MASt3R-Nav: WayPixel Navigation in Relative 3D Maps
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910250211213312 |
|---|---|
| author | Garg, Vansh Jayanti, Rohit Pandya, Krish Chittawar, Sarthak Tourani, Siddharth Khan, Muhammad Haris Garg, Sourav Krishna, Madhava |
| author_facet | Garg, Vansh Jayanti, Rohit Pandya, Krish Chittawar, Sarthak Tourani, Siddharth Khan, Muhammad Haris Garg, Sourav Krishna, Madhava |
| contents | Visual navigation ability is strongly tied to its underlying representation of the world. Unlike classical 3D maps that require globally-consistent geometry, image- or object-relative topological graphs almost entirely do away with geometric understanding. But, this comes at the cost of navigation capability, often limiting it to merely teach-and-repeat. In this work, we propose a novel map representation in the form of pixel-relative connectivity, which is geometrically accurate but does not require global geometric consistency. Inspired by recent progress in 3D grounded image matching, we construct a map from an image sequence through inter-image connectivity based on pixel correspondences in the relative 3D coordinate systems of individual image pairs. We then use this pixel-level graph to perform global path planning by approximating and sparsifying intra-image pixel connectivity. Through this, we derive a ''WayPixel Costmap'' representation and train a controller conditioned on it to predict a trajectory rollout. We show that this dense pixel-level costmap based on relative geometry is a more accurate conditioning variable for control prediction than its image- and object-level counterparts. This enables a highly capable navigation system, as validated on four types of navigation tasks in the simulator and through real world demonstrations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_24111 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MASt3R-Nav: WayPixel Navigation in Relative 3D Maps Garg, Vansh Jayanti, Rohit Pandya, Krish Chittawar, Sarthak Tourani, Siddharth Khan, Muhammad Haris Garg, Sourav Krishna, Madhava Robotics Artificial Intelligence Visual navigation ability is strongly tied to its underlying representation of the world. Unlike classical 3D maps that require globally-consistent geometry, image- or object-relative topological graphs almost entirely do away with geometric understanding. But, this comes at the cost of navigation capability, often limiting it to merely teach-and-repeat. In this work, we propose a novel map representation in the form of pixel-relative connectivity, which is geometrically accurate but does not require global geometric consistency. Inspired by recent progress in 3D grounded image matching, we construct a map from an image sequence through inter-image connectivity based on pixel correspondences in the relative 3D coordinate systems of individual image pairs. We then use this pixel-level graph to perform global path planning by approximating and sparsifying intra-image pixel connectivity. Through this, we derive a ''WayPixel Costmap'' representation and train a controller conditioned on it to predict a trajectory rollout. We show that this dense pixel-level costmap based on relative geometry is a more accurate conditioning variable for control prediction than its image- and object-level counterparts. This enables a highly capable navigation system, as validated on four types of navigation tasks in the simulator and through real world demonstrations. |
| title | MASt3R-Nav: WayPixel Navigation in Relative 3D Maps |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2605.24111 |