Skip to content
RobothecaBeta
Log in

Situational Graphs Reasoning

  • Software
  • Navigation and mapping
  • Library

A ROS2 package that generates semantic concepts such as rooms and walls in real time from wall surfaces, using graph neural networks to estimate relations between them.

  • Stale

Made by Automation and Robotics Research Group (ARG).

Source on GitHub: github.com/snt-arg/situational_graphs_reasoning (opens in a new tab). Facts read at commit e0730d6 (opens in a new tab).

Licenses

Code
GPL-3.0-only (opens in a new tab)

Read by Robotheca from LICENSE (opens in a new tab) (GPL-3.0-only) at commit e0730d6 (opens in a new tab), on 22 Oct 2026.

Commercial use
Yes

Copyleft: Modified source must be published.

Labels

  • StaleNo commit in 12 months: the newest is from 5 Aug 2024.

What it does

  • Builds rooms and walls from wall surfaces produced by S-Graphs, in real time.
  • Uses graph neural networks to estimate the relations between wall surfaces.
  • Publishes room data and wall data for a given floor on ROS2 topics.
  • Subscribes to plane data from S-Graphs, both all map planes and planes from the latest keypoint.
  • Configured through JSON files that set data preprocessing and GNN hyperparameters for rooms and walls.

Written by Robotheca from the project's README (opens in a new tab) at commit e0730d6.

Getting started

Difficulty
Advanced
Hardware it needs, as the project states it
It was tested on Ubuntu 20.04 with ROS2 Foxy and Humble.

Maintenance

Status
Stale: no commit in 12 months
Newest commit
5 Aug 2024 on develop
Latest release
None published on GitHub

Checked on GitHub on 22 Oct 2026.

Links

Robots that can run it

No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.

Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.