Ground Vehicle Navigation with Depth Camera and Tracking Camera
Abstract
The aim of this research is to provide autonomous navigation of a 4 wheel vehicle using commercial, oxB;-the-shelf depth and tracking cameras. Some sensitive operations need accuracy within a few inches of navigation ability for indoor or outdoor scenarios where GPS signals are not available. Combination of the Visual Odometry(VO), Distance-Depth(D-D), and Object Detection data from the cameras can be used for accurate navigation and object avoidance. The Intel RealSense D435i, a depth camera, generates depth measurements and the relative position vector of an object. The Intel RealSense T265, a tracking camera, generates its own coordinate system and grabs coordinate goals. Both of them can generate Simultaneous Localization and Mapping (SLAM) data. The cameras share their data to provide a more robust capability. Combining the Intel cameras with a Pixhawk autopilot, it was demonstrated that the vehicle can follow a desired path and avoid objects along that path.
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 01, 2022
- Accession Number
- AD1173775
Entities
People
- Kim Hongseok
Organizations
- Air Force Institute of Technology