UMTRI Research Review, August 2022

Page 1

UMTRI’s 2022 annual student seminar series concluded in August with its annual poster competition. The seminars, which took place every Tuesday between May to August via zoom, exposed students to the depth and breadth of UMTRI’s research enterprise and provided them with valuable insights and opportunities in transportation and mobility safety, equity and efficiency. Final project posters are research-showcase/https://www.umtri.umich.edu/student-found here:

FEATURE Continued on page 2

ASeminarUMTRIumtri.umich.edu2022StudentSeries

From the Director

UNIVERSITY OF MICHIGAN TRANSPORTATION RESEARCH INSTITUTE AUGUST 2022 researchreview

This summer marked three years since UMTRI transitioned its administrative home from the U-M Office of Research (UMOR) to Michigan Engineering. t that time, Dean Galimore stated: “As we look to the future of mobility, we must think holistically about this complex problem. I am confident this change will help us do so to the great benefit of our faculty members, our students at both the undergraduate and graduate levels, and eventually society at Thislarge.”transition has provided UMTRI researchers greater access to a wide range of engineering resources including facilities, faculty and students. It also provided a more sustainable funding environment for UMTRI that has enabled us to grow our research enterprise and to attract and retain faculty and staff. UMTRI also has contributed significantly to the strategic goals of Michigan Engineering. Not only have we lent our strengths and expertise in engineering, but UMTRI also has introduced complimentary science to include the fields of biosciences, engineering systems, human factors, data sciences, and social and behavioral science. In 2021-2022 we hired six faculty, many of whom are already collaborating on research projects with colleagues throughout Michigan Engineering.

Vehicles with ADAS have been involved in 392 crashes in the last year, according to the federal highway safety agency. Six of those were fatal, five resulted in serious injuries, with 41 resulting in minor or moderate injuries. Four involved a “vulnerable roaduser,” such as a cyclist or pedestrian.

To address this challenge, we create and demonstrate the strengths of a publicly available, free tool that municipalities and other interested parties may use to understand cruising for parking and also the effects of policy interventions on parking search behaviors. Our approach uses large datasets that are made up of GPS locations (or breadcrumbs) harvested from smartphones and/or navigation devices. By studying the circuity of paths taken on a road network, we can visualize and quantify the extent of cruising for parking. Read more at: edu/parking-a-serious-and-vexing-problemhttps://www.umtri.umich.

James UMTRISayerDirector

NHTSA Releases New Data About Autonomous Vehicle Crashes

2 RESEARCH REVIEW | AUGUST 2022

Full report: reportingregulations/standing-general-order-crash-https://www.nhtsa.gov/laws-

At a recent meeting with the deans and directors, Steve Ceccio, associate dean for academic affairs shared that UMTRI’s contributions are easily measured, “UMTRI’s strong connection to industry is an asset for our collate, providing experiential opportunities for students that lead to jobs in the real world.” Throughout the year, UMTRI provides a diverse range of engagement and learning opportunities to nearly 300 students, visiting scholars and practitioners. And each summer over 50 students participate in an intensive research experience culminating in a poster competition facilitated by UMTRI Associate Director and Research Professor, Jingwen Hu. Students not only gain valuable experience but they often engage with sponsors in industry and government. In this edition of the UMTRI Research Review, we feature publications and projects, many that involve students, as well as our colleagues through Michigan Engineering and we look forward to deepening our relationships and collaborations.

From the Director Continued from page 1

UMTRI shared the following response to newly released data from the National Highway Traffic Safety Administration (NHTSA) “Thousands of people lose their lives every year due to traffic fatalities, and millions more suffer life-changing injuries. CAV’s have the potential to positively impact lives around the world - and not just in terms of safer roads. CAVs also can help reduce emissions, traffic congestion, and improve transportation equity and accessibility. Strong partnerships are needed in government, industry, and academia, as well as robust policies and regulations which are based on research.” – Jim Sayer, Director UMTRI Newly released data from the National Highway Traffic Safety Administration (NHTSA) details when crashes occurred in vehicles equipped with Advanced Driver Assistance Systems (ADAS), the driver assistance features found on many cars, and Automated Driving Systems (ADS), which refer to autonomous technologies being tested — and in some cases deployed — on public streets and roadways.

Cruising for Parking: A serious and vexing problem

Cruising for parking is a serious and vexing problem for cities around the world. Weinberger, R.; Millard-Ball, A.; Hampshire, R.C.; Greenberg, A.; Fabusuyi, T. and Calvin, E.

