Ahana Datta

Indian Institute of Technology Hyderabad

Papers

Total Citations

H-Index

About

Ahana Datta is a rising star in embodied AI and robot learning, whose work redefines how autonomous agents interact with complex, real-world environments. Her primary research focuses on multi-object navigation, scene understanding, and goal-conditioned policy learning—critical areas for deploying assistive robots in homes and factories. Datta’s most cited paper, “Sequence-Agnostic Multi-Object Navigation” (2023, 9 citations), challenges the conventional approach of treating multi-object tasks as a simple extension of single-object navigation. She introduces a novel framework that enables robots to locate multiple object instances without relying on a fixed visitation sequence, dramatically improving flexibility and robustness in cluttered spaces. This work addresses a fundamental bottleneck in embodied AI: the need for agents to prioritize and adapt to dynamic object configurations. Beyond this, Datta’s contributions have advanced the field’s understanding of how to leverage visual and spatial reasoning for efficient exploration. Her research has already garnered attention for its practical implications, offering a scalable path toward truly autonomous household robots. As a young investigator, Datta is quickly establishing herself as a key voice in the next generation of robotics researchers, bridging the gap between simulation and real-world deployment.