POSTER OT-04: PHYSICS-INFORMED MULTI-STEP REAL-TIME CONFLICT-BASED VEHICLE SAFETY PREDICTION

PHYSICS-INFORMED MULTI-STEP REAL-TIME CONFLICT-BASED VEHICLE SAFETY PREDICTION


PI: Qianwen Li

Co-PI(s): OT-04

Institution(s): University of Georgia


Abstract

Real-time vehicle safety prediction is critical in roadway safety management as drivers or vehicles can be altered beforehand to take corresponding evasive actions and avoid possible collisions. This study proposes a physics-informed multi-step real-time conflict-based vehicle safety prediction model to enhance roadway safety. Physics insights (i.e., traffic shockwave properties) are combined with data-driven features extracted from deep-learning techniques to improve the prediction accuracy. A time series of future vehicle safety indicators are predicted such that vehicles/drivers have enough time to take precautions. The safety indicator at each time stamp is a continuous value that the sign reflects the presence of conflict risks, and the absolute value indicates the conflict risk level to advise different magnitudes of evasive actions. A customized loss function is developed for the proposed prediction model to give more attention to risky events, which are the focus of safety management. The prediction superiority of the proposed model is proven through numerical experiments by comparing it with two benchmarks constructed based on the literature. Further, sensitivity analysis on key model parameters is carried out to advise parameter selections in developing real-world conflict-based vehicle safety prediction applications.


Please comment below with any statements or questions you may have. Also let GTI if you would be interested webinars or presentations on similar topics.

POSTER OT-03: SOLVING LAB HURDLES: SOLUTIONS FOR UHI PAVEMENT EXPERIMENTS.

SOLVING LAB HURDLES: SOLUTIONS FOR UHI PAVEMENT EXPERIMENTS.


PI: Ali Keyvanfar

Co-PI(s): OT-03

Institution(s): Kennesaw State University


Abstract

This research initiative offers a holistic approach to mitigating the Urban Heat Island (UHI) effect, combining both technological innovation and comprehensive analysis. The first phase of the study focuses on the conceptual development of 12 specialized testing chambers designed to evaluate the effectiveness of various pavements of more than 11 coating materials in UHI mitigation. These chambers replicate a range of climatic and traffic conditions, from temperature gradients to rainfall and solar absorption, for assessing the performance of different coating solutions in developing cooling pavement material. The second phase of the research employs advanced machine learning algorithms, specifically ChatGPT-based data analytics models, to conduct an in-depth network analysis of 34 key contributing factors to the UHI effect within five years of projector study. A novel concept introduced in this phase is the term “death loops,” which are self-reinforcing feedback loops among contributing factors that exacerbate the UHI phenomenon. A stringent correlation threshold was applied to isolate the most impactful factors, providing targeted areas for intervention. The study also incorporates future scenario analysis, examining potential technological advancements in Artificial Intelligence (AI) and Electric Vehicles (EVs) and their implications for UHI mitigation. Preliminary findings suggest that effective interventions include targeting these “death loops,” improving surface albedo through reflective materials, and increasing canopy cover via green infrastructure. By synergizing the technological advancements in material science from the first phase with the data-driven insights from the second phase, this research serves as a comprehensive resource for stakeholders. It not only addresses the current challenges posed by UHIs but also offers a roadmap for adapting to future technological shifts. The multidisciplinary approach ensures that the solutions are both effective and adaptable, providing invaluable guidance for urban planners, policymakers, and environmentalists in formulating long-term UHI mitigation strategies.


Please comment below with any statements or questions you may have. Also let GTI if you would be interested webinars or presentations on similar topics.

POSTER OT-06: FOSTERING SMART AND SUSTAINABLE TRAVEL THROUGH ENGAGED COMMUNITIES USING INTEGRATED MULTIDIMENSIONAL INFORMATION-BASED SOLUTIONS

FOSTERING SMART AND SUSTAINABLE TRAVEL THROUGH ENGAGED COMMUNITIES USING INTEGRATED MULTIDIMENSIONAL INFORMATION-BASED SOLUTIONS


