UMTRI Project #1: Adaptive Safety Designs for Injury Prevention: Human Modeling and Impact Simulations
Faculty Mentor: Jingwen Hu, [email protected]
Prerequisites:
- Proficiency in MATLAB or other programming tools
- Interested in machine-learning, statistical modeling, and/or injury biomechanics research
- Demonstrated ability in 3D human geometry model and/or FE model development and application is a plus
Project Description: Unintentional injuries, such as those occurring 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 geometry and 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/machine-learning 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; conduct impact simulations with those models; and use machine-learning models to build surrogate models for injury assessment toward adaptive safety designs.
Research Mode: In Lab, Online or Hybrid
UMTRI Project #2: Driver State Monitoring for Automated Vehicles
Faculty Mentor: Monica L.H. Jones, [email protected]
Prerequisites:
- Motivated students, keen to work both independently and within a group.
- Some experience with scientific programming languages is required (e.g. Mathematica, MatLab, Python).
- Familiarity with computer vision programming is desired.
Project Description: With increasing automation (SAE Levels 2 and 3), the role of the driver will transition from Driver Driving (DD) to Driver Not Driving (DND). Freed from completing operational tasks of driving, drivers will have a much larger behavioral repertoire. Driver state monitoring (DSM) systems attempt to predict the driver’s readiness to respond to a takeover request or other emerging needs within the situation from information obtained from cameras and other sensors. These systems face several challenges to comprehensively track the continuum of possible driver postures and behaviors. Many research questions persist with respect to the efficacy and effectiveness of DSM systems. The results of this project may identify disallowed states and provide further design guidance for DSMs.
This project explores the characteristics and behaviors associated with non-nominal postures, driver engagement, monitoring, and state levels – under day and night conditions. It also seeks to quantify driver responses to unscheduled automated-to-manual (non-critical) transitions in L3 automated driving conditions. Data were gathered at the American Center for Mobility closed test facility. Continuous measures during in-vehicle exposures include 2D image and 3D depth data, physiological response, driver performance and behavior data, vehicle data, and available DSM outputs.
Student researchers will also assist with data analysis, and develop image processing models &/or computational models that predict driver engagement.
Research Mode: In Lab, Hybrid
UMTRI Project #3: Electrical Vehicle Charging Station Recommendation Smart-Phone APP Development
Faculty Mentor: Shan Bao, [email protected]
Prerequisites:
- Motivated students who are comfortable working with a big group.
- Having skills of website development is a great plus!!
Project Description: The transition to electric vehicles (EVs) represents a significant market opportunity for the automotive industry and the energy sector. while the success of this transition heavily relies on user acceptance. While EVs have a number of advantages over traditional gasoline vehicles, such as lower emissions and reduced operating costs, they also present some unique challenges for users, including range anxiety and the availability of charging infrastructure. To encourage EV adoption, it is crucial to provide users with convenient and reliable charging options. While there is a general consensus that EV production will eventually dominate the automobile industry, the majority of potential customers are still hesitant to switch to EVs. The objective is to develop a smartphone-based user-centered charging station (CS) recommendation system through data-driven methods, which require inputs from multiple data sources.
The research team will be working with industry experts directly on this project. Student researchers will assist with data collection, and analysis, and develop a phone app.
Research Mode: In lab or Hybrid
UMTRI Project #4: Safety and Independence of Passengers in Wheelchairs Using Automated Vehicles and Aircraft
Faculty Mentor: Kathleen D. Klinich, [email protected]
Prerequisites:
- Strong technical writing skills, experience with spreadsheet/data analysis, mechanical design/controls experience, and an interest in improving the user travel experience and working with people who have disabilities.
Project Description: We have multiple projects to ensure that people who travel while seated in their wheelchairs can safely and independently do so in automated vehicles where there may not be a driver to assist in securing the wheelchair, or in aircraft where personal wheelchair use is not currently allowed. Student researchers could help with measuring the posture and shape of volunteers using wheelchairs, help with dynamic test fixture design and laboratory testing, assist with data analysis, or help create computational models of wheelchair geometry
Research Mode: In Lab, hybrid
UMTRI Project #5: Motion Sickness to Inform Automated Vehicle Design
Prerequisites:
- Motivated students, keen to work both independently and within a group.
- Some experience with scientific programming languages is required (e.g. Mathematica, MatLab, Python).
- Familiarity with computer vision programming is desired
Project Description: Motion sickness in road vehicles may become an increasingly important problem as automation transforms drivers into passengers. However, the 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-road and at the Mcity and Michigan Proving Ground test facilities. Continuous measures include 2D image and 3D depth data, thermal imaging, physiological response, vehicle data, and self-reported motion sickness response. Modeling effort will elucidate relationships among the factors contributing to motion sickness for the purpose of generating hypotheses and informing future countermeasures for AVs.
Students will have hands-on experiences working on instrumenting AVs at Mcity, and testing. Student researchers will also assist with data analysis or develop computational models that detect and predict passenger motion sickness.
