Cat®Digital, at Caterpillar Inc., serves a diverse user base through an e-Commerce site with visitors including personal consumers, sole proprietors, and large organizations. Students on this team will analyze e-commerce site clickstream data, and develop algorithms to classify unique customer types, developing dynamic website content to best serve each persona.
ProQuest is a content aggregator and research and learning hub with deep historical newspaper content, which creates challenges for optical character recognition (OCR). Students on this team will use machine learning to deliver an end-to-end system that reliably improves the quality of OCR ProQuest content.
Reinforcement learning (RL) is a subfield of machine learning concerned with sequential decision making under uncertainty. In the past decade, RL has seen breakthroughs in game domains (such as AlphaGO and AlphaStar). However, applying RL to real-world applications is still challenging due to the requirement of online interaction and its susceptibility to distribution shift.
Modern vehicles equipped with Advanced Driving Assistance Systems (ADAS) are capable of maintaining the position of the vehicle in the lane automatically (LCA -Lane Centering Assist). Students on this team will design and build the equipment that Subaru needs to efficiently benchmark competing vehicles’ LCA functions.
The JPMorgan Chase project team will design and deliver a real-time digital dashboard to track loan activity on three client-facing portals. The dashboard will provide highly valuable data for the product owner business team, customer servicing representatives, and the CLP Digital technology team. All team members will become JPMC Summer Interns based in Jersey City, NJ.
Researchers at the University of Michigan Transportation Research Institute (UMTRI) have been improving accident impact simulations by broadening the types of body sizes and shapes considered. Students will develop parametric human body models that are capable of testing wide ranges of body sizes, types, and shapes to help create better adaptive and personalized designs for human safety and mobility.
Whirlpool is looking at advanced controls technologies including machine learning, neural networks, and model predictive controllers that will more efficiently cool complex refrigerator systems. Students on this team will evaluate current capabilities on the Python framework that will be fast prototyped and applied in a simulation environment with a conceptual plant model.
Backyard Brains, in conjunction with previous MDP projects, has developed a device to collect and store audio data from the wild to detect and differentiate between birdsongs, insects, and rainfall. Students on this team will optimize the device to make it more manufacturable, user friendly, and ready to ship to Ecuador for field trials.
The Statistics Online Computational Resource (SOCR) is an online platform including web-services and advanced methods and tools in probability, statistics, and machine learning in the health sector. This team will develop an enhanced analysis and visualization toolbox with an emphasis on “Big Data” - very large datasets that are difficult to analyze and interpret in meaningful ways with basic probability and statistical methods.
ArtsEngine is a U-M program based on North Campus that promotes durable collaborations between arts, design, engineering, and technology. Students on the ArtsEngine project will create a media-integrative 21st century expressive instrument by re-imagining and re-designing a vintage analog musical instrument – a Hammond M3 organ.
Honda Sensing® advanced driver-assistance systems (ADAS) are systems developed to automate, adapt and enhance vehicle systems for safety and better driving.Students on this team will develop algorithms to gather and interpret weather data, communicate to the ADAS, and drive decisions about how individual systems will be utilized.
This faculty research team presents a chance to join an exciting research group that designs sensors for spacecraft that explore extreme environments in space from the surface of the Sun to the outer edges of the solar system. We will design and test a Faraday cup to further our understanding of the Sun.
The primary objective for the Ann Arbor Virtual+ Academy is to provide students in the Ann Arbor Public School System access to online and extended learning options that will help them to develop a personalized learning path.Students on the A2 Virtual+ team will create a standalone web application that will streamline and simplify the class registration process for students, parents, and staff.
ProQuest is a content aggregator and research and learning hub for students, librarians, researchers and literature specialists. The students on the AI ProQuest team will deliver an end-to-end system that can reliably suggest and assist users in exploring relevant documents by utilizing a knowledge graph built off citations and other data from ProQuest’s corpus, which contains over one billion documents.
Consumer adoption of autonomous technology will depend in large part on how split-second moments in which imminent hazards are about to happen are experienced. Students on this Veoneer team will use human centric design to research and prototype a visual and audible driver alert system that improves the communication between the vehicle and its operator.
On orbit servicing of satellites is soon to become the next big space endeavor and Northrop Grumman is already ahead of the game with early vehicles performing that mission. What is needed is help determining how those vehicles do their job, including mission tools and components, and you can be part of it!
This faculty research team is designing a nanospacecraft and operating a space mission that will explore the feasibility of a novel propulsion technology – miniature electrodynamic tethers – as propellant-less propulsion to new classes of very small satellites known as picosats and femtosats. Students will create a spacecraft with an operational ED tether for the first experimental testing of propellantless operation in space.
Union Pacific is the second largest landowner in the United States (after the U.S.A Federal Government) and many people at times require access to the land managed by UP’s Real Estate department. The student team will redesign and deliver a new business system to replace the current paper based process.
Union Pacific manages over 33,000 craft professionals including conductors and engineers who are managed through unions via collective bargaining agreements; when these agreements aren’t followed, claims are required to be submitted for review. The student team will redesign and deliver a fully electronic claims system to replace the current, outdated, paper based process that doesn’t meet current needs.
Principal aims to help individuals by providing disability income insurance so that when the unexpected happens, people are better able to continue living the lifestyle they’veworked for. Students on this team will work to design and prototype a working digital process flow that allows the key stakeholders to collaborate digitally and makes the experience parallel to – or better than – consumer digital expectations.
DENSO, one of the largest global mobility suppliers of advanced technology, systems and components, leverages a product launch system to ensure successful, on time product launches. Students on this team will become intimately familiar with DENSO’s core processes in commercial management and product launch readiness, while developing a platform that will optimize our global network and provide a virtual reach towards manufacturing.
The energy consumption data on the impacts of the last mile of travel is often estimated rather than calculated, resulting in uncertainty in emissions data. Students on the EPA team will develop and validate a physics-based model of energy usage of electric bikes and scooters based on environmental, geospatial, and behavioral variables, and create a simple website to communicate model results to the public.