Michael E. Fitzpatrick
Papers
1
Total Citations
32
H-Index
1
About
Michael E. Fitzpatrick is a leading researcher in autonomous vehicle navigation, with a primary focus on robust positioning systems for wheeled robots in GNSS-denied environments. His most-cited work introduces a deep learning framework that leverages wheel encoder data to maintain accurate vehicle localization when satellite signals are unavailable—a critical advancement for underground mining, urban canyons, and indoor logistics. This contribution, which has garnered 32 citations since 2021, addresses a fundamental challenge in field robotics by replacing expensive LiDAR or vision systems with cost-effective, computationally efficient sensor fusion. Fitzpatrick’s approach demonstrates how neural networks can learn vehicle kinematics from raw encoder streams, achieving sub-meter accuracy without external infrastructure. His research bridges the gap between theoretical deep learning and practical deployment, offering scalable solutions for autonomous forklifts, delivery robots, and mining vehicles. By prioritizing reliability in signal-degraded conditions, Fitzpatrick’s work has direct implications for industrial automation and emergency response robotics. His ongoing investigations continue to push the boundaries of dead-reckoning accuracy, making him a key figure in the evolution of resilient navigation systems for real-world autonomous platforms.
Research Focus
Key Achievements
Top Papers
- 1