Yasen Hu

Yasen Hu

Perception Systems Engineer

General Motors

Biography

I am a perception systems engineer at the General Motors Research & Development. My research interests include perception and sensor fusion. I would love to utilize my knowledge and skills to build vehicles with more safety features.

Interests

  • Sensor Fusion
  • Computer Vision
  • Machine Learning
  • Artificial Intelligence

Education

  • M.S. in Computer Science, 2020

    Georgia Institute of Technology

  • M.S.E. in Electrical and Computer Engineering, 2014

    University of Michigan-Dearborn

  • B.S.E in Control Engineering, 2010

    Huazhong University of Science and Technology

Experience

 
 
 
 
 

Perception Systems Engineer

General Motors

Jan 2016 – Present Warren, Michigan

Responsibilities include:

  • Research and Development

Projects

*

Libtorch Yolov5

A C++ LibTorch inference implementation of the yolov5 object detection algorithm.

SORT

C++ version of SORT: Simple Online and Realtime Tracking of multiple objects in a video sequence

Unscented Kalman Filter

Implement UKF to estimate vehicle state on highway with noisy LiDAR and Radar measurements

Lidar Object Detection

Processing point cloud data to find obstacles.

Accomplish­ments

Sensor Fusion Nanodegree Program

Learn to fuse LiDAR point clouds, Radar signatures, and camera images using Kalman Filters to perceive the environment and detect and track vehicles and pedestrians over time.
See certificate

State Estimation and Localization for Self-Driving Cars

Understand the key methods for parameter and state estimation used for autonomous driving, such as the method of least-squares. Applied extended and unscented Kalman Filters to a vehicle state estimation problem.
See certificate

Self-Driving Car Nanodegree Program

Learn the skills and techniques used by self-driving car teams at the most advanced technology companies in the world, which includes: computer vision and deep learning, sensor fusion, localization and control, path planning and system integration
See certificate

Contact