Full paper: https://arxiv.org/abs/2110.07111

Kusari, Arpan; Li, Pei; Yang, Hanzhi, Punshi, Nikhil; Rasulis, Mich, Bogard, Scott, LeBlanc, David. Current autonomous vehicle (AV) simulators are built to provide large-scale testing required to prove capabilities under varied conditions in controlled, repeatable fashion. However, they have certain failings including the need for user expertise and complex inconvenient tutorials for customized scenario creation. Simulation of Urban Mobility (SUMO) simulator, which has been presented as an open-source AV simulator, is used extensively but suffers from similar issues which make it difficult for entry-level practitioners to utilize the simulator without significant time investment. In that regard, we provide two enhancements to SUMO simulator geared towards massively improving user experience and providing real-life like variability for surrounding traffic. Firstly, we calibrate a car-following model, Intelligent Driver Model (IDM), for highway and urban naturalistic driving data and sample automatically from the parameter distributions to create the background vehicles. Secondly, we combine SUMO with OpenAI gym, creating a Python package which can run simulations based on real world highway and urban layouts with generic output observations and input actions that can be processed via any AV pipeline. Our aim through these enhancements is to provide an easy-to-use platform which can be readily used for AV testing and validation.

3 RESEARCH REVIEW | AUGUST 2022

Enhancing SUMO Simulator for Simulation based Testing and Validation of Autonomous Vehicles

Full paper: https://arxiv.org/abs/2109.11620

A Novel Traffic Simulation Framework for Testing Autonomous Vehicles Using SUMO and CARLA Li, Pei; Kusari, Arpan; LeBlanc, David Traffic simulation is an efficient and cost-effective way to test Autonomous Vehicles (AVs) in a complex and dynamic environment. Numerous studies have been conducted for AV evaluation using traffic simulation over the past decades. However, the current simulation environments fall behind on two fronts -- the background vehicles (BVs) fail to simulate naturalistic driving behavior and the existing environments do not test the entire pipeline in a modular fashion. This study aims to propose a simulation framework that creates a complex and naturalistic traffic environment. Specifically, we combine a modified version of the Simulation of Urban MObility (SUMO) simulator with the Cars Learning to Act (CARLA) simulator to generate a simulation environment that could emulate the complexities of the external environment while providing realistic sensor outputs to the AV pipeline. In past research work, we created an open-source Python package called SUMO-Gym which generates a realistic road network and naturalistic traffic through SUMO and combines that with OpenAI Gym to provide ease of use for the end user. We propose to extend our developed software by adding CARLA, which in turn will enrich the perception of the ego vehicle by providing realistic sensor outputs of the AVs surrounding Using the proposed framework, AVs perception, planning, and control could be tested in a complex and realistic driving environment. framework in constructing output generation and AV evaluations are demonstrated using several case studies

Kusari, Arpan; Sun, Wenbo Low dimensional primitive feature extraction from LiDAR point clouds (such as planes) forms the basis of the majority of LiDAR data processing tasks.A major challenge in LiDAR data analysis arises from the irregular nature of LiDAR data that forces practitioners to either regularize the data using some form of gridding or utilize a triangular mesh such as triangulated irregular network (TIN). While there have been a handful applications using LiDAR data as a connected graph, a principled treatment of utilizing graph-theoretical approach for LiDAR data modeling is still lacking. In this paper, we try to bridge this gap by utilizing a graphical approach for normal estimation from LiDAR point clouds. We formulate the normal estimation problem in an optimization framework, where we find the corresponding normal vector for each LiDAR point by utilizing its nearest neighbors and simultaneously enforcing a graph smoothness assumption based on point samples. This is a non-linear constrained convex optimization problem which can then be solved using projected conjugate gradient descent to yield an unique solution. As an enhancement to our optimization problem, we also provide different weighted solutions based on the dot product of the normals and Euclidean distance between the points. In order to assess the performance of our proposed normal extraction method and weighting strategies, we first provide a detailed analysis on repeated randomly generated datasets with four different noise levels and four different tuning parameters. Finally, we benchmark our proposed method against existing state-of-the-art approaches on a large scale synthetic plane extraction dataset. Full paper and code for the proposed approach: https://arxiv.org/pdf/2205.11460. pdf

3. Di, X., Shi, R., DiGuiseppi, C., Eby, D. W., Hill, L. L., Mielenz, T. J., Molnar, L. J., Strogatz, D., Andrews, H. F., Goldberg, T. E., Lang, B. H., Kim, M., & Li, G. (2021). Using Naturalistic Driving Data to Predict Mild Cognitive Impairment and Dementia: Preliminary Findings from the Longitudinal Research on Aging Drivers (LongROAD) Study. Geriatrics (Basel, Switzerland), 6(2). org/10.3390/geriatrics6020045https://doi.

2. Cao, Y., Zhou, F., Pulver, E. M., Molnar, L. J., Robert, L. P., Tilbury, D. M., & Yang, X. J. (2021). Towards standardized metrics for measuring takeover performance in conditionally automated driving: A systematic review: 65Org/10.1177/1071181321651213,Https://Doi. (1), 1065–1069. org/10.1177/1071181321651213https://doi.

4. Feng, S., Feng, Y., Sun, H., Bao, S., Zhang, Y., & Liu, H. X. (2021). Testing Scenario Library Generation for Connected and Automated Vehicles, Part II: Case Studies. IEEE Transactions on Intelligent Transportation Systems, 22(9), 5635–5647. org/10.1109/TITS.2020.2988309https://doi.

@Daniel Park, Associate Research Scientist @Shan Bao, Research Associate Professor Awards Jingwen Hu has been selected for designation as a Miller Faculty Scholar, for a two-year term effective September 1, 2022. Faculty Scholar is an honorary title awarded to a small group of the most accomplished assistant and associate professors in the College of Engineering.

Graph-theoretical approach to robust 3D normal extraction of LiDAR data

Featured Publications

5. Gaugler, J. E., Zmora, R., Mitchell, L. L., Finlay, J., Rosebush, C. E., Nkimbeng, Promotions

4 RESEARCH REVIEW | AUGUST 2022

1. Cantilina, K., Daly, S. R., Reed, M. P., & Hampshire, R. C. (2021). Approaches and Barriers to Addressing Equity in Transportation: Experiences of Transportation Practitioners: 2675(10),Doi.Org/10.1177/03611981211014533,Https://972–985. org/10.1177/03611981211014533https://doi.

Congratulations to Daniel Park and Shan Bao on their recent promotions.

7. Lee, B., Park, B.-K. (Daniel), Jung, K., & Park, J. (2021). Effects of a Bolster Curvature on an Automobile Seat Fit: 65Org/10.1177/1071181321651180,Https://Doi. (1), 423–426. org/10.1177/1071181321651180https://doi.

10. Vivoda, J. M., Molnar, L. J., Eby, D. W., Bogard, S., Zakrajsek, J. S., Kostyniuk, L. P., St. Louis, R. M., Zanier, N., LeBlanc, D., Smith, J., Yung, R., Nyquist, L., DiGuiseppi, C., Li, G., & Strogatz, D. (2021). The Influence of Hearing Impairment on Driving Avoidance Among a Large Cohort of Older Drivers. Journal of Applied Gerontology, 40(12), 1768–1777. doi.org/10.1177/0733464821999223https://

8. Park, B. K. D., Corner, B. D., Hudson, J. A., Whitestone, J., Mullenger, C. R., & Reed, M. P. (2021). A threedimensional parametric adult head model with representation of scalp shape variability under hair. Applied Ergonomics, 90. org/10.1016/j.apergo.2020.103239https://doi.

9. Peterson, C. M., & Gaugler, J. E. (2021). To speed or not to speed: Thematic analysis of American driving narratives. Journal of Safety Research, 78, 129–137. jsr.2021.04.005https://doi.org/10.1016/j.

5 RESEARCH REVIEW | AUGUST 2022 M., Baker, Z. G., Albers, E. A., & Peterson, C. M. (2021). Remote activity monitoring for family caregivers of persons living with dementia: a mixed method, randomized controlled evaluation. BMC Geriatrics, 21 02634-8https://doi.org/10.1186/s12877-021-(1).

11. Zhu, H., Song, Z., Zhuang, W., Hofmann, H., & Feng, S. (2021). Multi-objective Optimization for Connected and Automated Vehicles Using Machine Learning and Model Predictive Control. SAE International Journal of Electrified Vehicles, 11 https://doi.org/10.4271/14-11-02-0014(2).

6. Koh, S. W., & Hu, J. (2021). Occupant kinematics in a high-speed vehicle-tovehicle rear-end collision. International Journal of Vehicle Safety, 12(2), 166–176. IJVS.2021.121453https://doi.org/10.1504/

Paul W. Brown, Ann Arbor Sarah Hubbard, Okemos Denise Ilitch, Bingham Farms Ron Weiser, Ann Arbor

may be addressed to the Senior Director for Institutional Equity, and Title IX/Section 504/ADA Coordinator, Office for Institutional Equity, 2072 Administrative Services Building, Ann Arbor, Michigan 48109- 1432, 734-763-0235, TTY 734-647-1388, institutional.equity@umich.edu

UMTRI Research Review

UMTRI Director: James Sayer UMTRI Associate Directors: Kathleen D. Klinich

Jingwen Hu UMTRI Business Administrator: Emily Hamilton UMTRI Communications and Marketing Director: Francine Romine Layout and design: Graphikitchen, LLC

Mark J. Bernstein, Ann Arbor

University of Michigan Transportation Research Institute

The Regents of the University

The University of Michigan, as an equal opportunity/affirmative action employer, complies with all applicable federal and state laws regarding nondiscrimination and affirmative action. The University of Michigan is committed to a policy of equal opportunity for all persons and does not discriminate on the basis of race, color, national origin, age, marital status, sex, sexual orientation, gender identity, gender expression, disability, religion, height, weight, or veteran status in employment, educational programs and activities, and Inquiriesadmissions.orcomplaints

Jordan B. Acker, Huntington Woods

Mark S. Schlissel, ex officio

6 RESEARCH REVIEW | AUGUST 2022

Publication Information

The UMTRI Research Review is published four times a year by the Marketing and Communications Department of the University of Michigan Transportation Research Institute, 2901 Baxter Road, Ann Arbor, Michigan 48109-2150.

Michael J. Behm, Grand Blanc

To conduct and disseminate multidisciplinary transportation research to advance safe, equitable, and efficient mobility

UMTRI’s Mission

August 2022

Turn static files into dynamic content formats.

Create a flipbook
Issuu converts static files into: digital portfolios, online yearbooks, online catalogs, digital photo albums and more. Sign up and create your flipbook.