Nishant Shukla
University of California, Los Angeles, University of Virginia
Papers
6
Total Citations
201
H-Index
5
About
Nishant Shukla is a leading researcher at the intersection of machine learning, robotics, and human-robot interaction. His work focuses on enabling robots to learn complex tasks from human demonstrations, natural language instructions, and visual input. Shukla’s major contributions include developing a unified And-Or Graph (AoG) framework that integrates spatial, temporal, and causal reasoning for robot task learning and planning. This approach allows robots to acquire hierarchical task structures from both language and visual demonstrations, bridging the gap between symbolic reasoning and sensory data. His book, *Machine Learning with TensorFlow* (2018), with 92 citations, has become a foundational resource for practitioners, providing hands-on coding experience with one of the most popular ML frameworks. Shukla’s research on joint learning from language instruction and visual demonstration (42 citations) and robot learning with AoG (49 citations) has significantly advanced the field of cognitive robotics. His work on human-robot knowledge transfer and deductive planning from video demonstrations further demonstrates his commitment to creating robots that can continuously learn and collaborate with humans. With over 200 total citations, Shukla’s contributions are shaping the future of intelligent, interactive robotic systems.
Research Focus
Key Achievements
Top Papers
- 1Machine Learning with TensorFlow92 citations · 2018
- 2Robot learning with a spatial, temporal, and causal and-or graph49 citations · 2016
- 3
- 4Task Learning through Visual Demonstration and Situated Dialogue.7 citations · 2016
- 5
- 6A Unified Framework for Human-Robot Knowledge Transfer.5 citations · 2015