Autonomous drone racing has attracted increasing interest as a research topic for exploring the limits of agile flight. However, existing studies primarily focus on obstacle-free racetracks, while the perception and dynamic challenges introduced by obstacles remain underexplored, often resulting in low success rates and limited robustness in real-world flight. To this end, we propose a novel vision-based curriculum reinforcement learning framework for training a robust controller capable of addressing unseen obstacles in drone racing. We combine multi-stage cu rriculum learning, domain randomization, and a multi-scene updating strategy to address the conflicting challenges of obstacle avoidance and gate traversal. Our end-to-end control policy is implemented as a single network, allowing high-speed flight of quadrotors in environments with variable obstacles. Both hardware-in-the-loop and real-world experiments demonstrate that our method achieves faster lap times and higher success rates than existing approaches, effectively advancing drone racing in obstacle-rich environments. The video and code are available at: https://github.com/SJTU-ViSYS-team/CRL-Drone-Racing.
Research shows that youth participating in engaged agricultural learning gain important practical skills and knowledge. The physicality, setting, and social aspects of agricultural and horticultural projects are opportune for improving mental, emotional, and social well-being—yet the psychosocial and metacognitive impacts of agricultural learning are still unclear. This study examines psychosocial impacts among youth participants, ages 13–17, in the Felege Hiywot Center’s 2023 STEAM (science, technology, engineering, agriculture, and math) Farm Camp. The Farm Camp combines hands-on urban agriculture with employable skills training while addressing food insecurity in an urban neighborhood with limited access to affordable and nutritious foods. During the camp, students design and maintain garden plots where they grow food, prepare shared meals, and participate in integrative science projects. Using a mix of quantitative and qualitative data collected from surveys and facilitated journaling, we explored the positive psychosocial and metacognitive impacts of camp participation. We found gardening instilled positive feelings and was perceived as a source of stress relief and accomplishment among participants. Teens also gained social support through the development of friendships and mentorships. Furthermore, their participation in the program was associated with metacognitive skills development, including self-awareness and reflection. This case study provides a compelling example of how to engage youth from an underserved area in sustainable urban agriculture while fostering metacognitive skills development and positive psychosocial experiences. We conclude that urban youth agricultural learning programs have valuable impacts on participants that go beyond agricultural education and the achievement of practical skills. These findings—which highlight the potential to contribute to psychosocial well-being, social support, and metacognitive abilities associated with maturation and personal development—may be particularly useful for other programs addressing at-risk and vulnerable youth.
This paper introduces SPIRAL (Self-Play Incremental Racing Algorithm for Learning), a novel approach for training autonomous drones in multi-agent racing competitions. SPIRAL distinctively employs a self-play mechanism to incrementally cultivate complex racing behaviors within a challenging, dynamic environment. Through this self-play core, drones continuously compete against increasingly proficient versions of themselves, naturally escalating the difficulty of competitive interactions. This progressive learning journey guides agents from mastering fundamental flight control to executing sophisticated cooperative multi-drone racing strategies. Our method is designed for versatility, allowing integration with any state-of-the-art Deep Reinforcement Learning (DRL) algorithms within its self-play framework. Simulations demonstrate the significant advantages of SPIRAL and benchmark the performance of various DRL algorithms operating within it. Consequently, we contribute a versatile, scalable, and self-improving learning framework to the field of autonomous drone racing. SPIRAL's capacity to autonomously generate appropriate and escalating challenges through its self-play dynamic offers a promising direction for developing robust and adaptive racing strategies in multi-agent environments. This research opens new avenues for enhancing the performance and reliability of autonomous racing drones in increasingly complex and competitive scenarios.
Emily Steiner, Daniel van der Spuy, Futian Zhou
et al.
While autonomous racing performance in Time-Trial scenarios has seen significant progress and development, autonomous wheel-to-wheel racing and overtaking are still severely limited. These limitations are particularly apparent in real-life driving scenarios where state-of-the-art algorithms struggle to safely or reliably complete overtaking manoeuvres. This is important, as reliable navigation around other vehicles is vital for safe autonomous wheel-to-wheel racing. The F1Tenth Competition provides a useful opportunity for developing wheel-to-wheel racing algorithms on a standardised physical platform. The competition format makes it possible to evaluate overtaking and wheel-to-wheel racing algorithms against the state-of-the-art. This research presents a novel racing and overtaking agent capable of learning to reliably navigate a track and overtake opponents in both simulation and reality. The agent was deployed on an F1Tenth vehicle and competed against opponents running varying competitive algorithms in the real world. The results demonstrate that the agent's training against opponents enables deliberate overtaking behaviours with an overtaking rate of 87% compared 56% for an agent trained just to race.
