Sarthak Sharma

Robotics Research (United States)

Papers

1

Total Citations

2

H-Index

1

About

Sarthak Sharma is a robotics researcher whose work centers on advancing LiDAR-based perception and loop closure detection for mobile robots operating in complex, six-degree-of-freedom environments. His most cited paper, "FinderNet," introduces a novel, data-augmentation-free approach to canonicalization for point cloud loop detection and closure, directly addressing the fragility of state-of-the-art methods under wide viewpoint variations. By eliminating the need for extensive data augmentation, Sharma’s contribution enhances robustness and generalization in real-world robotic navigation, a critical step toward reliable autonomous systems. Though early in its impact, this work has already garnered citations from peers in robotics and computer vision, signaling its relevance to the field. Sharma’s research bridges the gap between theoretical embedding learning and practical deployment, offering a streamlined solution for 6-DOF separation challenges. His focus on canonicalization without augmentation marks a notable departure from conventional techniques, positioning him as an emerging voice in efficient, scalable perception for mobile robotics.

Research Focus

Key Achievements

1
H-Index
1
Papers
2
Total Citations
2
Avg Citations/Paper
🏆 Most Cited Paper
FinderNet: A Data Augmentation Free Canonicalization aided Loop Detection and Closure technique for Point clouds in 6-DOF separation
2 citations · 2024
📈 Most Prolific Year: 2024 (1 Papers)
🤝 Key Collaborators: 6
🏛 Institutions: Robotics Research (United States)

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago