UMTRI 2019 SURE Research Projects

UMTRI Project #1: Using Context to Improve Computer Vision Algorithms
Research Mentor Name: Carol Flannagan
Title: Research Assoc Prof.          Email:
Project Description: Large driving databases contain a wealth of information about drivers and the driving environment. However, the large amount of video data makes it difficult to extract information on a large scale (using human coders). Computer vision algorithms are beginning to be used to identify objects and potentially higher-level behaviors in these datasets, but it can take months or years to process through whole databases at current speeds. This project is a continuation of ongoing work to look at how context can be used to speed up processing and improve algorithm accuracy. If time permits, some principles learned will be implemented on UMTRI’s naturalistic driving databases.
Minimum qualifications of student: Some experience with Python, R, and/or C++ is required. Familiarity with the basics of convolutional neural networks is desired.

UMTRI Project #2: Evaluation of Autonomous Wheelchair Docking on City Buses
Research Mentor Name:  Kathleen D. Klinich
Title:  Associate Research Scientist          Email:
Project Description:  The project will evaluate a trial of autonomous docking technology on city buses using video analysis, driver surveys, customer surveys, and focus groups. The standard method for securing passengers using wheelchairs on buses is to use a four-point strap tiedown system that requires assistance from the driver.  TheRide is pilot testing deployment of rear-facing wheelchair docking stations that allow passengers a more independent travel experience.  The student will participate in data collection, analysis, and reporting. 
Minimum qualifications of student:  Strong technical writing skills, experience with spreadsheet/data analysis, interest in improving user travel experience and working with people who have disabilities

UMTRI Project #3: Level 2 Automated System Testing and Driver Behavior Analysis
Research Mentor Name: Shan Bao
Title: Associate Research Scientist          Email:
Project Description: This project is a US DOT funded 2-year project, which is designed to run field operational testing on Level 2 Automated System on the real roads. Student interns get to work with the advanced Level 2 Automated Systems on real cars and will be able to answer a lot of interesting and important research questions through hands on experiences.
Minimum qualifications of student: Have experience/knowledge of data reduction, analysis and are comfortable to work with a big group.

UMTRI Project #4: User Interface Assessment for Automated Driving Systems
Research Mentor Name: Brian T. W. Lin
Title: Assistant Research Scientist          Email:
Project Description: In automated vehicles (AV), information will be provided through different interfaces to the drivers, so they can stay in the loop of the AV’s maneuvers and states. This project aims to evaluate these human-machine interfaces, which are visually shown on the windshield, dashboard, and center console, as well as the auditory information. Methods for subjective assessment will be developed. The experiment will take place on closed course test facilities. Typical driving scenarios will be designed for the AV to engage, such as overtaking, rerouting, taking exit ramp. During the scenarios, necessary information will be shown on the interfaces for the driver. We intend to collect drivers’ subjective assessment for the importance, usefulness, acceptability, annoyance, and so on, of the information presented through various interfaces. Suggestions will be provided to the sponsor about what information should be presented, how the interfaces could be improved, and how the interface could help build trust in the automated driving systems.
Minimum qualifications of student: The qualified student:

  • will help conduct evaluation methods, collect subjective assessment data on the test facilities, conduct data analytic methods, and analyze the data with statistical methods,
  • must have taken the classes of statistics, and human factors or usability assessment,

UMTRI Project #5: Driver State Monitoring for Level 3 Automated Driving
Research Mentor Name: Monica L.H. Jones
Title: Assistant Research Scientist          Email:
Project Description: Autonomous vehicle level 3 (L3) driving systems do not require a driver to monitor the driving situation and automation in certain operational driving domains.  Rather, the social contract for a driver in L3 automated driving is that the driver be ‘receptive’ to an automation take-over request (TOR) or vehicle system failure.  Driver State Monitor (DSM) systems have a role to play in defining requirements for TOR requests within sufficient time for a typical person to respond appropriately to the driving situation at hand. Data will be gathered on a closed test track facility. Continuous measures during in-vehicle test conditions include: driver feedback, video, postural metrics, and available DSM outputs.  Data analysis and modeling efforts will seek to quantify the driver’s limitations and capabilities associated with unscheduled takeover requests (TORs), and how the quality of driver takeover may be assessed to support effective and efficient hand-off of the driving task.
Minimum qualifications of student:

  • Attention to detail
  • Ability to code for the purpose of data analysis & modeling (e.g. Mathematica, MatLab, Python)
  • Willingness to work in an open lab using shared workspace

UMTRI Project #6: Motion Sickness to Inform Automated Vehicle Design
Research Mentor Name: Monica L.H. Jones
Title: Assistant Research Scientist          Email:
Project Description: Motion sickness in road vehicles may become an increasingly important problem as automation transforms drivers into passengers. However, lack of a definitive etiology of motion sickness challenges the design of automated vehicles (AVs) to address and mitigate motion sickness susceptibility effectively. The quantification of motion sickness severity and identification of objective parameters is fundamental to informing future countermeasures. Data were gathered on the Mcity test facility and during on-road driving conditions.  Continuous measures during in-vehicle test conditions include: subjective ratings, perceived sensations, video, physiological response and vehicle data. Modeling effort will elucidate relationships among the factors contributing to motion sickness for the purpose of generating hypotheses and informing future countermeasures for AVs.
Minimum qualifications of student:

  • Attention to detail
  • Ability to code for the purpose of data analysis & modeling (e.g. Mathematica, MatLab, Python)
  • Willingness to work in an open lab using shared workspace

UMTRI Project #7: Adaptive Safety Designs for Injury Prevention: Human Modeling and Impact Simulations
Research Mentor Name: Jingwen Hu
Title: Research Associate professor          Email:
Project Description: Unintentional injuries, such as those occurred in motor vehicle crashes, falls, and sports are a major public health problem worldwide. Finite element (FE) human models have the potential to better estimate tissue-level injury responses than any other existing biomechanical tools. However, current FE human models were primarily developed and validated for midsize men, and yet significant morphological and biomechanical variations exist in human anatomy. The goals of this study are to develop parametric human FE models accounting for the geometric variations in the population, and to conduct a feasibility study using population-based simulations to evaluate the influence of human morphological variation on human impact responses in motor-vehicle crashes and sport-related head impacts. Specifically, in this study, students will use medical image analysis and statistical methods to quantify the geometric variance of the skeleton among the population; use mesh morphing methods to rapidly morph a baseline human FE model to a large number of human models with a wide range of size and shape for both males and females; and conduct impact simulations with those models toward adaptive safety designs.
Minimum qualifications of student:

  • Proficiency in scientific programming languages (Matlab, Pyton, or Mathematica, etc)
  • Interested in injury/impact biomechanics research
  • Excellent oral and written communication skills
  • Ability to work well as a member of a team

Demonstrated ability in FE model development and application is a plus.