With the emergence of a green environment and green business, the banking sector has also enforced green practices. This study aims to explore the impact of motivational factors and green behaviors on the environmental performance of banking sector employees. This is a quantitative study and data has been collected through a cross-sectional survey of the questionnaire in the banking sector. 300 questionnaires were distributed to the bank employees. PLS-SEM was used to find the statistical results. The study finds a positive impact of Extrinsic motivation and Intrinsic motivation on Employee Environmental Performance, the mediating effect of Task-related Green Behaviors was also found to be positive. The study does not support the effect of Voluntary Green Behaviors on Employee Environment Performance and its mediating effect was also not supported. The study findings and deep knowledge of the impact of motivational and behavioral employee environmental performance on banking sector employees have provided new directions for researchers and policymakers. This study will help the policymakers in strategically developing rewarding policies for the employees that would definitely create a positive impact on performance. The results of the study have provided empirical confirmation of employees’ motivational needs and their impact on green behaviors that collectively impact employee environmental performance.
Cities. Urban geography, Urbanization. City and country
Jorn van Kampen, Mauro Moriggi, Francesco Braghin
et al.
This paper presents model predictive control strategies for battery electric endurance race cars accounting for interactions with the competitors. In particular, we devise an optimization framework capturing the impact of the actions of the ego vehicle when interacting with competitors in a probabilistic fashion, jointly accounting for the optimal pit stop decision making, the charge times and the driving style in the course of the race. We showcase our method for a simulated 1h endurance race at the Zandvoort circuit, using real-life data of internal combustion engine race cars from a previous event. Our results show that optimizing both the race strategy as well as the decision making during the race is very important, resulting in a significant 21s advantage over an always overtake approach, whilst revealing the competitiveness of e-race cars w.r.t. conventional ones.
This paper examines the strategic dynamics of international competition to develop Artificial Superintelligence (ASI). We argue that the same assumptions that might motivate the US to race to develop ASI also imply that such a race is extremely dangerous. These assumptions--that ASI would provide a decisive military advantage and that states are rational actors prioritizing survival--imply that a race would heighten three critical risks: great power conflict, loss of control of ASI systems, and the undermining of liberal democracy. Our analysis shows that ASI presents a trust dilemma rather than a prisoners dilemma, suggesting that international cooperation to control ASI development is both preferable and strategically sound. We conclude that cooperation is achievable.
Are institutional trust and interpersonal trust threatened by globalisation? For nineteen countries in Europe, using a fixed effects model for a panel data set relating globalisation to several economic and social macro variables, like income inequality and diversity, to average institutional and interpersonal trust derived from responses in European Social Surveys, we do not find any significant relation between the relatively moderate globalisation of the first two decades of the 21st century on average interpersonal and institutional trust. At the same time, occurrences of economic decline in a country are negatively related to institutional trust. GDP has a positive effect on both institutional and interpersonal.Combining the macro factors with the individual traits of respondents using pooled repeated cross-sectional data demonstrate the dominance of personal characteristics in individual levels of trust, with only institutional quality emerging as a macro variable which is significantly and positively related to trust, especially for the Socio-Economic Groups 3 to 7 (of the eight groups distinguished). Those who are born in the country exhibit higher levels of interpersonal trust, in particular in the higher SES groups 4–7, but show significantly lower institutional trust for the SES groups 0–2. Age is negatively related to institutional trust for all SES groups, but positively related to interpersonal trust for SES groups 4–7.These findings appear to imply that those who are concerned with the level of institutional trust in the population as a basic requirement for democracy in Europe should focus on the quality of institutions and not on globalisation.
