Project Ideas...

Below, you will find some alternate experiences at the ready for those of you nearing graduation. The following ideas have been pre-vetted by your individual Program Directors, and if any look interesting, your next step would be to develop a more complete Proposal.

To complete your Proposal, you'll still follow the same guidelines that are listed on the ISD Student Center, in the Capstone Corner. If you have any trouble accessing this link, please contact your Graduate Coordinator. Please feel free to reach out to the Capstone Coordinator. They would be happy to help you with brainstorming project ideas and help with your Proposal!

-ISD 503 Capstone Coordinator | isdcapstonecoord@umich.edu

Integrative Systems + Design Division | College of Engineering | University of Michigan

SI-North, 1075 Beal Ave. | Ann Arbor, MI 48109-2112

The University of Michigan Transportation Research Institute has been a source of great 503 projects in the past! Below are several projects that have been solicited by Prof. Jingwen Hu for 2020-2021:

Project 1: US Army project to make remotely driven vehicle easier to drive

Contact: Paul Green, Research Professor, pagreen@umich.edu

Project Description: We are working on a US Army project to make remotely driven vehicle easier to drive. As part of that project, we are looking for ways to load in real world data bases from Unreal so that we can drive them. We are looking at video games for this purpose.

Software that loads in data bases and is driver able

Project Background: The Army has a motion based simulator they use for studies, but it is so complicated, they can only do 1 experiment per year. We are looking for something we can use for pilot tests to understand problems and design better experiments.

Location: Ideally, this would be done at University of Michigan Transportation Research Institute using a simulator there. If not, this can be done remotely.

Programs that would be “best fits”: probably Auto MEng

Project 2: Visualize big data

Contact: Brian Lin, Assistant Research Scientist, btwlin@umich.edu

Project Description: UMTRI Human Factors Group have used a great amount of naturalistic driving data to investigate human drivers' behavior in order to develop advanced safety features. This project intends to visualize the big data based on various methods, theories, and tools to help sponsors make decisions and adjustments on the safety and automation features.

Data visualization tools/methods to elaborate the results from naturalistic driving data mining

Project Background:

Location: This project can be done remotely

Programs that would be “best fits”:Design science

Project 3: process image and depth data

Contact: Monica Jones, Assistant Research Scientist, mhaumann@umich.edu

Project Description: Driver State Monitoring Systems: Challenges to Track Driver Head, Gaze and Posture

With increasing automation (SAE Levels 2 and 3), the role of the driver will transition from Driver Driving (DD) to Driver Not Driving (DND). However, there is little quantitative information is available on naturalistic non-driving occupant behavior. Driver state monitoring (DSM) systems attempt to predict the driver’s readiness to respond to a takeover request or other emerging need 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.

Using computer vision and openCV face and gaze tracking resources, this project will seek to develop code to process image and depth data gathered from drivers and front-seat passengers. The objective is to process images to quantify occupant posture, state, (e.g. drowsiness, attention, vigilance) behaviors, and performance to in-vehicle exposures.

Datasets available have been gathered on the Mcity test facility, during on-road driving conditions and are planned to be conducted on American Center for Mobility (ACM).

Project Background: Image processing

Ability to code for the purpose of data analysis & modeling (e.g. Python, Mathematica, C++)

Location: This project can be done remotely.

Programs that would be “best fits”:Auto MEng, Systems Engineering + Design, CS, EECS

Project 4: Simulated vehicle testing

Contact: Shan Bao, Associate Research Scientist, shanbao@umich.edu

Project Description: When evaluating and testing automated vehicle technologies, it is pretty challenging and expensive to test the prototype system using real cars on real roads. Ideally, parameter setting of sensors and vehicle control systems can be tested and evaluated under variety of simulated scenarios at first. This work is sponsored by a mixed of sponsors with several focuses.

