Application of artificial neural networks and NEAT algorithm to control a quadcopter

• Autorzy: Przychodzki Mateusz , Niewiadomski Artur

Identyfikatory

DOI

10.34739/si.2023.29.03

• Języki publikacji: EN

Abstrakty

EN

We present a framework for building ArtificialNeuralNetworks (ANNs) able to control a quadcopter and perform basic maneuvers, like hover or following waypoints. In this approach, we make use of the Neuroevolution of Augmenting Topologies (NEAT) algorithm which is aimed at creating the network structure and the weights in result of evolutionary computations. In order to evaluate fitness of individuals, we use physics based, realistic simulation engine Gazebo, where each individual controls a drone in a simulated environment. Our approach is aimed at using one of existing, popular protocols used to remotely control drones, and train ANNs able to imitate signals received from a radio controller operated by a human pilot. Thus, contrary to the most of other approaches, our autonomous controller cooperates with standard drone software. Our ultimate goal is to train ANNs able to control a real-world quadcopter and perform advanced tasks autonomously. Not only such ANNs should be able to perform the maneuvers correctly, but they should be small enough to transfer them into a quadcopter’s limited memory. In this paper we report the first stage of our project - a successful development and deployment of the ANNs distributed training framework, and choosing the activation function for further research.

Słowa kluczowe

EN

artificial neural networks; unmanned aerial vehicles; NEAT algorithm; unity; Gazebo

• Wydawca: Wydawnictwo Uniwersytetu Przyrodniczo-Humanistycznego w Siedlcach
• Czasopismo: Studia Informatica : systems and information technology
• Rocznik: 2023
• Tom: Vol. 2(29)
• Strony: 41--56
• Opis fizyczny: Bibliogr. 46 poz., rys., tab., wykr.

Twórcy

autor

Przychodzki Mateusz

• University of Siedlce, Faculty of Exact and Natural Sciences, Institute of Computer Science, ul. 3 Maja 54, 08-110 Siedlce, Poland

• https://orcid.org/0009-0000-2668-4875

autor

Niewiadomski Artur

• University of Siedlce, Faculty of Exact and Natural Sciences, Institute of Computer Science, ul. 3 Maja 54, 08-110 Siedlce, Poland

