Praveen Kumar Reddy

Papers

Total Citations

H-Index

About

Praveen Kumar Reddy is a rising researcher at the forefront of self-supervised learning for embodied AI, with a primary focus on monocular depth estimation—a critical capability for robotics and autonomous vision systems. His most-cited work, "Embodiment: Self-Supervised Depth Estimation Based on Camera Models" (2024, 4 citations), tackles a fundamental challenge: eliminating the need for expensive ground-truth depth labels. By leveraging camera model geometry within a self-supervised framework, Reddy’s approach enables robots and vision agents to infer depth directly from unlabeled video streams, dramatically reducing data costs while maintaining robust performance. This contribution is pivotal for advancing real-world applications in navigation, manipulation, and scene understanding, where labeled data is scarce. Though early in his career, Reddy’s work demonstrates a keen ability to bridge theoretical models with practical, scalable solutions—positioning him as a promising voice in the intersection of computer vision and robotics. His research not only lowers barriers to deploying depth-aware systems but also opens new pathways for embodied agents to learn from their environments autonomously.