J.C. Sutton
Papers
4
Total Citations
58
H-Index
3
About
J.C. Sutton’s research lies at the intersection of autonomous mobile robotics and neural network-based spatial intelligence, with a focus on enabling robots to perceive, map, and navigate their environments without human intervention. His most influential work, “Autonomous mobile robot global self-localization using Kohonen and region-feature neural networks” (1997, 45 citations), introduces two pioneering neural approaches—Kohonen networks and region-feature neural networks (RFNNs)—that allow a robot to determine its location globally within a known space, a foundational challenge in robotics. Building on this, Sutton developed hyper-ellipsoid clustering (HEC) Kohonen networks, which use the Mahalanobis distance to learn elongated sonar data patterns, enhancing map building, place recognition, and motion planning (2002, 7 citations). He further advanced multi-robot systems by demonstrating how two physically distinct robots can share topographical knowledge generated by RFNNs (2002, 4 citations), and fused HEC Kohonen networks with the Julier-Uhlmann-Kalman filter for robust map building and tracking (2002, 2 citations). Though citation counts are modest, Sutton’s work represents a cohesive body of research that pushed the boundaries of self-localization, collaborative mapping, and sensor fusion in mobile robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4