• https://orcid.org/0000-0002-9652-5092

Bibliografia

• 1. Przychodzki, M. Zastosowanie sztucznych sieci neuronowych do kontroli bezzałogowych statków powietrznych. (Siedlce University of Natural Sciences,2023,9).
• 2. Rosenblatt, F. Principles of neurodynamics: Perceptions and the theory of brain mechanisms. (Spartan,1962).
• 3. Rumelhart, D., Hinton, G. & Williams, R. Learning representations by back-propagating errors. Nature. 323 pp. 533-536 (1986), https://api.semanticscholar.org/CorpusID:205001834
• 4. Maaloul, B. & Elloumi, S. Adaptive PID Controller of a Quadrotor. 2023 IEEE International Conference On Advanced Systems And Emergent Technologies. pp. 1-6 (2023).
• 5. Tayebi, A. & McGilvray, S. Attitude stabilization of a four-rotor aerial robot. 2004 43rd IEEE Conference On Decision And Control (CDC) (IEEE Cat. No.04CH37601). 2 pp. 1216-1221 Vol.2 (2004).
• 6. MATLABversion 7.10.0 (R2010a). (The MathWorks Inc.,2010).
• 7. Shah, S., Dey, D., Lovett, C. & Kapoor, A. AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles. Field And Service Robotics. (2017), https://arxiv.org/abs/1705.05065
• 8. AlMahamid, F. & Grolinger, K. Autonomous unmanned aerial vehicle navigation using reinforce ment learning: A systematic review. Engineering Applications Of Artificial Intelligence. 115 pp. 105321 (2022).
• 9. Duggal, V., Sukhwani, M., Bipin, K., Reddy, G. & Krishna, K. Plantation monitoring and yield estimation using autonomous quadcopter for precision agriculture.2016IEEEInternational Conference On Robotics And Automation (ICRA). pp. 5121-5127 (2016).
• 10. Patrick, O., Nnadi, E. & Ajaelu, H. Effective use of quadcopter drones for safety and security monitoring in a building construction sites: Case study Enugu Metropolis Nigeria. Journal Of Engineering And Technology Research. 12, 37-46 (2020).
• 11. Mohd Daud, S., Mohd Yusof, M., Heo, C., Khoo, L., Chainchel Singh, M., Mahmood, M. & Nawawi, H. Applications of drone in disaster management: A scoping review. Science And Justice. 62, 30-42 (2022), https://www.sciencedirect.com/science/article/pii/S1355030621001477
• 12. Merkel, D. Docker: lightweight linux containers for consistent development and deployment. Linux Journal. 2014, 2 (2014).
• 13. Lu, P. & Geng, Q. Real-time simulation system for UAV based on Matlab/Simulink. 2011 IEEE 2nd International Conference On Computing, Control And Industrial Engineering. 1 pp. 399-404 (2011).
• 14. Madaan, R., Gyde, N., Vemprala, S., Brown, M., Nagami, K., Taubner, T., Cristofalo, E., Scaramuzza, D., Schwager, M. & Kapoor, A. AirSim Drone Racing Lab. Proceedings Of The NeurIPS 2019 Competition And Demonstration Track. 123 pp. 177-191 (2020,12,8), https://proceedings.mlr.press/v123/madaan20a.html
• 15. González Rodríguez, C. Development and assembly of a cinematography drone. (UPC, Escola Tècnica Superiord’Enginyeria Industrial de Barcelona, Departament d’Enginyeria Electrònica,2019,6), http://hdl.handle.net/2117/165496
• 16. Zhao, H. & Wang, Z. Motion Measurement Using Inertial Sensors, Ultrasonic Sensors, and Magnetometers With Extended Kalman Filter for Data Fusion. IEEE Sensors Journal. 12, 943-953 (2012).
• 17. Bezkorovainyi, Y. & Sushchenko, O. Improvement of UAV Positioning by Information of Inertial Sensors. 2018 IEEE 5th International Conference On Methods And Systems Of Navigation And Motion Control (MSNMC). pp. 123-126 (2018).
• 18. Sun, J. Modeling and analysis of pulse-width modulation. Professional Education Seminar At IEEE Applied Power Electronics Conference, Austin, Texas, USA. (2008).
• 19. Gopalakrishnan, E. Quadcopter flight mechanics model and control algorithms. Czech Technical University. 69 pp. 8-30 (2017).
• 20. Member of Multiwii community- Waltr New MultiwiiSerialProtocol-MultiWii. Www.multiwii.com. (2011), ℎ𝑡𝑡𝑝: 𝑀𝑢𝑙𝑡𝑖𝑤𝑖𝑖𝑆𝑒𝑟𝑖𝑎𝑙𝑃𝑟𝑜𝑡𝑜𝑐𝑜l
• 21. Stanley, K. & Miikkulainen, R. Evolving neural networks through augmenting topologies. Evolutionary Computation. 10, 99-127 (2002).
