What is this project?
Lane detection vision systems are very good at identifying well marked lanes on paved roads, but these systems struggle when environments lack structure, like lane markings and road boundaries. Help the Hyundai America Technical Center, Inc. (HATCI) develop a vision-based perception stack to detect and localize soft road boundaries in unmarked dirt road scenarios, advancing off-road autonomy for automotive applications. This project aims to enhance vehicle navigation where traditional lane markings are absent, pushing the boundaries of autonomous driving technology.
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 will develop a prototype perception system that accurately detects and localizes soft road boundaries on dirt roads.
- Design and implement a vision-based perception stack using advanced image processing and machine learning techniques
- Develop algorithms for boundary detection and localization without standard lane markings
- Validate the perception system with diverse dirt road scenarios
- Deliver a system that takes images or videos as inputs, and estimates and displays the boundaries as the vehicle advances
- Demonstrate in real time on a display with a simple UI
- Optimize system performance under varying environmental conditions, such as lighting and terrain
- Tech Stack:
Python/C++, OpenCV, Pytorch, Keras, Tensor Flow
Stretch Goal Opportunities Include:
- Dynamically generate a feasible, smooth, and safe drivable path that is within the detected road edges
- Detect off-road surface anomalies, such as potholes and ruts
Why does it matter?
As the demand for autonomous driving expands beyond urban areas, the ability to navigate unmarked dirt roads becomes critical. This project will advance off-road autonomy, enabling vehicles to traverse rural and undeveloped terrains safely and effectively. Success on this project will improve safety in off-road driving scenarios, and accelerate the capabilities of off-road autonomous technologies.
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 (3 students)
Specific Skills: Implementation and tuning of computer vision algorithms, video processing, data augmentation techniques
EECS 281 (or equivalent) is required
Students should be either co-enrolled or have completed coursework/applied project work in machine/computer vision
Likely Majors: CS, CSE, ROB, DATA
General Programming (3 Students)
Specific Skills: Creation of integrated Computer Vision tool (image acquisition, database structure, model implementation, and basic UI)
EECS 281 (or equivalent) is required
All team members are expected to develop Computer Vision knowledge and skills
Must have completed EECS 216 or equivalent. EECS 460 is desired
Likely Majors: CS, DATA
Autonomous Systems (1 Student)
Specific Skills: Interest or experience in autonomous navigation systems
Likely Majors: ROB, ME, AUTO
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.
- Familiarity with computer vision frameworks, i.e. Python/C++, OpenCV, Pytorch, Keras, Tensor Flow
- Experience with autonomous vehicle systems and off-road navigation challenges
- Strong problem-solving skills, and the ability to adapt to variable and unpredictable environments
- Ability to work collaboratively in a team, and communicate technical findings effectively
- Interest in cars and the automotive industry
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
- ROB 330: Localization, Mapping and Navigation
- EECS 504: Foundations of Computer Vision
- EECS 442/542: Computer Vision
- EECS 453: Machine Learning
- EECS 504: Foundations of Computer Vision
- ROB 535: Self Driving Cars: Perception and Control
Sponsor Mentor
Enrique Corona
Enrique Corona holds a Ph.D. in electrical engineering with a specialization in machine learning and computer vision. He currently works as a perception manager in the ADAS group at Hyundai America Technical Center Inc., where he focuses on developing and integrating perception technologies for driver assistance systems. Previously, he was a research computer vision engineer at Ford Motor Company, contributing to 2D-3D object detection and multimodal sensor calibration in the ADAS domain. Before that, he worked at Whirlpool Corporation as a senior research engineer, where he developed lab-based computer vision metrology systems, and supported evaluation of research technologies for potential market integration.
Faculty Mentor
Bernadette Bucher
Bernadette is an assistant professor in the Robotics and Computer Science and Engineering Departments. Her research interests lie in the intersection of robotics, computer vision, and machine learning. Her research is on learning interpretable visual representations and estimating their uncertainty for use in downstream science and robotics tasks, particularly autonomous mobile manipulation.
Previously, she has worked at the Boston Dynamics AI Institute, NVIDIA Research, and Lockheed Martin Corporation. Bernadette received her PhD in computer science in the GRASP lab at University of Pennsylvania.
Project Meetings
During the winter 2026 semester, the HATCI team will meet on North Campus on TBD.
Work Location
Most of the work will take place on campus in Ann Arbor, with periodic visits to the Hyundai America Technical Center, Inc. in Ypsilanti, MI to talk to stakeholders and present findings.
Course Substitutions: AUTO 503, ChE Elective, CS Capstone/MDE, DATA Capstone, DATA Graduate Capstone, GAME 503, CoE Honors, MECHENG 490, MECHENG 590, ROB Flex Tech , ROB 590
Citizenship Requirements:
- This project is open to all students.
- 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 HATCI.
Summer Project Activities:
No summer activity is required. Qualified students will be guaranteed an opportunity to interview for summer 2026 internships no later than February 2026. Students must have the right to work in the U.S.A. indefinitely, without sponsorship, to participate in a summer internship.