Aug 2021 · Autonomous Racing / System Integration / Team Leadership / Open Source / Sponsorships
MIT Driverless: Autonomous Race Car & Open-Source Ecosystem
Led perception for MIT’s autonomous Formula Student race car, improving detection mAP from 66.97% to 89.35%. The team released its dataset, labeling pipeline and training infrastructure as an open-source foundation used by more than 100 student racing teams.
The challenge
Autonomous racing combines accuracy, latency and system integration under track conditions, with a shared workflow across a large student engineering team.
The approach
We developed the perception stack and released the dataset, annotation pipeline and training infrastructure. I also co-led pitches securing more than $200K in sponsorships from Google, Waymo and Oracle.
The outcome
Detection mAP improved from 66.97% to 89.35%. The open-source work has supported more than 100 student racing teams worldwide.