John McConnell

Papers

Total Citations

H-Index

About

John McConnell is an emerging researcher whose work sits at the intersection of autonomous underwater robotics, perception, and state estimation. His research focuses on developing robust simultaneous localization and mapping (SLAM) solutions for autonomous underwater vehicles (AUVs), with a particular emphasis on making these systems practical using low-cost sensor configurations. McConnell's most cited contribution, "Overhead Image Factors for Underwater Sonar-Based SLAM" (2022, 34 citations), demonstrates his innovative approach of leveraging widely available overhead imagery to enhance sonar-based navigation — a creative solution to the persistent challenge of accurate underwater state estimation. His work extends beyond single-robot systems; "DRACo-SLAM" (2022, 20 citations) addresses the complex problem of multi-robot coordination underwater, introducing a distributed SLAM framework that accounts for the severe communication constraints inherent to acoustic underwater channels. Complementing these contributions, his survey on underwater robot perception (2022, 10 citations) reflects his broad command of the field. With all three major works published in the same year and accumulating over 60 citations collectively, McConnell represents a promising voice advancing the frontier of reliable, scalable underwater autonomy.