomic determinants. Findings reveal that motorcycles dominate as the primary commuting mode for both groups, driven by cultural norms and constrained public transport access. Staff exhibit higher rates of vehicle ownership and longer, more dispersed commutes, while students tend to reside closer to campus and rely on borrowed motorcycles. Temporal analysis shows structured weekday travel among staff and more flexible, weekend-active patterns among students. The findings offer targeted insights for developing sustainable transportation strategies in rapidly expanding peri-urban institutions—such as promoting bicycle and pedestrian infrastructure, designing transport policies that account for widespread motorcycle borrowing among students, and differentiating mobility interventions based on the spatial dispersion and financial profiles of staff versus students.

Benjamin David Evans, Hendrik Willem Jordaan, Herman Arnold Engelbrecht

Map-based methods for autonomous racing estimate the vehicle's location, which is used to follow a high-level plan. While map-based optimisation methods demonstrate high-performance results, they are limited by requiring a map of the environment. In contrast, mapless methods can operate in unmapped contexts since they directly process raw sensor data (often LiDAR) to calculate commands. However, a major limitation in mapless methods is poor performance due to a lack of optimisation. In response, we propose the local map framework that uses easily extractable, low-level features to build local maps of the visible region that form the input to optimisation-based controllers. Our local map generation extracts the visible racetrack boundaries and calculates a centreline and track widths used for planning. We evaluate our method for simulated F1Tenth autonomous racing using a two-stage trajectory optimisation and tracking strategy and a model predictive controller. Our method achieves lap times that are 8.8% faster than the Follow-The-Gap method and 3.22% faster than end-to-end neural networks due to the optimisation resulting in a faster speed profile. The local map planner is 3.28% slower than global methods that have access to an entire map of the track that can be used for planning. Critically, our approach enables high-speed autonomous racing on unmapped tracks, achieving performance similar to global methods without requiring a track map.

Zhuyun Zhou, Zongwei Wu, Florian Bolli et al.

Autonomous racing has rapidly gained research attention. Traditionally, racing cars rely on 2D LiDAR as their primary visual system. In this work, we explore the integration of an event camera with the existing system to provide enhanced temporal information. Our goal is to fuse the 2D LiDAR data with event data in an end-to-end learning framework for steering prediction, which is crucial for autonomous racing. To the best of our knowledge, this is the first study addressing this challenging research topic. We start by creating a multisensor dataset specifically for steering prediction. Using this dataset, we establish a benchmark by evaluating various SOTA fusion methods. Our observations reveal that existing methods often incur substantial computational costs. To address this, we apply low-rank techniques to propose a novel, efficient, and effective fusion design. We introduce a new fusion learning policy to guide the fusion process, enhancing robustness against misalignment. Our fusion architecture provides better steering prediction than LiDAR alone, significantly reducing the RMSE from 7.72 to 1.28. Compared to the second-best fusion method, our work represents only 11% of the learnable parameters while achieving better accuracy. The source code, dataset, and benchmark will be released to promote future research.

