Kautilya Chenna
Papers
2
Total Citations
82
H-Index
2
About
Kautilya Chenna is a roboticist whose work lies at the intersection of dexterous manipulation, deep learning, and probabilistic inference. His primary research focus is on enabling robots to perform complex, multi-fingered grasps—a critical capability for tasks requiring precision and adaptability. Chenna’s major contribution is a novel framework that reframes grasp planning as a probabilistic inference problem within a learned deep network. By training a convolutional neural network to predict grasp success from both visual object features and grasp configurations, his approach allows robots to efficiently infer optimal hand poses in high-dimensional spaces. This work, published in 2018 and 2019, has garnered over 80 combined citations, underscoring its influence in the manipulation community. Chenna’s methodology bridges the gap between data-driven perception and classical planning, offering a scalable solution for dexterous hands. His research is particularly notable for its practical implications in manufacturing, assistive robotics, and autonomous systems, where reliable grasping remains a foundational challenge. Through this synthesis of deep learning and probabilistic reasoning, Chenna is shaping the next generation of robotic manipulation.
Research Focus
Key Achievements
Top Papers
- 1
- 2