Contribute to core technologies that fuel spatial reasoning in future robotics and augmented reality applications.
My lab works on Visual SLAM, a way to localize and map the surroundings using a camera. This is used on robots for navigation as well as in mobile systems for augmented reality applications. We are exploring several extensions to Visual SLAM including permanence reasoning, distributed operation and executing on resource-constrained platforms.
Students will learn concepts in Computer Vision, Machine Learning and Concurrency by participating in this project. I will need students with some background in programming, and the ability to spend 10-15 hours a week for multiple semesters.
Students will learn about visual spatial reasoning. Technical topics including modern computer vision (particularly multi-view geometry), machine learning, 2D (color) and 3D (depth) images, and working with large software systems.
The computer vision skills are directly relevant to several driverless car companies, augmented reality applications in companies such as Facebook reality labs, Magic Leap, MS Hololens etc., and other companies with mobile systems such as Google and Amazon.
|Length of commitment||Year-long (10-12 months)|
|Start time|| |
|Level of collaboration||Small group project (2-3 students)|
|Who is eligible||All undergraduate students|
Once you begin the digital badge series, you will have access to all the necessary activities and instructions. Your mentor has indicated they would like you to also complete the specific preparation activities below. Please reference this when you get to Step 2 of the Preparation Phase.