COMPUTER VISION BASED SYSTEM FOR AUTONOMOUS TAXIING OF AIRCRAFT

Prashant Gaikwat, Abhishek Mukhopadhyay, Anujith Muraleedharan, Mukund Mitra, Pradipta Biswas

Indian Institute of Science, Bengaluru

AVIATION Journal Vol 27 No 4 (2023)

Implementation

For running the project, one system is used to run ROS to control the robot based on the control signal received, which is the result from the lane and object detection model on an external GPU.

Initialization

Connect to the robot via SSH and run the following commands:

rosrun tankbot_scripts differential_tank.py
rosrun lightDetection tst_server.py

On the GPU:

Run the following script inside the Deployment scripts folder:

python wheel_control_generation.py

Joystick Key Inputs Detection

After the above steps, in the ROS system, run:

rosrun lightDetection turtlebot3_pointop_key

On the GPU:

Run:

python fusedControl_v1.py

Final Step in ROS:

rosrun lightDetection autoUI.py

Model checkpoint

Please copy the resources folder to the Deployment Scripts folder in the repository.

🎥 Video Demonstration

For a video demonstration of the project, visit the webpage here.

BibTeX Citation

If you find our work useful, please consider citing us!

@article{Gaikwad2023,
    title={Developing a computer vision based system for autonomous taxiing of aircraft},
    author={Gaikwad, P. and Mukhopadhyay, A. and Muraleedharan, A. and Mitra, M. and Biswas, P.},
    journal={Aviation},
    volume={27},
    number={4},
    pages={248--258},
    year={2023},
    month={Dec},
    doi={10.3846/aviation.2023.20588}
}

Acknowledgments

Parts of this project page were adopted from the Nerfies page.

Website License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.