PI: Srinivas Peeta

Co-PI(s): OT-06

Institution(s): Georgia Institute of Technology


Abstract

This project will develop systematic deployment tools that smart and connected communities (SCCs) can use to achieve their sustainable travel goals in a quantifiable manner by leveraging advances in information, communication, and sensor technologies. While the deployment of advanced technological solutions offers great promise for communities to improve residents’ quality of life, they encounter challenges in realizing these aspirations due to the diversity in technological and travel needs and barriers faced by the residents. Solutions to achieve sustainability objectives related to enhancing travel mobility, safety, equity, access, active lifestyle, and health will be developed using an immersive living lab (City of Peachtree Corners, GA). They include building novel partnerships involving emerging micromobility services in the private sector and the well-established public transit modes, personalized behavioral interventions to nudge and incentivize personal auto users to consider sustainable alternatives, and community level public policy interventions to enable flexible and novel travel alternatives. For underserved residents, the solutions include strategies to overcome information deserts in lower-income neighborhoods, age-related technology savviness issues for senior residents, and reduced access to smartphones and transportation options. These solutions will be developed using data collected from residents and other sources, and will be deployed using an information design system that provides targeted information to the various community stakeholders using multiple delivery mechanisms. This project seeks to foster deployment paradigms associated with holistic, community-level decision-making to achieve sustainable travel goals while meeting the needs of different stakeholders. It draws on methods from multi-objective optimization, multi-agent simulation, machine learning, behavioral economics, and data and policy analytics, to generate relevant multidimensional solutions. Further, it will lead to novel paradigms and algorithms for the solution options themselves, and for the development of generalizable principles related to practical deployment frameworks in the inherently complex SCCs.


Please comment below with any statements or questions you may have. Also let GTI if you would be interested webinars or presentations on similar topics.

POSTER OT-05: ENHANCING URBAN FREIGHT EFFICIENCY THROUGH SIMULATION-GUIDED INITIATIVES

ENHANCING URBAN FREIGHT EFFICIENCY THROUGH SIMULATION-GUIDED INITIATIVES


PI: Sofia Perez-Guzman

Co-PI(s): OT-05

Institution(s): Georgia Institute of Technology


Abstract

Current freight demand patterns pose challenges to energy efficiency and counteract supply-side progress. Urbanization and logistic sprawl exacerbate the complexities of supplying urban cores, giving rise to issues like pollution, congestion, and noise. Understanding the impact of urban freight and land-use decisions on energy efficiency, congestion, and emissions is paramount. A Behavioral Microsimulation Software (BMS) was devised to investigate this. The BMS simulates freight vehicle tours in a study area, offering insights into freight activity and policy impacts. At the general level, the BMS provides aggregate metrics; at the detailed level, it outputs tour details. It leverages freight trip generation estimates, and the US Bureau of Economic Analysis Input-Output Accounts for trade analysis. This versatile BMS evaluates a spectrum of supply chain activities?transportation supply to land use interventions. The study scrutinized three policies: (1) logistical development, (2) off-hour deliveries (OHD), and (3) demand management on e-commerce, all applied to a metropolitan and a specific region in New York State. The logistical development analysis showed that new facility development leads to smaller increases in freight (business-to-business) Vehicles-Miles Traveled (VMT) when located closer to the city?s center than toward the area’s outskirts. Moving closer to the city?s center reduces VMT when relocating an existing facility. These results underscore supply-side initiatives’ role in efficiency. The OHD investigation highlighted how higher penetration of OHD leads to lower freight (business-to-business) VMT, emissions, and fuel consumption, enhancing efficiency and reducing costs due to more compact and efficient tours. These findings emphasize the potency of demand-side strategies in fostering efficient urban freight systems. The demand management on e-commerce case showed that various forms of consumer adoption of household delivery consolidation could lead to notable reductions in the total number of deliveries, tours, and stops, resulting in cost savings, reduced fuel consumption, and decreased environmental emissions from business-to-customers freight activity. The findings serve as a practical illustration of the potential benefits that demand management strategies can bring to e-commerce deliveries. Reduced VMT yields cost savings, lower energy consumption, and decreased emissions, yielding substantial societal benefits. For policymakers and practitioners, these insights are invaluable for shaping effective urban freight policies. Efficient urban freight systems harmonize with sustainability goals, cost savings, and reduced environmental impact, driving positive outcomes for communities and economies.


Please comment below with any statements or questions you may have. Also let GTI if you would be interested webinars or presentations on similar topics.

