Parvez Alam
Papers
1
Total Citations
2
H-Index
1
About
Parvez Alam is a researcher at the forefront of autonomous systems and robotics, with a primary focus on LiDAR-based perception and odometry. His most notable contribution is the development of **LiDAR-OdomNet**, a deep learning network that fuses attention-based features to accurately predict translation parameters for LiDAR odometry—a critical challenge for autonomous vehicles, drones, and mobile robots. Trained and validated on the widely-used KITTI odometry benchmark, this work demonstrates a data-driven approach that enhances the reliability of self-localization in complex environments. While his research is still gaining traction, with 2 citations to date, LiDAR-OdomNet represents a promising step toward more robust, end-to-end learning solutions in 3D spatial awareness. Alam’s work sits at the intersection of computer vision, sensor fusion, and deep learning, and his contributions are particularly relevant for researchers seeking to improve real-time navigation in unstructured settings. As the field of autonomous navigation rapidly evolves, Alam’s attention-based feature fusion methodology offers a compelling direction for future exploration.
Research Focus
Key Achievements
Top Papers
- 1