Cities. Urban geography, Urbanization. City and country
The Covid-19 pandemic and energy, climate, and demographic crises have shown how cities are vulnerable to these impacts and how the access to green and blue spaces has become highly relevant to people. One strategy that we can observe is the strong focus on the resilience discourse, meaning implementing more green and blue spaces in urban areas, such as at previous brownfield quarters. However, social justice implications of urban greening have been overlooked for a long time. The implementation of strategies to improve the quality and availability of the green and blue infrastructures may indeed have negative outcomes as far as housing accessibility is concerned by trigging gentrification processes. Issues related to environmental justice and socio-spatial justice are increasing in contemporary cities and call for a better understanding of the global and local mechanisms of production and reproduction of environmental and spatial inequalities. This thematic issue includes eleven articles with different methodologies, with examples from Europe and North America as well as different lenses of green gentrification. Some articles focus more on the question of costs, benefits, and distributional consequences of various infrastructural options for urban greening. Others, instead, discuss how the strategic urban planning tools and policy processes take into account distributional consequences, with specific attention on participatory processes.
We propose a novel B-spline trajectory optimization method for autonomous racing. We consider the unavailability of sophisticated race car and race track dynamics in early-stage autonomous motorsports development and derive methods that work with limited dynamics data and additional conservative constraints. We formulate a minimum-curvature optimization problem with only the spline control points as optimization variables. We then compare the current state-of-the-art method with our optimization result, which achieves a similar level of optimality with a 90% reduction on the decision variable dimension, and in addition offers mathematical smoothness guarantee and flexible manipulation options. We concurrently reduce the problem computation time from seconds to milliseconds for a long race track, enabling future online adaptation of the previously offline technique.
Reinforcement Learning (RL) has emerged as a transformative approach in the domains of automation and robotics, offering powerful solutions to complex problems that conventional methods struggle to address. In scenarios where the problem definitions are elusive and challenging to quantify, learning-based solutions such as RL become particularly valuable. One instance of such complexity can be found in the realm of car racing, a dynamic and unpredictable environment that demands sophisticated decision-making algorithms. This study focuses on developing and training an RL agent to navigate a racing environment solely using feedforward raw lidar and velocity data in a simulated context. The agent's performance, trained in the simulation environment, is then experimentally evaluated in a real-world racing scenario. This exploration underlines the feasibility and potential benefits of RL algorithm enhancing autonomous racing performance, especially in the environments where prior map information is not available.
The estimation of racial disparities in various fields is often hampered by the lack of individual-level racial information. In many cases, the law prohibits the collection of such information to prevent direct racial discrimination. As a result, analysts have frequently adopted Bayesian Improved Surname Geocoding (BISG) and its variants, which combine individual names and addresses with Census data to predict race. Unfortunately, the residuals of BISG are often correlated with the outcomes of interest, generally attenuating estimates of racial disparities. To correct this bias, we propose an alternative identification strategy under the assumption that surname is conditionally independent of the outcome given (unobserved) race, residence location, and other observed characteristics. We introduce a new class of models, Bayesian Instrumental Regression for Disparity Estimation (BIRDiE), that take BISG probabilities as inputs and produce racial disparity estimates by using surnames as an instrumental variable for race. Our estimation method is scalable, making it possible to analyze large-scale administrative data. We also show how to address potential violations of the key identification assumptions. A validation study based on the North Carolina voter file shows that BISG+BIRDiE reduces error by up to 84% when estimating racial differences in party registration. Finally, we apply the proposed methodology to estimate racial differences in who benefits from the home mortgage interest deduction using individual-level tax data from the U.S. Internal Revenue Service. Open-source software is available which implements the proposed methodology.
I Putu Dika Mustika, I Gede Adi Setia Darma, I Kadek Merta Wijaya
Bali Festival Park is a tourist place that is very loved by the Balinese people and also tourists, both foreign tourists, and local tourists. This place presents a variety of rides and facilities that are quite complete for visitors to spend their free time. However, at this time the Bali Festival Park has begun to be abandoned by the public and tourists, this has made some buildings that can still be used physically abandoned. The building is an icon of the main building has a unique roof shape and also has an adequate area, besides that this building also still has a solid structure. The building that faces directly towards the sea also has its own added value, which is to offer a unique view of the beach. Currently, the world of work is very important in regional economic growth so it is very important to provide good and comfortable facilities for workers to increase their productivity so that the function of the Taman Festival Bali performance theater building becomes a Co-Working space using an adaptive approach. reuse will be a good choice because, in addition to being able to work together with various companies, employees can also indulge themselves with the scenery and existing facilities. This research itself aims to create a comfortable place for companies as a place to be able to provide peace for their employees and can share work experiences with other companies. The method used is descriptive qualitative through studies and descriptions of architectural problems and formulating solutions in the form of schematic designs. The results of this study are the elements of space that are presented in the form of floor plans, 3D Interior, and exterior.
