Skip to content

Using Intel Realsense T265 and D435 to navigate UAV indoor

Notifications You must be signed in to change notification settings

germal/Indoor_Position_Control

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Indoor_Position_Control

Commertials drones uses GPS to navigate which is prone to low accuracy and also do not work Indoor, this project will guide how to fuse Intel realsense T265 /tf ROS topic to px4's /odometry/in topic. Further we will use depth pointcloud information to avoid from Intel Realsense D435 to avoid indoor obstacles during navigation. This could be used in excavation sites for mapping an indoor, warehouse management, disaster management like earthquake and etc.

Objectives for the project

  1. Use Intel T265 to replace GPS on drone to LPS(Local Positioning System).
  2. Avoid obstacle using D435 during navigation.
  3. Map the environment for later use.

Hardware used

  1. Intel Realsense T265 Tracking camera and D435 Depth camera, for more information click here.
  2. Nvidia Jetson Nano for onboard computing, for more information click here.
  3. Pixhawk 4 for fight controller as it supports PX4 firmware and MAVROS, for more information click here.

Prerequisite

  1. Install Jetpack on Nvidia Jetson Nano or Ubuntu 16.04 any other computation board.
  2. Install ROS from here, Mavros from here.
  3. Install Intel Realsense SDK from here. SDK is developed for Jetson Nano which uses its CUDA cores to enhance performance and software FPS of the cameras.

About

Using Intel Realsense T265 and D435 to navigate UAV indoor

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • C++ 51.2%
  • Python 48.8%