FPGA based acceleration of cloud point processing
Project Description

In the autonomous driving technology, a large amount of point cloud processing algorithms is performed in many fields such as simultaneous localization and mapping (SLAM), action planning, object detection and tracking. Point cloud processing algorithms are computationally intensive, depending on computers, which take the challenge for the unmanned platforms with limited space and energy. To respond to the challenge, we will develop a FPGA-aided real-time point-cloud processing system for the application in autonomous vehicles.

Supervisor
ZHANG Wei
Quota
1
Course type
UROP1100
Applicant's Roles

The applicant is expected to help on the design of FPGA acceleration for the cloud point processing on FPGA including the system level interface design and RTL implementation of the acceleration function.

Applicant's Learning Objectives

The applicant can learn the design methodology of embedded system design, design flow and techniques of FPGA-based acceleration.

Complexity of the project
Challenging