Advertisement

Autonomous Robots

, Volume 43, Issue 8, pp 2209–2228 | Cite as

A constrained instantaneous learning approach for aerial package delivery robots: onboard implementation and experimental results

  • Mohit Mehndiratta
  • Erdal KayacanEmail author
Article
  • 204 Downloads

Abstract

Rather than utilizing a sophisticated robot which is trained—and tuned—for a scenario in a specific environment perfectly, most people are interested in seeing robots operating in various conditions where they have never been trained before. In accordance with the goal of utilizing aerial robots for daily operations in real application scenarios, an aerial robot must learn from its own experience and its interactions with the environment. This paper presents an instantaneous learning-based control approach for the precise trajectory tracking of a 3D-printed aerial robot which can adapt itself to the changing working conditions. Considering the fact that model-based controllers suffer from lack of modeling, parameter variations and disturbances in their working environment, we observe that the presented learning-based control method has a compelling ability to significantly reduce the tracking error under aforementioned uncertainties throughout the operation. Three case scenarios are considered: payload mass variations on an aerial robot for a package delivery problem, ground effect when the aerial robot is hovering/flying close to the ground, and wind-gust disturbances encountered in the outdoor environment. In each case study, parameter variations are learned using nonlinear moving horizon estimation (NMHE) method, and the estimated parameters are fed to the nonlinear model predictive controller (NMPC). Thanks to learning capability of the presented framework, the aerial robot can learn from its own experience, and react promptly—unlike iterative learning control which allows the system to improve tracking accuracy from repetition to repetition—to reduce the tracking error. Additionally, the fast C++ execution of NMPC and NMHE codes facilitates a complete onboard implementation of the proposed framework on a low-cost embedded processor.

Keywords

Instantaneous learning Learning-based NMPC NMPC–NMHE framework Unmanned aerial vehicle Tilt-rotor tricopter Package delivery Ground effect Wind-gust disturbance 

Notes

Acknowledgements

This work was equally financially supported by the National Research Foundation, Prime Minister’s Office, Singapore under its Medium-Sized Centre funding scheme, and the Aarhus University, Department of Engineering (28173). In addition, the authors would like to acknowledge Siddharth Patel, Lee Ying Jun Wilson and Suraj Ravindrababu for their support during the real-time experiments.

Supplementary material

Supplementary material 1 (mp4 22649 KB)

