Vishnu Sashank Dorbala
Papers
4
Total Citations
80
H-Index
3
About
Vishnu Sashank Dorbala is a leading researcher at the intersection of embodied AI, human-robot interaction, and natural language understanding. His work focuses on enabling robots to navigate complex, unstructured environments by integrating large language models (LLMs) and social cues. Dorbala’s most impactful contribution is the development of **Language-Guided Exploration (LGX)** for zero-shot object navigation, as detailed in his highly cited 2023 paper (70 citations). This algorithm allows an embodied agent to find uniquely described objects—like a “cat-shaped mug”—in unseen spaces without prior training, pushing the boundaries of language-driven robotics. He also pioneered **ProxEmo**, an end-to-end system that predicts pedestrian emotions from gait patterns to enable socially-aware robot navigation, and explored trust dynamics in human-guided navigation using deep reinforcement learning. With a growing citation impact and a knack for tackling fundamental challenges in robot autonomy, Dorbala’s work is shaping how machines perceive, reason, and interact with both their physical and social environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4