Nima Keivan

Papers

Total Citations

H-Index

About

Nima Keivan is a researcher whose work lies at the intersection of robotics, computer vision, and state estimation, with a particular focus on visual-inertial simultaneous localization and mapping (SLAM). His most-cited paper, "Asynchronous Adaptive Conditioning for Visual-Inertial SLAM" (2015, 25 citations), addresses a critical challenge in autonomous navigation: maintaining robust localization under real-world conditions where sensor data arrives at irregular intervals. Keivan’s contribution here is a novel framework that adaptively conditions the visual-inertial system to handle asynchronous measurements, improving accuracy and reliability in dynamic environments. This work has been influential in advancing the practical deployment of SLAM systems on resource-constrained platforms, such as drones and mobile robots. Beyond this, Keivan’s research explores how to fuse heterogeneous sensor streams efficiently, a key enabler for long-term autonomy. His impact is evident in the continued relevance of his methods to modern visual-inertial odometry pipelines, and his work is frequently cited by researchers tackling sensor fusion and real-time estimation challenges. Keivan’s contributions exemplify the kind of foundational engineering that bridges theoretical algorithms with robust, real-world robotic systems.