References

  1. Albersmeyer, J., & Diehl, M. (2010). The lifted newton method and its application in optimization. SIAM Journal on Optimization, 20(3), 1655–1684.  https://doi.org/10.1137/080724885.MathSciNetCrossRefzbMATHGoogle Scholar
  2. Alexis, K., Nikolakopoulos, G., & Tzes, A. (2011). Switching model predictive attitude control for a quadrotor helicopter subject to atmospheric disturbances. Control Engineering Practice, 19(10), 1195–1207.  https://doi.org/10.1016/j.conengprac.2011.06.010.CrossRefGoogle Scholar
  3. Alexis, K., Papachristos, C., Siegwart, R., & Tzes, A. (2016). Robust model predictive flight control of unmanned rotorcrafts. Journal of Intelligent & Robotic Systems, 81(3), 443–469.CrossRefGoogle Scholar
  4. Amazon. (2017). Amazon prime air. https://www.amazon.com/Amazon-Prime-Air/b?node=8037720011, [Accessed September 4, 2017]
  5. Ariens, D., Houska, B., Ferreau, H., & Logist, F. (2010). ACADO: Toolkit for automatic control and dynamic optimization. Optimization in Engineering Center (OPTEC), 1st edn, http://www.acadotoolkit.org/, [Accessed June 28, 2019]
  6. Ataka, A., Tnunay, H., Inovan, R., Abdurrohman, M., Preastianto, H., Cahyadi, A. I., & Yamamoto, Y. (2013). Controllability and observability analysis of the gain scheduling based linearization for UAV quadrotor. In: 2013 International conference on robotics, biomimetics, intelligent computational systems, pp. 212–218,  https://doi.org/10.1109/ROBIONETICS.2013.6743606
  7. Bemporad, A., Pascucci, C., & Rocchi, C. (2009). Hierarchical and hybrid model predictive control of quadcopter air vehicles. In: IFAC Proceedings volumes, 3rd IFAC conference on analysis and design of hybrid systems, Vol. 42(17), pp. 14–19.  https://doi.org/10.3182/20090916-3-ES-3003.00004, http://www.sciencedirect.com/science/article/pii/S1474667015307308.CrossRefGoogle Scholar
  8. Bircher, A., Kamel, M., Alexis, K., Oleynikova, H., & Siegwart, R. (2016). Receding horizon “next-best-view” planner for 3D exploration. In: 2016 IEEE international conference on robotics and automation (ICRA), pp. 1462–1468,  https://doi.org/10.1109/ICRA.2016.7487281.
  9. Bouabdallah, S. (2007). Design and control of quadrotors with application to autonomous flying. Ph.D. Dissertation, EPFL.Google Scholar
  10. Bouabdallah, S., Noth, A., & Siegwart, R. (2004). PID vs LQ control techniques applied to an indoor micro quadrotor. In: 2004 IEEE/RSJ international conference on intelligent robots and systems (IROS) (IEEE Cat. No.04CH37566), Vol.  3, pp. 2451–2456.Google Scholar
  11. Bouffard, P., Aswani, A., & Tomlin, C. (2012). Learning-based model predictive control on a quadrotor: Onboard implementation and experimental results. In: 2012 IEEE international conference on robotics and automation (ICRA), pp. 279–284,  https://doi.org/10.1109/ICRA.2012.6225035.
  12. Cao, G., Lai, E. M. K., & Alam, F. (2016). Gaussian process model predictive control of unmanned quadrotors. In: 2016 2nd International conference on control, automation and robotics (ICCAR), pp. 200–206,  https://doi.org/10.1109/ICCAR.2016.7486726.
  13. Chen, J., Liu, H., Zheng, J., Lv, M., Yan, B., Hu, X., & Gao, Y. (2016). Damage degree evaluation of earthquake area using UAV aerial image. International Journal of Aerospace Engineering, 2016, 2052603.  https://doi.org/10.1155/2016/2052603.Google Scholar
  14. Chowdhary, G., Mühlegg, M., How, J. P., & Holzapfel, F. (2013a). Concurrent learning adaptive model predictive control (pp. 29–47). Berlin: Springer.  https://doi.org/10.1007/978-3-642-38253-6_3.CrossRefGoogle Scholar
  15. Chowdhary, G., Mühlegg, M., How, J. P., & Holzapfel, F. (2013b). A concurrent learning adaptive-optimal control architecture for nonlinear systems. In: 52nd IEEE conference on decision and control, pp. 868–873,  https://doi.org/10.1109/CDC.2013.6759991.
  16. Dentler, J., Kannan, S., Bezzaoucha, S., Olivares-Mendez, M. A., & Voos, H. (2018). Model predictive cooperative localization control of multiple uavs using potential function sensor constraints. Autonomous Robots,.  https://doi.org/10.1007/s10514-018-9711-z.CrossRefGoogle Scholar
  17. Diehl, M., Bock, H., Schlöder, J. P., Findeisen, R., Nagy, Z., & Allgöwer, F. (2002). Real-time optimization and nonlinear model predictive control of processes governed by differential-algebraic equations. Journal of Process Control, 12(4), 577–585.  https://doi.org/10.1016/S0959-1524(01)00023-3.CrossRefGoogle Scholar
