Ling Guan
Digital Signal Processing
SLAM, or Simultaneous localization and mapping, is an algorithm designed to solve the computational problem of constructing or updating a map of an unknown environment while simultaneously keeping track of an agent's location within it. SLAM has been playing a key role in the design and manufacturing automatic vehicles. In this project, students are required to develop an improved SLAM algorithm using machine intelligence and tracking techniques and deploy it on mobile PC platform on a toy land vehicle.
The objective of this project is to develop an improved software system to enhance the current SLAM algorithm for automatic navigation of cars and other land vehicles.
The system to be developed should: (i) deploy on PC platform; (ii) tracking and constructing the map in real time with good accuracy; (iii) be mounted on a toy land vehicle to test the effectiveness and robustness.
Study the literature on machine intelligence, image analysis and object tracking by SLAM;
Develop a prototype with Open Source Computer Vision (OpenCV) library and C++ language;
Deploy the software on a mobile PC platform mounted on the land vehicle.
Test the prototype for typical road conditions.
This project will be carried out by a group of three students. It is expected that all three students are involved in all aspects of the project. Study the techniques/algorithms in machine learning, image analysis, and object tracking by SLAM. The students will learn practical programming skills in C++ and objective-C, and get familiar with Open Source Computer Vision (OpenCV) library, iOS software development. They will also participate in deploying the software on the mobile PC platform on the vehicle. All students are responsible for the demo and project report.
Software development and testing
Software development and testing
Hardware/software integration and testing
hardware/software co-design, intelligent systems, image analysis
LG02: SLAM Algorithm for Automatic Driving | Ling Guan | Tuesday September 18th 2018 at 01:35 PM