Sitemap
A list of the pages and collections found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
publications
Towards Global Localization using Multi-Modal Object-Instance Re-Identification
Published in Advances in Robotics (AIR) - Oral, 2025
We propose a dual-path object-instance re-identification transformer that integrates RGB and depth information for robust object ReID and camera localization across varying viewpoints and environments.
Recommended citation: Aneesh Chavan, Vaibhav Agrawal, Vineeth Bhat, Sarthak Chittawar, Siddharth Srivastava, Chetan Arora, K. Madhava Krishna. (2025). "Towards Global Localization using Multi-Modal Object-Instance Re-Identification." Proceedings of the 2025 Advances in Robotics (Oral).
Download Paper
MASt3R-Nav: WayPixel Navigation in Relative 3D Maps
Published in IEEE International Conference on Robotics and Automation (ICRA), 2026
We introduce WayPixel navigation, a pixel-relative topological map representation that enables geometrically grounded navigation without requiring globally consistent metric maps.
Recommended citation: Vansh Garg, Rohit Jayanti, Krish Pandya, Sarthak Chittawar, Siddharth Tourani, Muhammad Haris Khan, Sourav Garg, K. Madhava Krishna. (2026). "MASt3R-Nav: WayPixel Navigation in Relative 3D Maps." Proceedings of the 2026 IEEE International Conference on Robotics and Automation.
Download Paper
PixelLoop: Shortcut Topological Navigation with Pixel-Level Loops
Published in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026
PixelLoop augments pixel-relative topological maps with loop closures, enabling shortcut navigation and improved planning efficiency in large-scale environments.
Recommended citation: Sarthak Chittawar, Vansh Garg, Aditya Vadali, Krish Pandya, Rohit Jayanti, Sourav Garg, K. Madhava Krishna. (2026). "PixelLoop: Shortcut Topological Navigation with Pixel-Level Loops." IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026).
Download Paper