Go-SLAM: Grounded Object Segmentation and Localization with Gaussian Splatting SLAM
This work addresses the challenge of integrating semantic object understanding into 3D scene reconstruction for real-time robot interactions, representing an incremental step forward in bridging these domains.
The paper tackles the problem of reconstructing dynamic environments with object-level information by introducing Go-SLAM, a framework that uses 3D Gaussian Splatting SLAM to enable open-vocabulary querying and optimal path generation for robots, resulting in high-fidelity reconstructions, precise segmentation, flexible querying, and efficient path planning as demonstrated in evaluations.
We introduce Go-SLAM, a novel framework that utilizes 3D Gaussian Splatting SLAM to reconstruct dynamic environments while embedding object-level information within the scene representations. This framework employs advanced object segmentation techniques, assigning a unique identifier to each Gaussian splat that corresponds to the object it represents. Consequently, our system facilitates open-vocabulary querying, allowing users to locate objects using natural language descriptions. Furthermore, the framework features an optimal path generation module that calculates efficient navigation paths for robots toward queried objects, considering obstacles and environmental uncertainties. Comprehensive evaluations in various scene settings demonstrate the effectiveness of our approach in delivering high-fidelity scene reconstructions, precise object segmentation, flexible object querying, and efficient robot path planning. This work represents an additional step forward in bridging the gap between 3D scene reconstruction, semantic object understanding, and real-time environment interactions.