Presentation Title

Autonomous Collision Avoidance System for Unmanned Aerial Systems using Stereoscopic Vision

Faculty Mentor

Subodh Bhandari

Start Date

18-11-2017 9:45 AM

End Date

18-11-2017 10:00 AM

Location

9-245

Session

Engineering/CS 2

Type of Presentation

Oral Talk

Subject Area

engineering_computer_science

Abstract

This presentation discusses the use of stereoscopic vision as a means of sensing and detecting obstacles and other aircraft for collision avoidance systems for small unmanned aerial systems (UASs). The importance of this research has become increasingly significant as the presence of UASs in commercial and private sectors has led to stricter FAA regulations. Implementing collision avoidance systems can help integrate UASs more seamlessly into the National Airspace System with fewer safety concerns and fewer financial burdens. Stereoscopic vision provides a cheaper and more lightweight solution for collision detection. The project uses a Zed stereo camera that is mounted on a DJI S900 Hexacopter unmanned aerial vehicle (UAV) to generate depth maps. A NVIDIA Jetson TX1 board is used for onboard processing of the depth maps and obstacle avoidance. The board communicates with the PixHawk 3DR autopilot module, which transmits data to the ground control station via XBee radios. By using the Zed SDK, it is possible to obtain depth maps directly from the camera and use them in the implementation of obstacle avoidance. The algorithm that is used will partition the depth map into multiple sections, allowing it to find the section of the image that has pixels which represent objects furthest away. In other words this section should be obstacle free. From here, the UAV can maneuver in the direction of the selected section of the depth map, allowing it to avoid any obstacles in its path.

Summary of research results to be presented

Our system has been tested multiple times for verification of the computer algorithm. During the manual flight tests, we have verified that the correct quadrants are selected and response time is around 10 decision a second. Furthermore, the Zed camera has allowed for clear visualization of obstacles during these flight tests where specific objects are very distinguishable. In the flight test data, the system's images has shown that the system can see details such as trees, other UAVs, and ground vehicles. This has allowed us to verify that we are able to advanced to implementing the autonomous navigation of the system by using only waypoint input from the user.

This document is currently not available here.

Share

COinS
 
Nov 18th, 9:45 AM Nov 18th, 10:00 AM

Autonomous Collision Avoidance System for Unmanned Aerial Systems using Stereoscopic Vision

9-245

This presentation discusses the use of stereoscopic vision as a means of sensing and detecting obstacles and other aircraft for collision avoidance systems for small unmanned aerial systems (UASs). The importance of this research has become increasingly significant as the presence of UASs in commercial and private sectors has led to stricter FAA regulations. Implementing collision avoidance systems can help integrate UASs more seamlessly into the National Airspace System with fewer safety concerns and fewer financial burdens. Stereoscopic vision provides a cheaper and more lightweight solution for collision detection. The project uses a Zed stereo camera that is mounted on a DJI S900 Hexacopter unmanned aerial vehicle (UAV) to generate depth maps. A NVIDIA Jetson TX1 board is used for onboard processing of the depth maps and obstacle avoidance. The board communicates with the PixHawk 3DR autopilot module, which transmits data to the ground control station via XBee radios. By using the Zed SDK, it is possible to obtain depth maps directly from the camera and use them in the implementation of obstacle avoidance. The algorithm that is used will partition the depth map into multiple sections, allowing it to find the section of the image that has pixels which represent objects furthest away. In other words this section should be obstacle free. From here, the UAV can maneuver in the direction of the selected section of the depth map, allowing it to avoid any obstacles in its path.