Learning motion primitives for planning swift maneuvers of quadrotor


This work proposes a novel, learning-based method to leverage navigation time performance of unmanned aerial vehicles in dense environments by planning swift maneuvers using motion primitives. In the proposed planning framework, desirable motion primitives are explored by reinforcement learning. Two-stage training composed of learning in simulations and real flights is conducted to build up a swift motion primitive library. The library is then referred in real-time and the primitives are utilized by an intelligent control authority switch mechanism when swift maneuvers are needed for particular portions of a trajectory. Since the library is constructed upon realistic Gazebo simulations and real flights together, probable modeling uncertainties which can degrade planning performance are minimal. Moreover, since the library is in the form of motion primitives, it is computationally inexpensive to be retained and used for planning as compared to solving optimal motion planning problem algebraically. Overall, the proposed method allows for exceptional, swift maneuvers and enhances navigation time performance in dense environments up to 20% as being demonstrated by real flights with Diatone FPV250 quadrotor equipped with PX4 FMU.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12


  1. 1.

    During training, the parameters \(u_{min}\) and \(u_{max}\) are selected as 0.2 and 2.0 m/s while spatial path segments are generated within rough limits of turning radius (\(\pm \,2.0\) m) and altitude change (\(\pm \,2.0\) m) considering our lab space limitations and Diatone FPV250 Quadrotor’s capabilities for experimental demonstration. However, agent is flexible to have different limits based on the hardware.

  2. 2.

    Average deviation from the path is calculated by averaging the spatial distances between each data point of the 4th degree Bézier curve approximation of the desired path and the closest point on the 10th degree Bézier curve approximation of the resultant path to that point over the total number of data points.


  1. Abbeel, P., Coates, A., & Ng, A. Y. (2010). Autonomous helicopter aerobatics through apprenticeship learning. The International Journal of Robotics Research, 29(13), 1608–1639.

    Article  Google Scholar 

  2. Bareiss, D., Bourne, J. R., & Leang, K. K. (2017). On-board model-based automatic collision avoidance: Application in remotely-piloted unmanned aerial vehicles. Autonomous Robots, 41(7), 1539–1554.

    Article  Google Scholar 

  3. Camci, E., & Kayacan, E. (2016). Waitress quadcopter explores how to serve drinks by reinforcement learning. In 2016 IEEE region 10 conference (TENCON) (pp. 28–32). IEEE.

  4. De Casteljau, P. (1959). Outillages méthodes calcul. Paris: Andr e Citro en Automobiles SA.

    Google Scholar 

  5. Degiovanni, L., & Bernard, P. (2016). Tp drone diatone 250 fpv. http://eduscol.education.fr/. Accessed May 2017.

  6. Deits, R., & Tedrake, R. (2015). Efficient mixed-integer planning for UAVs in cluttered environments. In 2015 IEEE international conference on robotics and automation (ICRA) (pp. 42–49). IEEE.

  7. Dong, Y., Camci, E., & Kayacan, E. (2018). Faster RRT-based nonholonomic path planning in 2D building environments using skeleton-constrained path biasing. Journal of Intelligent & Robotic Systems, 89(3–4), 387–401.

    Article  Google Scholar 

  8. Fuller, S. B., Teoh, Z. E., Chirarattananon, P., Pérez-Arancibia, N. O., Greenberg, J., & Wood, R. J. (2017). Stabilizing air dampers for hovering aerial robotics: Design, insect-scale flight tests, and scaling. Autonomous Robots, 41(8), 1555–1573.

    Article  Google Scholar 

  9. Gillula, J. H., Huang, H., Vitus, M. P., & Tomlin, C. J. (2010). Design of guaranteed safe maneuvers using reachable sets: Autonomous quadrotor aerobatics in theory and practice. In 2010 IEEE international conference on robotics and automation (ICRA) (pp. 1649–1654). IEEE.

