Keenan Granland
Papers
1
Total Citations
4
H-Index
1
About
Dr. Keenan Granland is a pioneering researcher at the intersection of agricultural robotics and deep learning, whose work addresses the critical global challenge of rising labor costs in orchard maintenance. His primary research focuses on developing robust computer vision systems that enable autonomous robots to navigate complex agricultural environments safely. Dr. Granland's most significant contribution is the HOB-CNNv2 architecture, a deep learning framework specifically designed to detect extremely occluded tree branches—a notoriously difficult problem in real-world orchard settings. This work, published in 2024 and already garnering 4 citations, introduces a novel approach that references dominant tree images to improve detection accuracy, directly preventing costly collisions between robots and tree canopies. By pushing the boundaries of visual perception in cluttered, natural environments, Dr. Granland is laying the essential groundwork for the next generation of autonomous agricultural machinery, promising to make precision farming more efficient and economically viable for growers worldwide.
Research Focus
Key Achievements
Top Papers
- 1