POSTER OT-02: RECRUITMENT METHOD IMPACTS ON MANAGED LANE CUSTOMER SATISFACTION SURVEY RESPONSE RATES AND RESPONSE DIFFERENCES ACROSS RECRUITMENT WAVES

RECRUITMENT METHOD IMPACTS ON MANAGED LANE CUSTOMER SATISFACTION SURVEY RESPONSE RATES AND RESPONSE DIFFERENCES ACROSS RECRUITMENT WAVES


PI: Randall Guensler

Co-PI(s): OT-02

Institution(s): Georgia Institute of Technology


Abstract

The Georgia State Road and Tollway Authority (SRTA) conducts regular customer satisfaction surveys of Express Lane facility users to assess customer experience and obtain customer input to help improve facility management. The 2021 SRTA Customer Satisfaction Survey was conducted in four waves, between August 2021 and November 2021 (1). A total of 6,012 SRTA customers took the survey, which represents a survey response rate of about 8.3%. The first three waves of survey invitations were distributed directly to SRTA customers via pre-formatted e-mail invitations, using the agency e-mail contact list. The traditional first two waves, an invitation and follow-up e-mail reminder, generated significant customer response (41% of the total responses). However, Wave 3 was a targeted invitation, designed to appeal to specific users that regularly travel on specific corridors. This invitation let each individual user know that SRTA was looking for information from customers who reside in their county that used their specific Express Lane. This third wave significantly increased customer response, providing almost 27% of total responses. The open invitation used in the fourth wave (in which customer identity cannot be tracked) yielded almost 32% of the total survey response; however, 99% of these responses came from open SRTA newsletter invitations (less than 1% came from social media). The demographics and use characteristics were somewhat different across these waves. In the anonymous response survey, the distribution of ages was slightly skewed towards greater proportions of older individuals. Customer satisfaction with Peach Pass customer service centers was generally lower in the anonymous wave, providing information that would not have been captured without this wave. Given that the customer satisfaction rates for some service elements differ across the direct survey invitation responses and the anonymous survey invitation responses, for other agencies looking to assess customer satisfaction, it is worth considering the use of direct survey invitations as well as an anonymous survey response option.


Please comment below with any statements or questions you may have. Also let GTI if you would be interested webinars or presentations on similar topics.

POSTER OT-01: FOSTERING SMART AND SUSTAINABLE TRAVEL THROUGH ENGAGED COMMUNITIES USING INTEGRATED MULTIDIMENSIONAL INFORMATION-BASED SOLUTIONS

FOSTERING SMART AND SUSTAINABLE TRAVEL THROUGH ENGAGED COMMUNITIES USING INTEGRATED MULTIDIMENSIONAL INFORMATION-BASED SOLUTIONS


PI: Srinivas Peeta

Co-PI(s): Omar Asensio

Institution(s): Georgia Institute of Technology


Abstract

This project will develop systematic deployment tools that smart and connected communities (SCCs) can use to achieve their sustainable travel goals in a quantifiable manner by leveraging advances in information, communication, and sensor technologies. While the deployment of advanced technological solutions offers great promise for communities to improve residents’ quality of life, they encounter challenges in realizing these aspirations due to the diversity in technological and travel needs and barriers faced by the residents. Solutions to achieve sustainability objectives related to enhancing travel mobility, safety, equity, access, active lifestyle, and health will be developed using an immersive living lab (City of Peachtree Corners, GA). They include building novel partnerships involving emerging micromobility services in the private sector and the well-established public transit modes, personalized behavioral interventions to nudge and incentivize personal auto users to consider sustainable alternatives, and community level public policy interventions to enable flexible and novel travel alternatives. For underserved residents, the solutions include strategies to overcome information deserts in lower-income neighborhoods, age-related technology savviness issues for senior residents, and reduced access to smartphones and transportation options. These solutions will be developed using data collected from residents and other sources, and will be deployed using an information design system that provides targeted information to the various community stakeholders using multiple delivery mechanisms. This project seeks to foster deployment paradigms associated with holistic, community-level decision-making to achieve sustainable travel goals while meeting the needs of different stakeholders. It draws on methods from multi-objective optimization, multi-agent simulation, machine learning, behavioral economics, and data and policy analytics, to generate relevant multidimensional solutions. Further, it will lead to novel paradigms and algorithms for the solution options themselves, and for the development of generalizable principles related to practical deployment frameworks in the inherently complex SCCs.


Please comment below with any statements or questions you may have. Also let GTI if you would be interested webinars or presentations on similar topics.