Skip to content

Semantic-aware navigation in ROS 2 using vision-based perception.

Notifications You must be signed in to change notification settings

saumyaezhil/Semantic-Aware-Navigation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Semantic-Aware-Navigation

This project implements a semantic-aware navigation system in ROS 2.
Instead of treating the environment as just obstacles and free space, the robot also understands what it is seeing (for example walls, floor, objects) and uses that information while navigating.

The system combines:

  • Gazebo simulation
  • Nav2 for navigation
  • A semantic segmentation node
  • Projection of semantic labels into the navigation costmap

This allows the robot to avoid certain types of regions (like obstacles or restricted zones) more intelligently than standard navigation.

What it contains

  • A custom Gazebo world and robot model
  • ROS 2 nodes for semantic segmentation and visualization
  • A semantic costmap layer that affects path planning
  • A launch file to run the full pipeline

---- in progress ----

About

Semantic-aware navigation in ROS 2 using vision-based perception.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages