Functional scene graph improves robot mapping and pose accuracy
Functional-SLAM: Interaction-Aware Mapping with Online Functional Scene Graphs
Robotics
Summary
Robots need to understand not just where things are but how they relate to each other to interact better. The authors developed Functional-SLAM, a system that builds and updates maps showing these functional relationships as the robot explores in real time. This helps the robot make more accurate guesses about its own location, especially in tricky environments where places look similar or textures are poor. Their approach runs faster than older methods that work only after exploring is done.
What this means in practice
- •For robotics developers: Create robots that maintain detailed maps with functional object relations while exploring unknown environments in real time to aid interaction tasks.
- •For augmented reality engineers: Improve virtual object placement stability by using functional topology in environments with repetitive visual features or low texture quality.
Authors
Xinggang Hu, Chenyangguang Zhang, Zihan Zhu, Ruida Zhang, Xiangkui Zhang, Xiangyang Ji
Abstract
Existing SLAM systems lack modeling of the functional relations required for fine-grained robotic interaction. Functional 3D scene graphs can represent relations between objects and interaction elements, but existing methods rely on offline reconstruction, making them inadequate for real-time interaction in real-world exploration. To address this limitation, we propose Functional-SLAM, the first framework that continuously and recursively maintains a functional scene graph as an online SLAM state. The framework combines anchor-keyframe geometry with functional-context constraints for persistent node maintenance, accumulates multi-frame evidence through temporal relations to commit stable functional edges, and supplements visual loop-closure candidates with functional topology in scenes with repetitive appearance or degraded texture. Experiments show that Functional-SLAM efficiently constructs stable functional maps online, substantially improving runtime over offline methods while maintaining highly competitive accuracy. Compared with peer SLAM systems, it further improves pose estimation accuracy through functional-topology-assisted loop closure. The code is publicly available at https://github.com/Hbelief1998/Functional-SLAM-CoRL_2026.