رضا عیوض لو, داوود رزاقی

ارزشگذاری داراییها اعم از اوراق بهادار و داراییهای واقعی یکی از ارکان موثر بر تصمیمات سرمایه گذاری است، ارزشگذاری منصفانه منجر به تخصیص بهینه منابع سرمایه ای می شود و تخصیص بهینه سرمایه در اقتصاد نقش بی بدیلی را در رشد و توسعه اقتصادی ایفا می کند. در حال حاضر فقدان چارچوب مدون و مشخصی که بتواند برآورد دقیقی از ارزش تبیین نماید اهمیت دو چندان یافته است. بنابراین ارائه چارچوبی که بتواند فارغ از قضاوتهای شخصی و سلایق مختلف به صورت علمی و مستدل جهت ارائه الگوی مناسب به منظور ارزشگذاری شرکتها مورد استفاده قرار گیرد، اهمیت یافته است. در این پژوهش ابتدا با استفاده از مصاحبه با خبرگان به انتخاب الگوی مناسب ارزشگذاری سهام در 14 گونه شرکت مختلف خواهیم پرداخت بدین صورت که ابتدا با استفاده از فرآیند تحلیل شبکه ای و براساس نظر خبرگان وزن معیارها محاسبه شده و درنهایت الگویی جامع برای ارزشگذاری اقسام گوناگون شرکتها پیشنهاد شده است. در انتها هم آسیب شناسی جامعی از محیط ارزشگذاری ارائه شده است.معیارهای به کارگرفته شده در این پژوهش در 4 دسته رویکرد سودآوری گذشته (شامل میانگینEBIT، سود به قیمت گذشته)، رویکرد مبتنی بر دارایی(شامل ارزش اسمی، ارزش دفتری، ارزش جایگزینی، ارزش خالص دارایی ها و ارزش تصفیه)، رویکرد تنزیل جریانهای نقدی(شامل fcff،fcfe،apv،eva و ddm) و رویکرد بازار(p/s،p/nav، p/e به جزگذشته، ev/ebit،p/c،ev/s،p/b،p/cf و p/dps) قرار گرفتند. این پژوهش از نظر هدف از نوع کاربردی است و از نظر ماهیت و روش جمع اوری داده ها، از نوع توصیفی و از شاخه مطالعه موردی می باشد.

Tiarna Lee, Esther Puyol-Anton, Bram Ruijsink et al.

In computer vision there has been significant research interest in assessing potential demographic bias in deep learning models. One of the main causes of such bias is imbalance in the training data. In medical imaging, where the potential impact of bias is arguably much greater, there has been less interest. In medical imaging pipelines, segmentation of structures of interest plays an important role in estimating clinical biomarkers that are subsequently used to inform patient management. Convolutional neural networks (CNNs) are starting to be used to automate this process. We present the first systematic study of the impact of training set imbalance on race and sex bias in CNN-based segmentation. We focus on segmentation of the structures of the heart from short axis cine cardiac magnetic resonance images, and train multiple CNN segmentation models with different levels of race/sex imbalance. We find no significant bias in the sex experiment but significant bias in two separate race experiments, highlighting the need to consider adequate representation of different demographic groups in health datasets.

Ari Decter-Frain

Bayesian Improved Surname Geocoding (BISG) is the most popular method for proxying race/ethnicity in voter registration files that do not contain it. This paper benchmarks BISG against a range of previously untested machine learning alternatives, using voter files with self-reported race/ethnicity from California, Florida, North Carolina, and Georgia. This analysis yields three key findings. First, machine learning consistently outperforms BISG at individual classification of race/ethnicity. Second, BISG and machine learning methods exhibit divergent biases for estimating regional racial composition. Third, the performance of all methods varies substantially across states. These results suggest that pre-trained machine learning models are preferable to BISG for individual classification. Furthermore, mixed results across states underscore the need for researchers to empirically validate their chosen race/ethnicity proxy in their populations of interest.

Rudolf Reiter, Jasper Hoffmann, Joschka Boedecker et al.

We present an approach for safe trajectory planning, where a strategic task related to autonomous racing is learned sample-efficient within a simulation environment. A high-level policy, represented as a neural network, outputs a reward specification that is used within the cost function of a parametric nonlinear model predictive controller (NMPC). By including constraints and vehicle kinematics in the NLP, we are able to guarantee safe and feasible trajectories related to the used model. Compared to classical reinforcement learning (RL), our approach restricts the exploration to safe trajectories, starts with a good prior performance and yields full trajectories that can be passed to a tracking lowest-level controller. We do not address the lowest-level controller in this work and assume perfect tracking of feasible trajectories. We show the superior performance of our algorithm on simulated racing tasks that include high-level decision making. The vehicle learns to efficiently overtake slower vehicles and to avoid getting overtaken by blocking faster vehicles.