Details in building design and construction. Including walls, roofs, Urban renewal. Urban redevelopment
Commit messages are important for software development and maintenance. Many neural network-based approaches have been proposed and shown promising results on automatic commit message generation. However, the generated commit messages could be repetitive or redundant. In this paper, we propose RACE, a new retrieval-augmented neural commit message generation method, which treats the retrieved similar commit as an exemplar and leverages it to generate an accurate commit message. As the retrieved commit message may not always accurately describe the content/intent of the current code diff, we also propose an exemplar guider, which learns the semantic similarity between the retrieved and current code diff and then guides the generation of commit message based on the similarity. We conduct extensive experiments on a large public dataset with five programming languages. Experimental results show that RACE can outperform all baselines. Furthermore, RACE can boost the performance of existing Seq2Seq models in commit message generation.
Naba Rizvi, Reggie Casanova-Perez, Harshini Ramaswamy
et al.
As Human-Computer Interaction (HCI) research aims to be inclusive and representative of many marginalized identities, there is still a lack of available literature and research on intersectional considerations of race, gender, and sexual orientation, especially when it comes to participatory design. We aim to create a space to generate community recommendations for effectively and appropriately engaging Queer, Transgender, Black, Indigenous, People of Color (QTBIPOC) populations in participatory design, and discuss methods of dissemination for recommendations. Workshop participants will engage with critical race theory, queer theory, and feminist theory to reflect on current exclusionary HCI and participatory design methods and practices.
Thomas Herrmann, Francesco Passigato, Johannes Betz
et al.
Increasing attention to autonomous passenger vehicles has also attracted interest in an autonomous racing series. Because of this, platforms such as Roborace and the Indy Autonomous Challenge are currently evolving. Electric racecars face the challenge of a limited amount of stored energy within their batteries. Furthermore, the thermodynamical influence of an all-electric powertrain on the race performance is crucial. Severe damage can occur to the powertrain components when thermally overstressed. In this work we present a race-time minimal control strategy deduced from an Optimal Control Problem (OCP) that is transcribed into a Nonlinear Problem (NLP). Its optimization variables stem from the driving dynamics as well as from a thermodynamical description of the electric powertrain. We deduce the necessary first-order Ordinary Differential Equations (ODE)s and form simplified loss models for the implementation within the numerical optimization. The significant influence of the powertrain behavior on the race strategy is shown.
Sherif Nekkah, Josua Janus, Mario Boxheimer
et al.
Formula Student Driverless challenges engineering students to develop autonomous single-seater race cars in a quest to bring about more graduates who are well-prepared to solve the real world problems associated with autonomous driving. In this paper, we present the software stack of KA-RaceIng's entry to the 2019 competitions. We cover the essential modules of the system, including perception, localization, mapping, motion planning, and control. Furthermore, development methods are outlined and an overview of the system architecture is given. We conclude by presenting selected runtime measurements, data logs, and competition results to provide an insight into the performance of the final prototype.
Automated gender classification has important applications in many domains, such as demographic research, law enforcement, online advertising, as well as human-computer interaction. Recent research has questioned the fairness of this technology across gender and race. Specifically, the majority of the studies raised the concern of higher error rates of the face-based gender classification system for darker-skinned people like African-American and for women. However, to date, the majority of existing studies were limited to African-American and Caucasian only. The aim of this paper is to investigate the differential performance of the gender classification algorithms across gender-race groups. To this aim, we investigate the impact of (a) architectural differences in the deep learning algorithms and (b) training set imbalance, as a potential source of bias causing differential performance across gender and race. Experimental investigations are conducted on two latest large-scale publicly available facial attribute datasets, namely, UTKFace and FairFace. The experimental results suggested that the algorithms with architectural differences varied in performance with consistency towards specific gender-race groups. For instance, for all the algorithms used, Black females (Black race in general) always obtained the least accuracy rates. Middle Eastern males and Latino females obtained higher accuracy rates most of the time. Training set imbalance further widens the gap in the unequal accuracy rates across all gender-race groups. Further investigations using facial landmarks suggested that facial morphological differences due to the bone structure influenced by genetic and environmental factors could be the cause of the least performance of Black females and Black race, in general.