Hiloni Mehta

Papers

Total Citations

H-Index

About

Hiloni Mehta is a rising researcher at the intersection of natural language processing and robotics, with a primary focus on enabling robots to understand and execute complex commands expressed in everyday language. Her most influential work, "Generalizing to New Domains by Mapping Natural Language to Lifted LTL" (2022, 13 citations), addresses a critical bottleneck in human-robot interaction: the challenge of grounding open-ended natural language instructions into formal, verifiable task specifications like Linear Temporal Logic (LTL). Mehta’s key contribution lies in developing methods that allow language models to generalize beyond limited vocabularies, moving from finite probability distributions to more flexible, lifted representations. This work is foundational for creating robots that can adapt to novel environments and tasks without exhaustive retraining. By bridging the gap between the ambiguity of human language and the precision required for robot control, Mehta is helping to make autonomous systems more accessible and robust. Her research holds significant promise for applications in service robotics, manufacturing, and assistive technologies, where intuitive communication is paramount.