Subhro Roy
Papers
4
Total Citations
96
H-Index
4
About
Subhro Roy’s research lies at the intersection of robotics, natural language processing, and human-robot interaction, with a focus on enabling robots to understand and execute complex instructions in partially observable, real-world environments. His major contributions center on developing multimodal frameworks that allow robots to estimate and communicate latent semantic knowledge, bridging the gap between ambiguous human language and robust robotic action. Roy’s most-cited work, “Multimodal estimation and communication of latent semantic knowledge for robust execution of robot instructions” (40 citations), introduces methods for robots to infer missing environmental information and ground commands even when world knowledge is incomplete. This is complemented by his influential 2018 paper on grounding robot plans from natural language with incomplete world knowledge (35 citations), which advances semantic reasoning for task execution. His 2022 architecture for grounded language communication with field robots (13 citations) further demonstrates practical deployment in unstructured settings, while his real-time communication system for manipulation tasks (8 citations) highlights his focus on dynamic, partially observed environments. Roy’s work is pivotal for creating resilient, communicative robots that can collaborate seamlessly with humans in challenging field operations.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4