Incremental Abstraction in Distributed Probabilistic SLAM Graphs
This work addresses the problem of creating dense, semantic representations in SLAM for robotics applications, but it is incremental as it builds on existing SLAM and graph-based methods.
The paper tackles the challenge of incrementally building compact, semantic scene graphs during SLAM by introducing a distributed framework that uses neural networks to propose abstract scene elements and Gaussian Belief Propagation for efficient inference. It demonstrates significant compression of real indoor datasets by recovering major planes.
Scene graphs represent the key components of a scene in a compact and semantically rich way, but are difficult to build during incremental SLAM operation because of the challenges of robustly identifying abstract scene elements and optimising continually changing, complex graphs. We present a distributed, graph-based SLAM framework for incrementally building scene graphs based on two novel components. First, we propose an incremental abstraction framework in which a neural network proposes abstract scene elements that are incorporated into the factor graph of a feature-based monocular SLAM system. Scene elements are confirmed or rejected through optimisation and incrementally replace the points yielding a more dense, semantic and compact representation. Second, enabled by our novel routing procedure, we use Gaussian Belief Propagation (GBP) for distributed inference on a graph processor. The time per iteration of GBP is structure-agnostic and we demonstrate the speed advantages over direct methods for inference of heterogeneous factor graphs. We run our system on real indoor datasets using planar abstractions and recover the major planes with significant compression.