This project integrates DINOv2 visual foundation model features into nvblox 3D maps, enabling semantic understanding of environments beyond simple RGB color. The system processes RGB-D data, extracts ...

While the original course project emphasized semantic mapping, this version restructures and extends the system to improve modularity, maintainability, and autonomy. The codebase has been refactored ...

Abstract: Semantic mapping aims to construct a 3D semantic representation of the environment, providing essential knowledge for robots operating in complex outdoor settings. While Bayesian Kernel ...

Abstract: This paper introduces SLIM-VDB, a new lightweight semantic mapping system with probabilistic semantic fusion for closed-set or open-set dictionaries. Advances in data structures from the ...