Kevin Kaighn

SRI International, Vision International University

Papers

Total Citations

H-Index

About

Kevin Kaighn is a robotics researcher specializing in autonomous navigation, sensor fusion, and vision-based perception for challenging environments. His work focuses on enabling reliable robot operation in visually-degraded conditions—such as smoke-filled rooms, low-light tunnels, or dusty disaster zones—where standard cameras fail. Kaighn’s major contributions include developing multi-sensor fusion techniques that combine low-cost inertial, visual, and depth sensors to maintain accurate motion estimation when individual sensors degrade. His most cited paper (23 citations) pioneers FPGA acceleration for feature-based vision processing, dramatically improving real-time performance for applications like infrastructure inspection. In his SIGNAV system (7 citations), Kaighn introduced semantically-informed SLAM that understands scene context—distinguishing walls from debris or doors from obstacles—to maintain robust mapping even in GPS-denied, visually-degraded settings. This work bridges the gap between classical geometric SLAM and modern semantic understanding, directly supporting indoor rescue missions and autonomous inspection. With a growing citation record and publications in top robotics venues, Kaighn is establishing himself as a key voice in resilient perception for field robotics, pushing autonomous systems toward true operational robustness in the real world’s most difficult conditions.