  18. Diehl, M., Uslu, I., Findeisen, R., Schwarzkopf, S., Allgöwer, F., Bock, H. G., et al. (2001). Real-time optimization for large scale processes: Nonlinear model predictive control of a high purity distillation column (pp. 363–383). Berlin: Springer.  https://doi.org/10.1007/978-3-662-04331-8_20.CrossRefzbMATHGoogle Scholar
  19. Eren, U., Prach, A., Koçer, B. B., Raković, S. V., Kayacan, E., & Açıkmeşe, B. (2017). Model predictive control in aerospace systems: Current state and opportunities. Journal of Guidance, Control, and Dynamics, 40(7), 1541–1566.  https://doi.org/10.2514/1.G002507.CrossRefGoogle Scholar
  20. Garcia, G. A., & Keshmiri, S. (2013). Online artificial neural network model-based nonlinear model predictive controller for the Meridian UAS. International Journal of Robust and Nonlinear Control, 23(15), 1657–1681.  https://doi.org/10.1002/rnc.3037.MathSciNetCrossRefzbMATHGoogle Scholar
  21. Garimella, G., & Kobilarov, M. (2015). Towards model-predictive control for aerial pick-and-place. In: 2015 IEEE international conference on robotics and automation (ICRA), pp. 4692–4697,  https://doi.org/10.1109/ICRA.2015.7139850.
  22. Grúne, L. (2012). NMPC without terminal constraints. IFAC Proceedings Volumes, 45(17), 1–13.CrossRefGoogle Scholar
  23. Kayacan, E., Kayacan, E., Ramon, H., & Saeys, W. (2014a). Distributed nonlinear model predictive control of an autonomous tractor-trailer system. Mechatronics, 24(8), 926–933.CrossRefGoogle Scholar
  24. Kayacan, E., Kayacan, E., Ramon, H., & Saeys, W. (2014b). Nonlinear modeling and identification of an autonomous tractor-trailer system. Computers and Electronics in Agriculture, 106, 1–10.  https://doi.org/10.1016/j.compag.2014.05.002.CrossRefGoogle Scholar
  25. Kayacan, E., Kayacan, E., Ramon, H., & Saeys, W. (2015a). Learning in centralized nonlinear model predictive control: Application to an autonomous tractor-trailer system. IEEE Transactions on Control Systems Technology, 23(1), 197–205.CrossRefGoogle Scholar
  26. Kayacan, E., Kayacan, E., Ramon, H., & Saeys, W. (2015b). Towards agrobots: Identification of the yaw dynamics and trajectory tracking of an autonomous tractor. Computers and Electronics in Agriculture, 115, 78–87.CrossRefGoogle Scholar
  27. Kayacan, E., Peschel, J. M., & Kayacan, E. (2016). Centralized, decentralized and distributed nonlinear model predictive control of a tractor-trailer system: A comparative study. In: 2016 American control conference (ACC), pp. 4403–4408,  https://doi.org/10.1109/ACC.2016.7525615.
  28. Kraus, T., Ferreau, H., Kayacan, E., Ramon, H., Baerdemaeker, J. D., Diehl, M., et al. (2013). Moving horizon estimation and nonlinear model predictive control for autonomous agricultural vehicles. Computers and Electronics in Agriculture, 98, 25–33.CrossRefGoogle Scholar
  29. Kühl, P., Diehl, M., Kraus, T., Schlöder, J. P., & Bock, H. G. (2011). A real-time algorithm for moving horizon state and parameter estimation. Computers & Chemical Engineering, 35(1), 71–83.CrossRefGoogle Scholar
  30. Lee, W. Y. J., Mehndiratta, M., & Kayacan, E. (2018). Fly without borders with additive manufacturing: A microscale tilt-rotor tricopter design. In: Proceedings of the 3rd international conference on progress in additive manufacturing (Pro-AM 2018), pp. 256–261,  https://doi.org/10.25341/D43K5G.
  31. Li, B., Zhou, W., Sun, J., Wen, C., & Chen, C. (2018). Model predictive control for path tracking of a VTOL tailsitter UAV in an HIL simulation environment. In: 2018 AIAA modeling and simulation technologies conference, American Institute of Aeronautics and Astronautics, p. 1919.Google Scholar
  32. Mayne, D., Rawlings, J., Rao, C., & Scokaert, P. (2000). Constrained model predictive control: Stability and optimality. Automatica, 36(6), 789–814.MathSciNetCrossRefGoogle Scholar
  33. Mehndiratta, M., & Kayacan, E. (2017). Receding horizon control of a 3 DOF helicopter using online estimation of aerodynamic parameters. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering,.  https://doi.org/10.1177/0954410017703414.CrossRefGoogle Scholar
  34. Mehndiratta, M., & Kayacan, E. (2018a). Online learning-based receding horizon control of tilt-rotor tricopter: A cascade implementation. In: 2018 American control conference (ACC), pp. 1–6.Google Scholar
