Ashwini Pokle
Papers
2
Total Citations
30
H-Index
2
About
Ashwini Pokle’s research sits at the intersection of natural language processing and robotics, with a focus on enabling robots to understand and execute human commands. Her most cited work, co-authored with Xiaoxue Zang and others, introduces an end-to-end deep learning model that translates free-form natural language instructions into high-level behavioral plans for robot navigation. By leveraging attention mechanisms, the model connects user instructions with a topological map of the environment, allowing robots to interpret complex, natural directions and plan actions accordingly. This work, presented at EMNLP 2018, has garnered over 25 citations, reflecting its influence on grounded language understanding and human-robot interaction. Pokle’s contributions are notable for bridging the gap between linguistic abstraction and physical robot behavior, advancing the goal of intuitive, instruction-following autonomous systems. Her research is particularly valuable for students and researchers interested in embodied AI, semantic parsing, and practical deployment of language-guided navigation in real-world settings.
Research Focus
Key Achievements
Top Papers
- 1
- 2