Search

One part of complying with norms, rules, and preferences is incorporating constraints (such as knowledge of ethics) into one's goal formulation and planning processing. We explore in a simple domain how the encoding of knowledge in different ethical frameworks influences an agent's goal formulation and planning processing and demonstrate ability of an agent to satisfy and satisfice when its collection of relevant constraints includes a mix of "hard" and "soft" constraints of various types. How the agent attempts to comply with ethical constraints depends on the ethical framing and we investigate tradeoffs between deontological framing and utilitarian framing for complying with an ethical norm. Representative scenarios highlight how performing the same task with different framings of the same norm leads to different behaviors. Our explorations suggest an important role for metacognitive judgments in resolving ethical conflicts during goal formulation and planning., Comment: 16 pages + refs. 5 figures, 2 tables. Minor revisions based on reviewer feedback. Accepted for presentation at Advances in Cognitive Systems (Jun 2024, Palermo)

While measures, such as traffic calming and advance driver assistance systems, can improve safety for Vulnerable Road Users (VRUs), their effectiveness ultimately relies on the responsible behavior of drivers and pedestrians who must adhere to traffic rules or take appropriate actions. However, these measures offer no solution in scenarios where a collision becomes imminent, leaving no time for warning or corrective actions. Recently, connected vehicle technology has introduced warning services that can alert drivers and VRUs about potential collisions. Nevertheless, there is still a significant gap in the system's ability to predict collisions in advance. The objective of this study is to utilize Digital Twin (DT) technology to enable a proactive safety alert system for VRUs. A pedestrian-vehicle trajectory prediction model has been developed using the Encoder-Decoder Long Short-Term Memory (LSTM) architecture to predict future trajectories of pedestrians and vehicles. Subsequently, parallel evaluation of all potential future safety-critical scenarios is carried out. Three Encoder-Decoder LSTM models, namely pedestrian-LSTM, vehicle-through-LSTM, and vehicle-left-turn-LSTM, are trained and validated using field-collected data, achieving corresponding root mean square errors (RMSE) of 0.049, 1.175, and 0.355 meters, respectively. A real-world case study has been conducted where a pedestrian crosses a road, and vehicles have the option to proceed through or left-turn, to evaluate the efficacy of DT-enabled proactive safety alert systems. Experimental results confirm that DT-enabled safety alert systems were succesfully able to detect potential crashes and proactively generate safety alerts to reduce potential crash risk., Comment: 19 pages, 9 figures, submitted to the Transportation Research Board 2024 TRB Annual Meeting

COVID-19 introduced tremendous disruptions to the normal operation of transit agencies, led to a massive suspension of regular service, and disturbed the access to essential mobility for many transit-dependent populations. In this study, we reexamine the national-level service disruption of the public transportation system as a result of the COVID-19 pandemic and investigate the disparities in the reduction of transit supply, causing certain racial-ethnic groups to be disproportionately affected. To support our analysis, we collect GTFS data from 232 transit agencies covering over 89 million people across 45 states in the U.S. Our findings suggest more disadvantaged communities and certain racial-ethnic groups have experienced disproportional reductions in transit supply, regardless of their pre-pandemic level of service. Further, we employ causal mediation analyses to address the mediation effect of the pre-pandemic level of transit service on the relationship between race/ethnicity and transit supply reduction. This analysis validates the disproportionate reduction in service quality for specific racial/ethnic groups, a trend evident across the majority of transit agencies. In particular, Black Americans are found to be associated with the greatest absolute service loss and also the largest total effects on transit supply reductions, while the White and Asian groups are less impacted. We further report that the most impacted communities by transit loss mainly consist of minority populations, where the reductions in transit are correlated with pandemic-related health and economic burdens and result in greater changes in mobility intensity. Our study contributes to a comprehensive understanding of transit inequities due to the pandemic and provides valuable insights to better prepare public transportation systems against future nationwide disasters.

In this study, a digital twin (DT) technology based Adaptive Traffic Signal Control (ATSC) framework is presented for improving signalized intersection performance and user satisfaction. Specifically, real-time vehicle trajectory data, future traffic demand prediction and parallel simulation strategy are considered to develop two DT-based ATSC algorithms, namely DT1 (Digital Twin 1) and DT2 (Digital Twin 2). DT1 uses the delay experienced by each vehicle from all approaches connected to the subject intersection, while DT2 uses the delay of each vehicle that occurred in all the approaches connected to the subject intersection as well as immediate adjacent intersection. To demonstrate the effectiveness of these algorithms, the DT-based ATSC algorithms are evaluated with varying traffic demands at intersection, and individual user level. Evaluation results show that both DT1 and DT2 performs significantly better compared to the density-based baseline algorithm in terms of control delay reductions ranging from 1% to 52% for low traffic demands. DT1 outperforms baseline algorithm for moderate traffic demands, achieving reduction in control delay ranging from 3% to 19%, while the performance of DT2 declines with increasing demand. For high traffic demands, DT1 achieved control delay reduction ranging from 1% to 45% and DT2 achieved 8% to 36% compared to the baseline algorithm. Moreover, DT1 and DT2 effectively distribute the delay per vehicle among all the vehicles, which approach towards intersection, compared to the baseline ATSC algorithm. This helps to improve user satisfaction by reducing prolonged delays at a traffic signal, specifically, for moderate and high traffic demands.

