What is this project?
Large venues like airports, stadiums, and public transit often have multiple entrances for both vehicles and pedestrians which, if not completely accurate in navigation applications, can make “last mile” travel difficult. Students on the Here Technologies team will build a system to automatically detect multiple entry points and routes for large public venues by combining satellite images, street-level imagery, probe data, and text descriptions, improving navigation services and supporting future crowd-aware and accessibility-focused routing.
What am I going to do?
MDP projects push you to integrate interdisciplinary engineering knowledge and develop strategic problem-solving skills. On this project, students build a system to identify multiple points of entry for, and routes into, large public spaces like Michigan Stadium, thus improving navigation services.
- Implement a data ingestion pipeline for image, text, and geospatial data from S3 buckets or zip files
- Develop algorithms to process satellite/street imagery and identify access points using CV methods
- Apply clustering and spatial analysis to infer common ingress/egress paths
- Design lightweight NLP pipelines to parse textual metadata for spatial cues
- Deploy the system on AWS using cloud-native tools and services
- Visualize detected entries and routing paths using open-source mapping libraries
- Validate system output on selected real-world venues
- Tech Stack:
Languages: Java, Scala or Python
Platform: Cloud Native (AWS preferred)
Libraries/SDKs: Open source
Data: HERE Technologies will provide necessary data sets via S3 buckets or zip files
Stretch Goal Opportunities Include:
- Add an Agentic AI layer that orchestrates the existing modules dynamically, deciding which tools to run, when to reprocess, and how to supplement missing data
- Use of NLP techniques to extract location-based insights from web pages or venue descriptions
- Confidence scoring and classification of entrance types (pedestrian, vehicular, delivery/service, etc.)
- Integration with open-source navigation SDKs for use in third-party apps
Why does it matter?
Here Technologies seeks to deliver a complete, accurate, and user-friendly digital model of the physical world. Building a smarter navigation system would facilitate the “last mile” navigation challenges for users, accurately answering questions such as: Which subway stop is best to access a specific building within a sports complex? Which part of an airport should you be dropped off at? HERE Technologies invests heavily in high-definition maps and indoor/outdoor navigation, and automatically detecting multiple entries and routing paths for complex venues like airports, malls, and stadiums would significantly enrich their venue-level map detail, and eliminate inefficient hand mapping.
Below are the skills needed for this project. Students with the following relevant skills and interests, regardless of major, are encouraged to apply! This is a team-based multidisciplinary project. Students on the team are not expected to have experience in all areas, but should be willing to learn and will be asked to perform a breadth of tasks throughout the two-semester project.
Computer Vision (2 students)
Specific Skills: Image segmentation, object detection, OpenCV, satellite/street image parsing, navigation algorithms
Likely Majors: CS, CSE, ECE, ROB, DATA
Natural Language Processing (1 Students)
Specific Skills: NLP text models
Likely Majors: CS, CE, ROB, ECE, CSE
Data Processing (2 Students)
Specific Skills: Large data processing, clustering techniques, NLP text models
Likely Majors: DATA, CS
Mapping & Visualization (1 Student)
Specific Skills: Mapping techniques, general urban planning knowledge, visualization, UI/UX
Must have some skills in writing computer code
Likely Majors: URP, SEAS, SI
Additional Desired Skills/Knowledge/Experience
Strong candidates will have familiarity or experience with some of the following items, and a positive attitude to learn what is necessary, as the project gets underway.
- Experience working on teams as a positive, contributing member
- If you have prior experience in any of the chosen tech stack, please indicate this in your personal statement:
Languages: Java, Scala or Python
Platform: Cloud Native (AWS preferred)
Libraries/SDKs: Open source
Data: HERE Technologies will provide necessary data sets via S3 buckets or zip files
- Experience using Git for version control and collaborative development
- Exposure to Agile or Scrum workflows
- Experience with geospatial data formats and tools (GeoJSON, shapefiles, GeoPandas)
- Knowledge/experience working with navigation algorithms
Recommended Coursework
Include completed relevant courses (term, institution, course number/title, and grade). If you’ve completed any of the following courses, we recommend mentioning them in your application materials:
- EECS 281: Data Structures and Algorithms
- EECS 442: Computer Vision
- EECS 485: Web Systems
- EECS 445: Introduction to Machine Learning
Sponsor Mentor
Buddika Gajapala
Gaj is a senior principal engineer at HERE Technologies with 25+ years of experience in software engineering in various domains, including consumer banking, trading, mortgage, and geospatial/maps. He has broad and deep experience in designing and implementing large scale, high-performant systems, and Cloud computing, and holds two patents.
Faculty Mentor
Sugih Jamin
Associate Professor, Computer Science Engineering
Sugih is an Associate Professor of computer science at the University of Michigan, and possesses more than 16 years of experience in Internet measurement, protocol, and infrastructure design and deployment. Sugih is an experienced MDP mentor.
Project Meetings
During the winter 2026 semester, the Here Technologies team will meet on North Campus on TBD
Work Location
Work will take place on campus in Ann Arbor.
Course Substitutions: CE MDE, ChE Elective, CS Capstone/MDE, DATA Capstone, DATA Graduate Capstone, CoE Honors, ROB Flex Tech , ROB 590
Citizenship Requirements:This project is open to all students. Note: International students on an F-1 visa will be required to declare part time CPT during Winter 2026 and Fall 2026 terms.
IP/NDA:Students will sign IP/NDA documents that are unique to Here Technologies.
Summer Project Activities: No summer activity will take place on the project.