Research Mode: In Lab, Hybrid
Faculty Mentor: Monica L.H. Jones, [email protected]
UMTRI Project #6: Development for Automated Vehicle Intelligent Lane-Weaving Function
Faculty Mentor: Brian T. W. Lin, [email protected]
Prerequisites:
- Know ROS framework
- Some experience with Python and Linux; experience with projects using ROS is a huge plus
- Have great communication skills and teamwork experience
Project Description: For autonomous vehicles (AV) to engage in a weaving movement, the system needs to decide when and how the lane change should be safely executed, according to the vehicle telematics, ramp geometry, and the maneuver of the other weaving/non-weaving vehicles. The research team had previously implemented the decision-making models in the augmented reality environment and evaluated them. In this project, we aim to deploy the complete computational ROS-based weaving decision models to Mcity’s Lincoln MKZ autonomous vehicle (AV), for which the models had been validated in computer simulations. We are keen to implement the models in AV with the signals input from the other vehicle on the test track through RTK and evaluate the performance of the models, communications among different entities, and safety issues.
The students who are involved will help program in Python to subscribe/broadcast ROS topics to control the AV and subscribe GPS data as the input for the decision model, conduct the test track experiment at Mcity, and analyze the data.
Research Mode: In Lab, Hybrid
UMTRI Project #7: Mobile AR App Development For 3D Body Shape Modeling
Faculty Mentor: B-K. Daniel Park, [email protected]
Prerequisites:
- Proficiency in computer programming languages (C#, C++, Unity, Etc.)
Project Description: This project aims to create a smartphone app that harnesses 3D statistical body shape models. UMTRI has emerged as a global leader in the field of parametric human anatomy modeling. 3D body shape models, developed using data from 3D laser scans and anthropometric measurements of individuals with diverse body characteristics, serve as the foundation of this technology. They enable the rapid generation of subject-specific 3D avatars and provide anthropometric predictions applicable to various domains, including engineering, medicine, and design. To foster knowledge sharing and facilitate potential collaborations, we have been sharing our developed models on the website, HumanShape.org, which has proven to be an excellent platform. This project seeks to enhance user experiences by transferring online models to a smartphone app and delivering more valuable experiences to users. Accomplishing this objective will necessitate utilizing cutting-edge programming techniques such as 3D visualization, mobile app design, and statistical analysis.
Research Mode: In Lab, Remote, Hybrid
UMTRI Project #8: Automated Vehicle Malfunction and Coping Strategies Development
Faculty Mentor: Shan Bao, [email protected]
Prerequisites:
- Team players who are motivated to work with other group members.
- Experience with human factors knowledge and/or text mining experiences are a plus!
Project Description: Automated systems that control/drive a vehicle or assist a driver may fail/malfunction at any time while driving in traffic and lead to crashes. This Mcity-sponsored project is designed to understand the typical and important failure types and taxonomies for automated vehicle systems that are currently on the road, as well as to develop coping strategies in mitigating hazards of such vehicle failures and supporting safe and efficient responses for drivers from both subject and surrounding vehicles. A hybrid approach is proposed to address the research questions both qualitatively and quantitatively.
The research team will be working with industry experts directly on this project. Students will have hands-on experiences working on scenarios simulation, and AV testing under different conditions.
Research Mode: In-lab (Mcity testing), Online or Hybrid
UMTRI Project #9: A Tool for Augmented Reality (AR) Assisted Surgery: 3D Human Modeling and Visualization
Faculty Mentor: Jingwen Hu, [email protected]
Prerequisites:
- Proficiency in computer programming languages (C#, C++, Unity, Python, etc.).
- Previous experience of using Microsoft HoloLens will be a plus.
Project Description: An AR-assisted surgery tool will provide a composite view between computer-generated patient anatomy and a surgeon’s view of the operative field, which may lead to more precise understanding of the detailed anatomy and also significantly increase accuracy in tumor localization and resection. In this study, we will focus on a software tool that can address the rapid development of computer anatomy models and accurate registration between the anatomy model and real patient geometry, which are the two key aspects of AR-assisted surgery tools. We plan to use an AR device, Microsoft HoloLens, as the main hardware to demonstrate the software capability, although our software should not be limited to HoloLens only. In this study, we will use liver surgery as an example, thus the medical images and anatomy models will only focus on the liver and the surrounding tissues. Because liver is the largest solid organ in the abdomen, is pliable, and operative interventions can alter its anatomy, it will pose significant challenges on model registration, which will be a good test for the AR-assisted surgery tool. For surgeons who have to deal with complex anatomical structures that are not always visible, the proposed AR-assisted surgery tool will provide much needed understanding of anatomic relations beneath the surface, and will likely lead to better accuracy, safer resection, lower complications, and superior surgical outcomes.
