Mridul Mahajan
Papers
1
Total Citations
16
H-Index
1
About
Mridul Mahajan is a researcher at the forefront of robotic manipulation and computer vision, with a particular focus on enabling machines to perceive and interact with the physical world more intelligently. His work centers on the critical challenge of robotic grasp detection, where he has pioneered novel approaches to overcome the scarcity of labeled training data—a persistent bottleneck in the field. In his highly cited 2020 paper, "Robotic Grasp Detection By Learning Representation in a Vector Quantized Manifold," Mahajan introduced a semi-supervised learning framework that leverages vector quantization to learn robust feature representations from limited annotations. This work, which has garnered 16 citations, demonstrates how robots can achieve reliable grasping capabilities even when traditional supervised methods fail due to data constraints. By addressing the fundamental problem of data efficiency, Mahajan's contributions have significant implications for deploying autonomous systems in unstructured environments, from manufacturing to service robotics. His research continues to push the boundaries of how machines learn to manipulate objects, making him a promising voice in the intersection of representation learning and embodied AI.
Research Focus
Key Achievements
Top Papers
- 1