Michael Sebok

Papers

Total Citations

H-Index

About

Michael Sebok is a researcher whose work spans the frontiers of artificial intelligence and robotics, bridging the gap between abstract computational theory and real-world autonomous systems. His most impactful contribution, "Statistical Relational Learning With Unconventional String Models" (2018, 44 citations), pioneers the application of statistical relational learning to grammatical inference. By leveraging model-theoretic representations of strings, Sebok provides a novel logical framework for representing formal languages, offering a powerful tool for advancing machine learning in structured data environments. This work has become a foundational reference for researchers exploring the intersection of logic, probability, and language. In robotics, Sebok addresses critical challenges in field deployment. His paper "Resilient Ground Vehicle Autonomous Navigation in GPS-Denied Environments" (2022) demonstrates the importance of co-designing vehicle navigation, control, and state estimation for mobile robots operating in cluttered, GPS-denied settings. Additionally, his study "On the Hybrid Kinematics of Tethered Mobile Robots" (2019) explores the enduring utility of tethers in hazardous environments, from nuclear waste cleanup to underwater inspection. Together, these contributions highlight Sebok’s ability to integrate theoretical rigor with practical engineering, making his work essential reading for students and researchers in AI, robotics, and autonomous systems.