Ke Sun
Senior Software Engineer at Zoox
California, United States
Summary
🤩
Rockstar🎓
Top SchoolKe Sun is a Senior Software Engineer at Zoox with 11 years of experience building motion planning, state estimation, and ML systems for robotic and autonomous vehicle applications. He holds a Ph.D. in Electrical and Systems Engineering from the University of Pennsylvania and has transitioned research-grade stochastic planning and VIO algorithms into production contexts. His work spans algorithm design to sensor fusion—evidenced by contributions to a robust stereo visual-inertial odometry project where he improved RANSAC, Huber weighting, and extrinsic calibration usage. Based in California, he blends academic rigor with practical engineering, optimizing reliability for agile platforms from quadrotors to self-driving cars.
11 years of coding experience
10 years of employment as a software developer
Bachelor of Engineering - BE Electronics and Information Engineering, Bachelor of Engineering - BE Electronics and Information Engineering at The Hong Kong Polytechnic UniversityMaster’s Degree Electrical and Electronics Engineering, Master’s Degree Electrical and Electronics Engineering at Carnegie Mellon UniversityDoctor of Philosophy (Ph.D.) Electrical and Electronics Engineering, Doctor of Philosophy (Ph.D.) Electrical and Electronics Engineering at University of Pennsylvania
Chinese, English
Github Skills (11)
algorithm10
computer-vision10
algorithms10
c-language10
cprogramming-language10
ransac10
eigen9
opencv9
sens8
cal8
calibration8
Programming languages (4)
Github contributions (5)
KumarRobotics/msckf_vio
Nov 2017 - Apr 2021
Robust Stereo Visual Inertial Odometry for Fast Autonomous Flight
Role in this project:
Algorithm Engineer
Algorithm EngineerContributions:18 commits, 4 PRs, 12 pushes in 3 years 5 months
Contributions summary:Ke primarily contributed to the `msckf_vio` project by modifying the core image processing pipeline. Their commits addressed bugs in the two-point RANSAC implementation and the Huber norm weight calculation, indicating a focus on improving the robustness of feature initialization and tracking. Furthermore, they modified the extrinsic calibration parameters usage, suggesting a role in sensor fusion and calibration within the visual-inertial odometry framework.
odometryvisual-inertial-odometrystereo-visionros
KumarRobotics/conformal_lattice_planner
Aug 2019 - Jan 2021
Contributions:398 commits, 1 push, 1 branch in 1 year 4 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.