Junsheng Fu
Technical Expert In Localization And Road Estimation
Gothenburg, Sweden
Summary
👤
SeniorJunsheng Fu is a technical expert in localization and road estimation for autonomous vehicles, currently shaping perception and mapping at Zenseact in Gothenburg, Sweden. With nine years in the field and a portfolio of 21 patents, 8 publications, and 13 open-source projects, he combines research depth with practical engineering. He has hands-on experience across camera, LiDAR, radar, and HD maps, specializing in sensor fusion, localization, road estimation, and high-definition mapping for robust autonomous systems. Notably, he contributed to an EKF-based object-tracking project that fuses LiDAR and radar data, incorporating pedestrian tracking, RMSE evaluation, Jacobian calculations, and careful angle normalization. His work emphasizes turning complex algorithms into reliable production software through thoughtful refactoring and rigorous validation. Based in Sweden, he operates at the intersection of IP-rich innovation and real-world deployment, advancing autonomous mobility.
9 years of coding experience
English, Chinese, Finnish
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (5)
object-tracking10
eigen10
lidar10
c-language8
c-programming-language8
Programming languages (4)
Github contributions (5)
JunshengFu/tracking-with-Extended-Kalman-Filter
Apr 2017 - Sep 2021
Object (e.g Pedestrian, vehicles) tracking by Extended Kalman Filter (EKF), with fused data from both lidar and radar sensors.
Role in this project:
Data Scientist
Data ScientistContributions:54 commits, 50 pushes, 1 branch in 4 years 5 months
Contributions summary:Junsheng contributed significantly to the project by implementing and refining core functionalities related to object tracking using an Extended Kalman Filter (EKF). Their work includes adding pedestrian tracking using lidar data, implementing RMSE calculation and Jacobian matrix computations, and refactoring code for handling fused data from lidar and radar sensors. The user also addressed issues related to angle normalization and initialization, improving the accuracy and reliability of the tracking system.
extended-kalman-filterslidarradar
JunshengFu/junshengfu.github.io
Apr 2017 - Nov 2024
Contributions:58 pushes, 1 branch in 7 years 7 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.