Summary
Evan Gravelle is an autonomy engineer with a decade of hands-on experience building state estimation, mapping, and control software for aerial and ground robots, currently improving C++ estimation stacks for Shield.AI’s fully autonomous quadrotor. He blends a PhD-level controls background with practical implementation skills across C++, Python, MATLAB, and ROS, having designed and analyzed provably convergent algorithms for traffic and multi-agent systems during his academic work. Evan has a track record of making sensors more reliable in GPS-denied environments—modeling ground effects for barometers, implementing EKFs and sliding-window estimators, and extending voxel mapping for obstacle avoidance. Comfortable leading teams and mentoring students, he also writes flight-data analysis tools to quantify sensor quality and algorithm performance. Now transitioning toward reinforcement learning, he brings a strong theoretical foundation in probability and deep learning paired with production-grade autonomy experience in safety-critical domains.
10 years of coding experience
5 years of employment as a software developer
University of California San Diego
Bachelor of Science (B.S.), Mechanical Engineering, 3.87, Bachelor of Science (B.S.), Mechanical Engineering, 3.87 at UC Santa Barbara