Mohamed Elhabiby

About

Mohamed Elhabiby is a leading researcher in autonomous navigation and multi-sensor positioning, with a focus on enabling robust localization in GNSS-challenged environments. His work spans LiDAR-inertial localization, visual odometry, and 3D mapping—critical technologies for self-driving cars, robotics, and smart city applications. Elhabiby’s most cited contributions include the development of the NavINST dataset (2025, 7 citations), a comprehensive multi-sensory urban dataset that supports advanced navigation research under diverse lighting and indoor conditions. He has also pioneered methods for LiDAR registration on high-accuracy 3D digital maps to maintain positioning integrity when GNSS signals are weak or denied (2022, 7 citations), and proposed a ground-constrained LiDAR-inertial localization framework for real-time trajectory estimation in point cloud maps (2023, 5 citations). His work on machine learning-based uncertainty estimation for visual odometry (2020, 5 citations) further strengthens low-cost integrated land vehicle navigation systems. With over 30 citations across his top papers, Elhabiby’s research is foundational for the next generation of reliable, continuous autonomous navigation solutions.

Research Focus

Key Achievements

Top Papers

1. 1
   The NavINST Dataset for Multi-Sensor Autonomous Navigation

   7 citations · 2025
2. 2
   Utilizing LiDAR Registration on 3D High Accuracy Digital Maps for Robust Positioning in GNSS Challenging Environments

   7 citations · 2022
3. 3
   LIDAR-INERTIAL LOCALIZATION WITH GROUND CONSTRAINT IN A POINT CLOUD MAP

   5 citations · 2023
4. 4
   Machine Learning-based Visual Odometry Uncertainty Estimation for Low-cost Integrated Land Vehicle Navigation

   5 citations · 2020
5. 5
   IMPROVED REFERENCE KEY FRAME ALGORITHM

   5 citations · 2019
6. 6
   RGB-D Indoor Plane-based 3D-Modeling using Autonomous Robot

   4 citations · 2014

Key Collaborators

Contact & Links