Papers
10
Total Citations
104
H-Index
5
About
Priya Shukla is a roboticist whose research lies at the intersection of intelligent grasping, computer vision, and machine learning. Her core work addresses one of robotics' most fundamental challenges: enabling robots to dexterously manipulate objects in unstructured environments. Shukla is a pioneer in applying deep reinforcement learning and evolutionary computing to robotic grasp manipulation, as demonstrated in her most-cited paper (26 citations), which fuses these techniques for robust grasp synthesis. She has also advanced semi-supervised and generative approaches to overcome the critical bottleneck of limited labeled training data, notably through generative models for grasp pose prediction (24 citations) and representation learning in vector-quantized manifolds (16 citations). Her work on generating quality grasp rectangles using Pix2Pix GANs (14 citations) further showcases her innovative use of generative adversarial networks for robotic perception. Shukla’s research has collectively garnered over 100 citations, reflecting its growing influence. She has also explored behavior-based manipulation using actor-critic architectures and context-aware 6D pose estimation, broadening her impact from fundamental grasp detection to full manipulation pipelines. Her contributions are essential reading for anyone working toward more capable, learning-driven robotic hands.
Research Focus
Key Achievements
Top Papers
- 1
- 2Generative model based robotic grasp pose prediction with limited dataset24 citations · 2022
- 3
- 4
- 5
- 6Robotized Grasp: Grasp manipulation using Evolutionary Computing5 citations · 2019
- 7Context-aware 6D pose estimation of known objects using RGB-D data4 citations · 2023
- 8
- 9Vision-based intelligent robot grasping using sparse neural network2 citations · 2025
- 10