Andrew Kramer

Papers

Total Citations

131

H-Index

About

Andrew Kramer is a leading researcher in autonomous robot navigation, specializing in state estimation and perception for challenging, visually degraded environments. His work centers on fusing radar and inertial sensors to enable robust mobility where cameras fail, such as in dense fog, smoke, or darkness. Kramer’s most impactful contribution is his pioneering approach to radar-inertial ego-velocity estimation, which combines millimeter-wave radar-on-a-chip data with inertial measurements in a sliding-window batch optimization. This method, detailed in his 2020 paper (102 citations), provides lightweight, reliable velocity estimates for mobile robots without relying on visual features. He extended this framework to micro-aerial vehicles, demonstrating simultaneous state estimation and obstacle detection in dense fog (20 citations). Additionally, his work on visual-inertial SLAM for subterranean environments (9 citations) addresses the extreme conditions of underground exploration. Kramer’s research has direct applications in search-and-rescue, industrial inspection, and planetary exploration, where traditional sensors are unreliable. His innovations are critical for enabling autonomous systems to operate safely in the most demanding real-world conditions.