-
Notifications
You must be signed in to change notification settings - Fork 17
Home
The frontier-based exploration planner is capable of autonomously exploring a previously unknown area, creating an occupancy grid map using Cartographer SLAM and generating an OctoMap. The planner does not require any prior knowledge of the environment, except for boundaries of the area to be explored. The planner may be applied to both indoor and outdoor environments.
It ensures frontiers detection, clustering and selection of the best frontier (a new target point). In each iteration, map and OctoMap are updated. Frontiers are clustered and a new target point is selected only when the prevoius target is reached. A robust frontier detection speeds up the exploration process, while a clustering algorithm ensures target evaluation in the real time.
The best frontier point to be visited is determined by estimating the benefit of the information gathered by visiting a candidate frontier point. The exploration loop is closed with an autonomous navigation to the selected frontier point, using the map generated through the exploration for trajectory planning and localization. Furthermore, the planner maintains a occupancy map of the environment. This guarantees that paths are only planned within free space, while giving a notion on exploration progress.
- Installation Instructions
- Parameters and Topics
- Launching the Exploration Planner
- Visualization
- Demo Scenario
This algorithm was developed by Ana Batinovic with the help and support of the members of the LARICS.