Yanmei LI

South Florida has been among the top foreclosure markets in the United States, but little research has explored whether this market presents different dynamics compared to other metropolitan areas. This research chooses Broward County to explore whether socioeconomic characteristics and certain public policy instruments relate to subprime lending and mortgage foreclosure patterns. Results indicate areas bounded by linear highways and railroads have a concentration of low-income black population and subprime loans. The spatial distribution of subprime loans is mostly explained by a higher percentage of minority and/or Hispanic population in a neighborhood. Yet, racial minorities, instead of Hispanic origin, contributes mostly to the concentration of subprime loans. The spatial pattern of foreclosures is more complex, determined not only by subprime loans but also possibly other factors associated with the mortgage crisis. This suggests that disadvantaged neighborhoods are disproportionally lacking favorable opportunities due to institutional and sub- cultural forces shaping the geography of subprime and foreclosure.

Siti Rofiatul Sazjiyah, Racmad Kristiono Dwi Susilo, Luluk Dwi Kumalasari

Giripurno Village is one of the villages that has the largest corn agricultural commodity in Batu City. The abundance of corn harvests makes prices unstable. In addition, most farmers sell their corn harvest in the form of corn kernels, so it is not optimal in processing corn cobs, husks, and silk. Most of the people belong to the low economy. The community service program aims to provide ideas through assistance to the Family Welfare Empowerment Group (PKK) to process corn silk waste into drinks that have economic potential for the community. The assistance method used is in the form of training in making drinks, packaging, and selling. The evaluation was carried out to determine the improvement of skills in making corn silk juice drinks. This assistance program was attended by 15 participants. The results of the assistance showed that PKK women had understood how to process corn silk. This is evidenced by the fact that sales have reached 468 products sold in several cities, especially East Java. Hence, it is concluded that the assistance of this corn silk drink, can improve the welfare of the local community.

Patrícia Santos Pedrosa, Eliana Sousa Santos, Nuria Álvarez Lombardero et al.

Kele Stewart

The family regulation system's policing, disruption, and restructuring of Black families and communities spills over into other systems also marked by stark racial inequities - the education and juvenile justice systems. This Article unpacks how that spillage magnifies the harm to Black children; by exploring the structural mechanisms through which these systems work together to compound disparity and perpetuate inequity, this Article provides further evidence of the family regulation system's failings. 

Jesse Robson

The paper will also address fee simple land, the additions to reserve process, models for economic development, tax advantages, buckshee leases, certificates of possession, and other land management topics. First Nation food sovereignty is First Nation control over First Nation food (Sherman, 2020). Quapaw leadership admits to it having been a significant challenge but recognizes that it is essential to their food sovereignty. Since 2010 the Quapaw have been able to successfully develop their own food system by taking calculated steps. [...]many First Nations farmers left the industry, creating a gap in agricultural knowledge for generations - the second barrier.

Maha Almohamad, Dania Mofleh, Shreela Sharma

This research commentary reviews the current impact of the COVID-19 pandemic on food insecurity. We explore the impact of the pandemic on existing programs and evaluate how these programs adapted under these unprecedented circumstances. Moreover, we explore currently undertaken, favorable strategies for successfully addressing food insecurity during the pandemic. These initiatives include a nonprofit-retail industry partnership and programmatic strategies implemented by the U.S. Department of Agriculture (USDA). In an effort to bring awareness to addressing this important public health issue, we note the need to document these strategies and determine the most effective solutions to combat food insecurity in a vulnerable population.

Evans Shoko, Maheshvari Naidu

Background: Politics is a major determinant of community’s access to health. The right to access to health for communities and individuals has been recognised as vital by international bodies and national constitutions. Several studies have considered the negative effects of political violence on community access to health. Aim: This study aimed to explore the complexities of political conflict in community health praxis. Setting: This study was conducted in three clinics in Chegutu Urban District, Zimbabwe. The site was particularly chosen because political conflicts therein have rarely been studied in terms of their indirect and subtle effects on community health. Methods: This study used a qualitative research approach to gain a deeper understanding of political conflict and community health by interviewing 20 health professionals selected through stratified random sampling. The data obtained from these interviews were thematically presented. Results: From the participants’ responses, it became clear that politics determines the nature of community health programmes, and individual access is partisan and contested. Political conflict to some extent increased intra-group conflicts amongst health professionals, leading to non-collaboration in healthcare. Conflict-induced economic decline has led to structural shortages and environmental pollution. Conclusion: The study findings demonstrate how politicisation of access to health can have detrimental effects on the excluded members of the community.