Research Mode: In Lab, Online, Hybrid
UMTRI Project #10: Support for Driver Interface Research
Faculty Mentor: Paul Green, [email protected]
Prerequisites:
- None, but being a licensed driver is helpful
Project Description: We are conducting a variety of projects for which help is needed. In support of a number of Army projects, we are writing a standard that defines measures of driving performance and provides representative data based on the literature and possibly based on original research. We have developed an industry standard for this purpose in the past for cars and trucks driven on-road, but for this research, we need to include off-road vehicles and armored vehicles. This research is quite fundamental in that it is defining the science of driving, but quite applied in that we need real-world data to support what we do. In addition, anyone working in the group invariably becomes involved in other projects as well, if for no other reason than to provide a broader research experience.
Research Mode: In Lab (possibly), Online, Remote, Hybrid
UMTRI Project #11: Driving Simulator Development – Unreal Engine
Faculty Mentor: Paul Green, [email protected]
Prerequisites:
- None, but being a licensed driver is helpful, and knowledge of Unreal is helpful
Project Description: We have a number of projects with the U.S. Army related to driving combat vehicles. In support of them, we need to develop a simulation in Unreal of driving in a specific virtual world, adding sound, vehicle dynamics, minimaps, and a HUD to represent a particular vehicle. We also need to record driving performance in real-time. We know this is feasible because a student completed elements of this in the past, but the documentation is incomplete and we need to add more features. We have requested hardware for this task from the Army.
Research Mode: In Lab (possibly), Online, Remote, Hybrid
UMTRI Project #12: Continuing Development of a Manned Driving Simulator
Faculty Mentor: Paul Green, [email protected]
Prerequisites:
- None, but being a licensed driver is helpful, and knowledge of Python is helpful
Project Description: For almost 2 years, various MDP teams have been working on the development of a driving simulator that includes a moving base cab for studies of human interaction with partially automated and automated vehicles. Our focus is on 3 elements: (1) a GUI to allow for the rapid creation of experiments (especially scenarios and vehicle placement), (2) the ability to import virtual worlds, and (3) control of a 2-DOF motion platform in real-time (pitch and roll). The underlying code runs under LINUX and uses CARLA and ROADRUNNER.
Research Mode: In Lab (possibly), Online, Remote, Hybrid
UMTRI Project #13: Development and Implementation of Software Tools for Human-Centered Design
Faculty Mentor: Matt Reed, [email protected]
Prerequisites:
- Prior experience with R and/or Python
Project Description: The Biosciences Group has developed a wide range of statistical models of human posture and body shape for use in human-centered design. However, the complexity of these models is such that relatively few people are able to use them. The goal of this project is to make more of these models available online for people around the world to use for human-centered design. (As an example, see: http://humanshape.org/). The tools include interactive analysis of standard anthropometry (body dimensions), three-dimensional anthropometry, head and face geometry, and vehicle occupant postures.
The student(s) will work with the faculty to develop and deploy design tools using R and/or Python. Applications may also be developed for implementation in open-source tools such as FreeCAD and Blender3D.
Research Mode: In-person, Remote, or Hybrid
UMTRI Project #14: Entropy-based Domain Adaptation for Deep Neural Networks
Faculty Mentor: Wenbo Sun, [email protected]
Prerequisites:
- Proficiency in Python
- Experience with deep neural networks, especially convolutional neural networks for image classification
- Familiar with state-of-the-art image classification datasets
- Experience with hyper-parameter tuning based on pre-trained models
- Experience with great lake computing
- Experience with transfer learning is desired
Project Description: Machine learning techniques have been widely used for image classification in the computer vision field. The deep neural network trained in one domain (source domain) may not be directly applicable to another domain (target domain), which requires the domain adaptation techniques to adjust a pre-trained model based on the target dataset. However, there is often the case that arbitrary application of domain adaptation techniques results in worse results (negative transfer). In this study, we would like to investigate whether specific regularization on the neural network architecture can improve the generalizability of deep neural networks through the control of information flows. In particular, in this study, the student will explore the feasibility of multiple regularization terms that can mitigate the negative transfer. The student is expected to conduct code implementation, model training, and hyperparameter tuning. It is expected that the research project will result in a journal/conference paper on the proposed methodology.
Research Mode: Online or hybrid
UMTRI Project #15: Development of a Smartphone App to Gather Participant Data In-the-Wild
Faculty Mentor: Kathleen D. Klinich [email protected]
Prerequisites:
- Proficiency in computer programming languages (C#, C++, Unity, etc), previous experience with app development
Project Description: UMTRI researchers often perform studies involving volunteers traveling as passengers in vehicles. For this project, the student researcher would develop a smartphone app that could be used by volunteers to record their experiences during travel. Additional applications also include passive (continuous) monitoring of time history and GPS location, and physical response to vehicle acceleration exposure using a smartphone’s IMU sensor. The app should be easily reconfigurable to adjust to the needs of different research studies. It needs to be accessible, so will need screen and voice input options.
Research Mode: Hybrid