Norman Jaklin

Papers

Total Citations

H-Index

About

Norman Jaklin’s research lies at the intersection of computational geometry and robotics, with a focus on path planning and structural compensation. His most notable contribution is in the **Weighted Region Problem**, where he developed methods for computing high-quality, cost-optimal paths across weighted planar subdivisions. His 2014 paper on this topic (10 citations) addresses the challenge of balancing computational speed with geometric accuracy, offering a grid-based approach that retains the exact geometry of the scene—a critical advancement for autonomous navigation and geospatial analysis. In robotics, Jaklin tackles the physical limitations of heavy-load systems. His 2020 work on the **ITER blanket remote handling system**—which manipulates 4-ton objects—proposes a novel deep learning framework to compensate for structural displacements of up to 100 mm at the end effector. By combining neural networks with physics-based virtual models, his method enhances precision in extreme environments, such as nuclear fusion maintenance. With a citation count reflecting his niche but impactful contributions, Jaklin’s work bridges theoretical path optimization and real-world robotic applications. His achievements demonstrate how deep learning can correct mechanical deformations, pushing the boundaries of automation in high-stakes industrial settings.