Gitesh Gunjal
Papers
1
Total Citations
7
H-Index
1
About
Gitesh Gunjal is a pioneering researcher at the intersection of robotics, Bayesian inference, and multi-modal perception. His work fundamentally addresses how robots can understand and interact with complex, unstructured environments by fusing sensory data—such as vision and touch—to infer not just what objects are, but how they behave. His most cited paper, “You’ve Got to Feel It To Believe It: Multi-Modal Bayesian Inference for Semantic and Property Prediction” (2024, 7 citations), introduces a novel framework that enables robots to estimate physical properties like friction and weight without relying on massive labeled datasets. This approach overcomes a critical bottleneck in learning-based robotics, where data scarcity often limits real-world deployment. Gunjal’s contributions are particularly impactful for tasks requiring nuanced physical interaction, such as manipulation in challenging environments. His work is gaining traction for its elegant fusion of probabilistic reasoning with multi-sensory inputs, offering a scalable path toward more autonomous and adaptable robots. As a rising voice in embodied AI, Gunjal is shaping how machines perceive and act upon the physical world.
Research Focus
Key Achievements
Top Papers
- 1