Pradyumna Dasu

Indian Institute of Technology Hyderabad

Papers

Total Citations

H-Index

About

Pradyumna Dasu is a robotics researcher whose work focuses on advancing autonomous navigation through topological mapping and simultaneous localization and mapping (SLAM). His most notable contribution is the development of a hierarchical unsupervised topological SLAM framework, which enables mobile robots to autonomously cluster their visual traversals into meaningful topologies without human-labeled data. This approach significantly improves loop detection and closure—a critical challenge in long-term robot navigation—by grouping visually similar images into coherent spatial clusters. Though early in his career, Dasu’s work has already garnered attention for its novel integration of unsupervised learning with topological mapping, offering a scalable solution for robots operating in unstructured environments. His research sits at the intersection of computer vision, machine learning, and robotics, with potential applications in autonomous exploration, search-and-rescue, and industrial inspection. As a researcher pushing the boundaries of unsupervised spatial reasoning, Dasu’s contributions are laying the groundwork for more adaptive and self-sufficient robotic systems capable of navigating complex, real-world spaces with minimal human intervention.