• 22. Lambora, A., Gupta, K. & Chopra, K. Genetic Algorithm- A Literature Review. 2019 International Conference On Machine Learning, Big Data, Cloud And Parallel Computing (COMITCon). pp. 380-384 (2019).
• 23. Lu, Y., Xue, Z., Xia, G. & Zhang, L. A survey on vision-based UAV navigation. Geo-spatial Information Science. 21, 21-32 (2018).
• 24. O’Shea, K. & Nash, R. An introduction to convolutional neural networks. ArXiv Preprint ArXiv:1511.08458. (2015).
• 25. Boden, M. A guide to recurrent neural networks and backpropagation. The Dallas Project. 2, 1-10 (2002).
• 26. Svozil, D., Kvasnicka, V. & Pospichal, J. Introduction to multi-layer feed-forward neural networks. Chemometrics And Intelligent Laboratory Systems. 39, 43-62 (1997).
• 27. Rady, S., Kandil, A. & Badreddin, E. A hybrid localization approach for UAV in GPS denied areas. 2011 IEEE/SICE International Symposium On System Integration (SII). pp. 1269-1274 (2011).
• 28. Valenti, F., Giaquinto, D., Musto, L., Zinelli, A., Bertozzi, M. & Broggi, A. Enabling Computer Vision-Based Autonomous Navigation for Unmanned Aerial Vehicles in Cluttered GPS-Denied Environments. 2018 21st International Conference On Intelligent Transportation Systems (ITSC). pp. 3886-3891 (2018).
• 29. Burman, P. & Others Quadcopter stabilization with neural network. (2016).
• 30. Meyer,J., Sendobry,A., Kohlbrecher,S.,Klingauf,U. & Von Stryk,O. Comprehensive simulation of quadrotor uavs using ros and gazebo. Simulation, Modeling, And Programming For Autonomous Robots: Third International Conference, SIMPAR 2012, Tsukuba, Japan, November 5-8, 2012. Proceedings 3. pp. 400-411 (2012).
• 31. Zhang, M., Qin, H., Lan, M., Lin, J., Wang, S., Liu, K., Lin, F. & Chen, B. A high fidelity simulator for a quadrotor UAV using ROS and Gazebo. IECON 2015- 41st Annual Conference Of The IEEE Industrial Electronics Society. pp. 002846-002851 (2015).
• 32. Sciortino, C. & Fagiolini, A. ROS/Gazebo-Based Simulation of Quadcopter Aircrafts. 2018 IEEE 4th International Forum On Research And Technology For Society And Industry (RTSI). pp. 1-6 (2018).
• 33. Stanley, K., Clune, J., Lehman, J. & Miikkulainen, R. Designing neural networks through neuroevolution. Nature Machine Intelligence. 1, 24-35 (2019).
• 34. Perez, R., Arnal, J. & Jansen, P. Neuro-Evolutionary Control for Optimal Dynamic Soaring. AIAA Scitech 2020 Forum., https://arc.aiaa.org/doi/abs/10.2514/6.2020-1946
• 35. Kim, E. & Perez, R. Neuroevolutionary Control for Autonomous Soaring. Aerospace. 8 (2021), https://www.mdpi.com/2226-4310/8/9/267
• 36. Betaflight community Betaflight flight software. Betaflight., https://betaflight.com/docs/wiki, [Accessed: 2023].
• 37. Gazebo community Gazebo. Gazebo., https://gazebosim.org/docs, [Accessed: 2023].
• 38. Smith, R. ODE Physic Engine. Open Dynamics Engine., http://ode.org/ode-latest-userguide.html, [Accessed: 2023].
• 39. Osrf What is SDFormat. SDFormat., http://sdformat.org/, [Accessed: 2023].
• 40. OsrfOsrf/vehicleGateway:Apluginlib-basedC++librarythatinterfaceswithseveralvehicleSDK’s. GitHub., ℎ𝑡𝑡𝑝𝑠 : //𝑔𝑖𝑡ℎ𝑢𝑏.𝑐𝑜𝑚/𝑜𝑠𝑟 𝑓/𝑣𝑒ℎ𝑖𝑐𝑙𝑒𝑔𝑎𝑡𝑒𝑤𝑎𝑦, [Accessed: 2023].
• 41. ArduPilot community ArduPilot/ARDUPILOT GAZEBO: Plugins and models for ve hicle simulation in gazebo SIM with Ardupilot SITL controllers. GitHub., ℎ𝑡𝑡𝑝𝑠 : //𝑔𝑖𝑡ℎ𝑢𝑏.𝑐𝑜𝑚/𝐴𝑟𝑑𝑢𝑃𝑖𝑙𝑜𝑡/𝑎𝑟𝑑𝑢𝑝𝑖𝑙𝑜𝑡𝑔𝑎𝑧𝑒𝑏𝑜, [Accessed: 2023].
• 42. Liang, O. RC TX RX Protocols Explained: PWM, PPM, SBUS, DSM2, DSMX, SUMD (2015). Oscarliang.com., https://oscarliang.com/pwm-ppm-sbus-dsm2-dsmx-sumd-difference/, [Accessed: 2023].
• 43. Technologies, U. Unity 3D. Unity3D., https://unity.com/, [Accessed: 2023].
• 44. Green, C. ResharpNEAT libary. GitHub., https://github.com/colgreen/sharpneat, [Accessed: 2023].
• 45. Wolf, F. UnityResharpNEAT libary. GitHub., https://github.com/flo-wolf/UnitySharpNEAT, [Accessed: 2023].
• 46. ALLAIN, R. How Do Drones Fly? Physics, of Course!. Wired., https://www.wired.com/2017/05/the-physics-of-drones/, [Accessed: 2023