Sundara Tejaswi Digumarti

University of Oxford, The University of Sydney

Papers

5

Total Citations

44

H-Index

4

About

Sundara Tejaswi Digumarti is a robotics researcher whose work bridges perception, navigation, and manipulation, with a focus on enabling autonomous systems to operate reliably in complex, real-world environments. His contributions span three key areas: multi-agent coordination, 3D scene understanding, and robotic grasping. In multi-agent robotics, his work on bearing-only rendezvous (12 citations) provided a foundational algorithm for mobile agents to meet using limited sensing, a critical capability for swarm robotics. For navigation, he developed InstaLoc (8 citations), a one-shot lidar localization method inspired by human spatial reasoning, and a learning-aided 3D lidar reconstruction pipeline (11 citations) that probabilistically completes sparse depth data for safer motion planning. In manipulation, his Fast-Learning Grasping framework (10 citations) integrates pre-grasping actions like pushing with deep reinforcement learning to efficiently handle clutter. Digumarti has also advanced unsupervised learning techniques for novel sensors, applying them to depth estimation and visual odometry for sparse light field cameras. His work consistently addresses practical challenges in robotics—from localizing a robot with a single lidar scan to grasping objects in messy scenes—making his research highly relevant for students and engineers building robust autonomous systems.

Research Focus

Key Achievements

4
H-Index
5
Papers
44
Total Citations
9
Avg Citations/Paper
🏆 Most Cited Paper
Rendezvous with bearing-only information and limited sensing range
12 citations · 2015
📈 Most Prolific Year: 2021 (2 Papers)
🤝 Key Collaborators: 18
🏛 Institutions: University of Oxford, The University of Sydney

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4
  5. 5

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 14 days ago