The work is designed to simulate real world driving scenarios in the virtual environment through software (e.g., Vissim and Carla) or Virtual Reality techniques. Student interns get to work with the exciting concepts and interact with our industry sponsors directly and will be able to implement your simulation results through hands on experiences. We are looking for multiple motivated student helpers. Training on certain software (e.g., ViSSIM, Carla) are available.

Project Background: Coding Experience (e.g., Python, R, and/or C++). Good at Vissim or Carla is plus!

Location: This project can be done remotely.

Programs that would be “best fits”:Auto MEng, Systems Engineering + Design, CS, EECS

Project 5: designing and implementing algorithms to optimize societal benefits in deliveries

Contact: Tayo Fabusuyi, Assistant Research Scientist, Fabusuyi@umich.edu

Project Description: The Covid-19 pandemic has further underscored the importance of on-demand delivery services but getting actionable data on these deliveries has been problematic. We will be using publicly available microdata and proprietary GPS data in providing estimates of these deliveries at specific addresses and in designing and implementing algorithms that provide the most societal benefits in making these deliveries.

Develop a nationally scalable approach that estimates and forecasts the volume of on-demand delivery at fine geographic scales and implements a routing algorithm that fulfills the deliveries in the most societal beneficial manner.

Project Background: Mathematical programming; Data visualization (e.g. using GeoJSON)

Location: Can be done remotely

Programs that would be “best fits”:Systems Engr + Design; CS; Mech; IOE

If you are having difficulties finding a project with your current employer or an internship, consider one of these:

• Participation in the DESIGN phase of this Siemens challenge: https://www.engineeringforchange.org/siemenschallenge/

There are 2 tracks: Design a postharvest off-grid preservation technology OR Design a very low-cost, energy-efficient, scalable technology for desalinating brackish water

• Is there an Energy Systems research-type question that could be answered through analysis of publicly-available data like from https://www.eia.gov/todayinenergy/detail.php?id=42675 or Kaggle, etc.?

• Carry out a Socio-Techno-economic analysis of different proposed technologies

If you are having difficulties finding a project with your current employer or an internship, consider one of these:

• Address manufacturing and operations aspects of potential design solutions to online challenges.

There are a number of online challenges, including a couple that speak directly to engineering for the greater good:

• Innovate for Impact, https://www.engineeringforchange.org/siemenschallenge/

• https://grabcad.com/challenges/nasa-regolith-advanced-surface-systems-operations-robot-rassor-bucket-drum-design-challenge

• Is there an Industry 4.0 research-type question that could be answered through analysis of publicly-available data like from https://www.eia.gov/todayinenergy/detail.php?id=42675 or Kaggle, etc.?

• Is there something in your house (or virtually through Solidworks, etc.?) that you can reverse engineer, and re-design for X?

What do you know about the industry the product comes from? What are competing products? How is it manufactured? How could it be manufactured better What is the social context of this product? (Who has access? Who doesn’t? Are there regulatory policies around this product?) If you were to re-design for “X”, who might your stakeholders be? Does the company have an IP strategy? (What is it?) etc.

If you are having difficulties finding a project with your current employer or an internship, consider one of these:

• Address manufacturing and operations aspects of potential design solutions to online challenges.

There are a number of online challenges, including a couple that speak directly to engineering for the greater good:

• Innovate for Impact, https://www.engineeringforchange.org/siemenschallenge/

• https://grabcad.com/challenges/nasa-regolith-advanced-surface-systems-operations-robot-rassor-bucket-drum-design-challenge

• Is there an Industry 4.0 research-type question that could be answered through analysis of publicly-available data like from https://www.eia.gov/todayinenergy/detail.php?id=42675 or Kaggle, etc.?

• Is there something in your house (or virtually through Solidworks, etc.?) that you can reverse engineer, and re-design for X?

What do you know about the industry the product comes from? What are competing products? How is it manufactured? How could it be manufactured better What is the social context of this product? (Who has access? Who doesn’t? Are there regulatory policies around this product?) If you were to re-design for “X”, who might your stakeholders be? Does the company have an IP strategy? (What is it?) etc.