Papers
31
Total Citations
751
H-Index
13
About
Peyman Moghadam is a leading robotics and machine learning researcher whose work spans field robotics, autonomous navigation, precision agriculture, and 3D perception. With a career bridging foundational sensor fusion techniques and cutting-edge deep learning, Moghadam has made lasting contributions to how robots understand and interact with complex environments. His early work on combining stereo vision and LiDAR for mobile robot path planning (2008) laid groundwork for robust multi-sensor navigation systems. This evolved into influential research on terrain traversability analysis and legged robot locomotion, including energetics-informed gait adaptation for hexapods — work that directly advances autonomous ground vehicle capability in unstructured environments. Moghadam has also made significant strides in 3D place recognition, with LoGG3D-Net (97 citations) and InCloud establishing him as a key voice in SLAM and relocalization research. His precision agriculture contributions are equally notable — from hyperspectral disease detection (158 citations) to LiDAR-based canopy density estimation — demonstrating real-world agricultural impact. More recently, his group has explored transformer architectures for hyperspectral imaging and explainability in object detection. Collectively, his publications have garnered over 600 citations, reflecting sustained influence across robotics, remote sensing, and AI communities worldwide.
Research Focus
Key Achievements
Top Papers
- 1Plant Disease Detection Using Hyperspectral Imaging158 citations · 2017
- 2
- 3
- 4Improving path planning and mapping based on stereo vision and lidar61 citations · 2008
- 5Energetics-informed hexapod gait transitions across terrains53 citations · 2015
- 6
- 7Terrain classification using a hexapod robot32 citations · 2013
- 8
- 9InCloud: Incremental Learning for Point Cloud Place Recognition26 citations · 2022
- 10