Autonomous Flying Robot

This is the demonstration of autonomous quadrotor developed by me using Robot Operating System (ROS) and Pixhawk Firmware.

This project was completed at the University of Cincinnati as a part of Cooperative Distributed Systems Lab. The objective of the project was to develop a robot to assist first responders in search and rescue missions in the post-disaster scenarios. The robot was designed and developed to fly in the cluttered indoor environment without GPS or any external positioning feedback.

For obstacle avoidance, laser sensors, as well as sonar sensors, were used. The robot was equipped with a camera to do object detection. For object detection, YOLO was used.

Video Links:

• Pixhawk for Quadcopter Waypoint Navigation using External Position Estimation

• Pixhawk Quadrotor Test for Robustness to Disturbance

References:

[1]. Redmon, J., Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767.

[2]. Intel^® Movidius^™ Neural Compute Stick