Human behavior is conditioned by codes and norms that constrain action. Rules, ``manners,'' laws, and moral imperatives are examples of classes of constraints that govern human behavior. These systems of constraints are "messy:" individual constraints are often poorly defined, what constraints are relevant in a particular situation may be unknown or ambiguous, constraints interact and conflict with one another, and determining how to act within the bounds of the relevant constraints may be a significant challenge, especially when rapid decisions are needed. Despite such messiness, humans incorporate constraints in their decisions robustly and rapidly. General, artificially-intelligent agents must also be able to navigate the messiness of systems of real-world constraints in order to behave predictability and reliably. In this paper, we characterize sources of complexity in constraint processing for general agents and describe a computational-level analysis for such constraint compliance. We identify key algorithmic requirements based on the computational-level analysis and outline an initial, exploratory implementation of a general approach to constraint compliance., Comment: 10 pages, 2 figures. Accepted for presentation at AGI 2023. Corrected author list (segmented list) and abstract text artifacts

Human trafficking is a universal problem, persistent despite numerous efforts to combat it globally. Individuals of any age, race, ethnicity, sex, gender identity, sexual orientation, nationality, immigration status, cultural background, religion, socioeconomic class, and education can be a victim of human trafficking. With the advancements in technology and the introduction of autonomous vehicles (AVs), human traffickers will adopt new ways to transport victims, which could accelerate the growth of organized human trafficking networks, which can make the detection of trafficking in persons more challenging for law enforcement agencies. The objective of this study is to develop an innovative audio analytics-based human trafficking detection framework for autonomous vehicles. The primary contributions of this study are to: (i) define four non-trivial, feasible, and realistic human trafficking scenarios for AVs; (ii) create a new and comprehensive audio dataset related to human trafficking with five classes i.e., crying, screaming, car door banging, car noise, and conversation; and (iii) develop a deep 1-D Convolution Neural Network (CNN) architecture for audio data classification related to human trafficking. We have also conducted a case study using the new audio dataset and evaluated the audio classification performance of the deep 1-D CNN. Our analyses reveal that the deep 1-D CNN can distinguish sound coming from a human trafficking victim from a non-human trafficking sound with an accuracy of 95%, which proves the efficacy of our framework.

The lack of transportation options and limited public transit service in rural areas of the United States may negatively affect residents quality of life by limiting employment, community engagement, education, and quality healthcare opportunities. This study used a mixed method approach combining quantitative and qualitative research methods to conduct the transportation needs assessment in Pickens County, Alabama. The study examined access to healthcare, jobs, and other relevant resources across all population categories in the area, including vulnerable populations, such as senior citizens, people with disabilities, and low-income households. Additionally, this study investigated public perceptions of and opinions about H.E.L.P. Inc., an origin-to-destination demand-response bus service for Pickens County residents. The study findings may be helpful to stakeholders, policymakers, and transportation services providers in the rural communities of the U.S., working to develop new approaches that would help meet the transportation needs of local communities., Comment: 20 pages

In January 2023, UCAS announced their intention to reform the personal statement to a series of short questions. This built upon UCAS's work with students and providers in 2022/23, as well as academic literature that has documented the challenges and inequalities that surround the personal statement, including the Higher Education Policy Institute (HEPI) Debate Paper, "Reforming the UCAS Personal Statement: Making the Case for a Series of Short Questions. HEPI Debate Paper 31" (ED630777), UCAS made an initial proposal to create short questions covering six themes (motivation; preparedness for course; preparedness through other experiences; extenuating circumstances; preparedness for study; and learning styles) and launched a consultation. This HEPI Policy Note aims to inform the consultation, presenting results from a survey of admissions professionals on their use of the UCAS personal statement in undergraduate admissions. The survey was launched in January 2023 and ran until April 2023. It primarily targeted people whose day-to-day work involves processing and assessing applications, hereafter called 'Admissions Officers'. This focus was chosen because the authors wanted to know how UCAS personal statements are used by practitioners, rather than gaining an institutional perspective from 'Admissions Managers', whose day-to-day job primarily involves managing those that process and assess applications. Although both Admissions Officers and Managers completed the survey, the former answered a broader range of questions.

University students' day-to-day lives largely depend on transportation. Public transit alternatives are not widely available in the United States' small-town, rural, and suburban collegiate environments (U.S.). This study disseminated an online survey among international students studying at The University of Alabama (UA) campus, a predominantly white institution in Tuscaloosa, Alabama. The objective of this research was to investigate and analyze international student travel experiences in a city with a significant college-affiliated population and highlight particular transportation issues in the area. The survey results show that international students find it difficult to travel within Tuscaloosa without a personal vehicle, as other modes of transportation, including walking, biking, and using public transportation, are not always convenient or reliable. The study findings may be of interest to transportation experts, city planners, university administrators, and college students who want to better understand travel-related challenges experienced by international students., Comment: 48 pages, 2 figures