ntnu-arl/gbplanner_ros

Graph-based Exploration Planner for Subterranean Environments

What it solves

OmniPlanner (also known as GBPlanner 3.0) provides a unified framework for autonomous robots to explore unknown environments, inspect specific structures or regions of interest, and navigate to targets. It addresses the challenge of creating a single planning system that works across different robot types (morphologies) and operating environments, such as aerial, ground, and underwater platforms.

How it works

It is a unified graph-based planning framework. The system adapts the planning process based on the motion and sensing characteristics of the specific robot being used, allowing it to generate feasible and informative paths for diverse platforms.

Who it’s for

This tool is for robotics researchers and developers working on autonomous exploration, inspection, and navigation in unknown or complex environments across various robot morphologies.

Highlights

  • Unified framework for exploration, inspection, and target-reach planning.
  • Supports aerial, ground, and underwater robots.
  • Modular formulation that adapts to different robot motion and sensing characteristics.
  • Built upon the legacy of GBPlanner 2.0, which was used by Team CERBERUS in the DARPA Subterranean Challenge.

Related

  • Project
    at-wat/neonavigation

    A ROS meta-package for autonomous vehicle navigation providing 2-D/3-DOF path planning, costmap handling, and collision prevention control.

  • Project
    wuyi2121/SCAN-Planner

    A spatial collision-aware local planner for quadruped robots that provides a robust foundation for long-range navigation, autonomous exploration, and obstacle avoidance.

  • Project
    introlab/rtabmap_ros

    A ROS 2 wrapper for RTAB-Map that provides graph-based SLAM with appearance-based loop closure detection for building 3D maps from RGB-D, stereo, or lidar data.

  • Project
    introlab/rtabmap

    RTAB-Map is a robotic mapping and localization library and standalone application used to build maps of unknown environments.

  • Project
    naturerobots/mesh_navigation

    A ROS 2 navigation stack for mobile robots that uses 3D triangle meshes and layered cost maps to enable safe movement across complex, uneven outdoor terrain.