FutureMapping 2: Gaussian Belief Propagation for Spatial AI
This work addresses the need for efficient probabilistic estimation in Spatial AI for smart robots and devices, but it is incremental as it focuses on applying an existing method (GBP) to this domain.
The paper argues that Gaussian Belief Propagation (GBP) is a suitable algorithmic framework for distributed, generic, and incremental probabilistic estimation in Spatial AI, aiming to enable high-performance smart robots and devices under real-world constraints, and provides a tutorial with simulation examples and code to demonstrate its properties.
We argue the case for Gaussian Belief Propagation (GBP) as a strong algorithmic framework for the distributed, generic and incremental probabilistic estimation we need in Spatial AI as we aim at high performance smart robots and devices which operate within the constraints of real products. Processor hardware is changing rapidly, and GBP has the right character to take advantage of highly distributed processing and storage while estimating global quantities, as well as great flexibility. We present a detailed tutorial on GBP, relating to the standard factor graph formulation used in robotics and computer vision, and give several simulation examples with code which demonstrate its properties.