Skip to content

Dynamic GraphSLAM

Home / Concepts / Dynamic GraphSLAM

Dynamic GraphSLAM

Auto-generated stub. Edit this file to add more details.

A SLAM framework that incorporates socially-aware GNNs for motion forecasting directly into factor graph optimization.

Why It Matters

It provides a way to incorporate stochastic, interaction-aware neural priors directly into SLAM optimization frameworks, moving beyond rigid heuristic motion models in dynamic environments.

Evidence

we propose DynoSLAM, a tightly-coupled Dynamic GraphSLAM architecture that integrates socially-aware Graph Neural Networks (GNNs) directly into the factor graph optimization.

Metadata & Links