Koji Minoda
Data Scientist
Chiyoda, Japan
Summary
🤩
Rockstar🎓
Top SchoolKoji Minoda is a data scientist and robotics-focused software engineer with seven years of experience building perception and localization systems for autonomous vehicles. Currently at Woven by Toyota, he improves ML models for AD/ADAS, after leading a six-person perception ML/Data team at TIER IV where he drove scalable MLOps, active learning, and 3D detection efforts. His open-source work on Autoware.Universe includes concrete improvements to gyro-based odometry, IMU correction, and sensor-fusion modules—demonstrating both algorithmic rigor and production-grade engineering. Trained in aeronautics and astronautics at the University of Tokyo with an exchange in robotics at EPFL, he blends aerospace fundamentals with hands-on autonomy software. Notably, he has scaled localization architectures and expanded operational domains by orders of magnitude while coordinating cross-team and OEM collaborations.
7 years of coding experience
4 years of employment as a software developer
Master of Engineering - MEng, Aeronautics and Astronautics, Master of Engineering - MEng, Aeronautics and Astronautics at University of TokyoExchange (Master Course), Robotics, Exchange (Master Course), Robotics at Ecole polytechnique fédérale de LausanneHigh School Diploma, High School Diploma at 筑波大学附属駒場高等学校
English, Japanese
Stackoverflow
93reputation
10kreached
3answers
9questions
Github Skills (22)
c-language10
localization10
cprogramming-language10
ros10
autonomous-driving10
robotics9
sensor-fusion9
data-structures6
hash6
gmp6
linux6
dbi6
perl6
indexing6
makefile6
Programming languages (10)
Github contributions (5)
autowarefoundation/autoware_universe
Mar 2022 - Jan 2023
Role in this project:
Back-end Developer & Robotics Engineer
Back-end Developer & Robotics EngineerContributions:697 reviews, 58 commits, 526 PRs in 10 months
Contributions summary:Koji primarily contributed to the Autoware.Universe repository by implementing and modifying core components related to autonomous driving functionalities. Their work focused on the localization module, including adding roll and pitch rate calculations to the gyro_odometer, adding raw twist output from the gyro_odometer, creating a new package for estimating acceleration, and incorporating sensor fusion by correcting the sign of the offset in imu_corrector. The user also addressed code style issues through automated fixes and added parameter declarations and modifications across different modules, improving overall software quality and functionality.
autowareros23d-mapcalibrationros
kminoda/autoware-documentation
May 2022 - Nov 2023
Contributions:75 pushes, 15 branches in 1 year 6 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.