  35. Mehndiratta, M., & Kayacan, E. (2018b). Reconfigurable fault-tolerant nmpc for y6 coaxial tricopter with complete loss of one rotor. In: 2018 IEEE conference on control technology and applications (CCTA), pp. 774–780,  https://doi.org/10.1109/CCTA.2018.8511444.
  36. Mehndiratta, M., Kayacan, E., & Kayacan, E. (2018). A simple learning strategy for feedback linearization control of aerial package delivery robot. In: 2018 IEEE conference on control technology and applications (CCTA), pp. 361–367,  https://doi.org/10.1109/CCTA.2018.8511485.
  37. Mehndiratta, M., Kayacan, E., Patel, S., Kayacan, E., & Chowdhary, G. (2019). Learning-based fast nonlinear model predictive control for custom-made 3D printed ground and aerial robots. Control Engineering,.  https://doi.org/10.1007/978-3-319-77489-3.MathSciNetCrossRefGoogle Scholar
  38. Mellinger, D., Lindsey, Q., Shomin, M., & Kumar, V. (2011). Design, modeling, estimation and control for aerial grasping and manipulation. In: 2011 IEEE/RSJ international conference on intelligent robots and systems, pp. 2668–2673,  https://doi.org/10.1109/IROS.2011.6094871.
  39. Mellinger, D., Michael, N., & Kumar, V. (2012). Trajectory generation and control for precise aggressive maneuvers with quadrotors. The International Journal of Robotics Research, 31(5), 664–674.  https://doi.org/10.1177/0278364911434236.CrossRefGoogle Scholar
  40. Nicolao, G. D., Magni, L., & Scattolini, R. (1998). Stabilizing receding-horizon control of nonlinear time-varying systems. IEEE Transactions on Automatic Control, 43(7), 1030–1036.MathSciNetCrossRefGoogle Scholar
  41. Ostafew, C. J., Schoellig, A. P., Barfoot, T. D., & Collier, J. (2016). Learning-based nonlinear model predictive control to improve vision-based mobile robot path tracking. Journal of Field Robotics, 33(1), 133–152.  https://doi.org/10.1002/rob.21587.CrossRefGoogle Scholar
  42. Prach, A., & Kayacan, E. (2017). An MPC-based position controller for a tilt-rotor tricopter VTOL UAV. Optimal Control Applications and Methods,.  https://doi.org/10.1002/oca.2350.CrossRefzbMATHGoogle Scholar
  43. Qi, J., Song, D., Shang, H., Wang, N., Hua, C., Wu, C., et al. (2016). Search and rescue rotary-wing UAV and its application to the Lushan Ms 7.0 earthquake. Journal of Field Robotics, 33(3), 290–321.CrossRefGoogle Scholar
  44. Rajappa, S., Bülthoff, H., & Stegagno, P. (2017). Design and implementation of a novel architecture for physical human-UAV interaction. The International Journal of Robotics Research, 36(5–7), 800–819.  https://doi.org/10.1177/0278364917708038.CrossRefGoogle Scholar
  45. Schoellig, A. P., Mueller, F. L., & D’Andrea, R. (2012). Optimization-based iterative learning for precise quadrocopter trajectory tracking. Autonomous Robots, 33(1), 103–127.  https://doi.org/10.1007/s10514-012-9283-2.CrossRefGoogle Scholar
  46. Seo, H., Kim, S., & Kim, H. J. (2017). Aerial grasping of cylindrical object using visual servoing based on stochastic model predictive control. In: 2017 IEEE international conference on robotics and automation (ICRA), pp. 6362–6368,  https://doi.org/10.1109/ICRA.2017.7989751.
  47. Shin, J., Kim, H. J., Park, S., & Kim, Y. (2010). Model predictive flight control using adaptive support vector regression. Neurocomputing 73(4):1031–1037,  https://doi.org/10.1016/j.neucom.2009.10.002, http://www.sciencedirect.com/science/article/pii/S0925231209003774, bayesian Networks / Design and Application of Neural Networks and Intelligent Learning Systems (KES 2008 / Bio-inspired Computing: Theories and Applications (BIC-TA 2007)CrossRefGoogle Scholar
  48. Szafir, D., Mutlu, B., & Fong, T. (2017). Designing planning and control interfaces to support user collaboration with flying robots. The International Journal of Robotics Research, 36(5–7), 514–542.  https://doi.org/10.1177/0278364916688256.CrossRefGoogle Scholar
  49. Vukov, M., Gros, S., Horn, G., Frison, G., Geebelen, K., Jørgensen, J., et al. (2015). Real-time nonlinear MPC and MHE for a large-scale mechatronic application. Control Engineering Practice, 45, 64–78.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.School of Mechanical and Aerospace EngineeringNanyang Technological UniversitySingaporeSingapore
  2. 2.Singapore Center for 3D Printing (SC3DP)Nanyang Technological UniversitySingaporeSingapore
  3. 3.Department of EngineeringAarhus UniversityAarhus CDenmark

Personalised recommendations