  10. Hehn, M., & D’Andrea, R. (2011). Quadrocopter trajectory generation and control. IFAC Proceedings Volumes, 44(1), 1485–1491.

    Article  Google Scholar 

  11. Hehn, M., & D’Andrea, R. (2015). Real-time trajectory generation for quadrocopters. IEEE Transactions on Robotics, 31(4), 877–892.

    Article  Google Scholar 

  12. Hwangbo, J., Sa, I., Siegwart, R., & Hutter, M. (2017). Control of a quadrotor with reinforcement learning. IEEE Robotics and Automation Letters, 2(4), 2096–2103.

    Article  Google Scholar 

  13. Korrapati, H., & Mezouar, Y. (2017). Multi-resolution map building and loop closure with omnidirectional images. Autonomous Robots, 41(4), 967–987.

    Article  Google Scholar 

  14. Landry, B., Deits, R., Florence, P. R., & Tedrake, R. (2016). Aggressive quadrotor flight through cluttered environments using mixed integer programming. In 2016 IEEE international conference on robotics and automation (ICRA) (pp. 1469–1475). IEEE.

  15. LaValle, S. M., & Kuffner, J. J. (2001). Randomized kinodynamic planning. The International Journal of Robotics Research, 20(5), 378–400.

    Article  Google Scholar 

  16. Lee, T., Leoky, M., & McClamroch, N. H. (2010). Geometric tracking control of a quadrotor UAV on se (3). In 2010 49th IEEE conference on decision and control (CDC) (pp. 5420–5425). IEEE.

  17. Ling, Y., Kuse, M., & Shen, S. (2018). Edge alignment-based visual-inertial fusion for tracking of aggressive motions. Autonomous Robots, 42(3), 513–528.

    Article  Google Scholar 

  18. Loianno, G., Brunner, C., McGrath, G., & Kumar, V. (2017). Estimation, control, and planning for aggressive flight with a small quadrotor with a single camera and imu. IEEE Robotics and Automation Letters, 2(2), 404–411.

    Article  Google Scholar 

  19. Lupashin, S., & D’Andrea, R. (2012). Adaptive fast open-loop maneuvers for quadrocopters. Autonomous Robots, 33(1–2), 89–102.

    Article  Google Scholar 

  20. Lupashin, S., Schöllig, A., Sherback, M., & D’Andrea, R. (2010). A simple learning strategy for high-speed quadrocopter multi-flips. In 2010 IEEE international conference on robotics and automation (ICRA) (pp. 1642–1648). IEEE.

  21. Mebarki, R., Lippiello, V., & Siciliano, B. (2017). Vision-based and imu-aided scale factor-free linear velocity estimator. Autonomous Robots, 41(4), 903–917.

    Article  Google Scholar 

  22. Mehndiratta, M., & Kayacan, E. (2017). Receding horizon control of a 3 DOF helicopter using online estimation of aerodynamic parameters. In Proceedings of the institution of mechanical engineers, part G: Journal of aerospace engineering (p. 0954410017703414).

  23. Meier, L., Tanskanen, P., Heng, L., Lee, G. H., Fraundorfer, F., & Pollefeys, M. (2012). Pixhawk: A micro aerial vehicle design for autonomous flight using onboard computer vision. Autonomous Robots, 33(1–2), 21–39.

    Article  Google Scholar 

  24. Mellinger, D., & Kumar, V. (2011). Minimum snap trajectory generation and control for quadrotors. In 2011 IEEE international conference on robotics and automation (ICRA) (pp. 2520–2525). IEEE.

  25. 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.

    Article  Google Scholar 

  26. Mueller, M. W., Hehn, M., & D’Andrea, R. (2015). A computationally efficient motion primitive for quadrocopter trajectory generation. IEEE Transactions on Robotics, 31(6), 1294–1310.

    Article  Google Scholar 

  27. Müller, M., Lupashin, S., & D’Andrea, R. (2011). Quadrocopter ball juggling. In 2011 IEEE/RSJ international conference on intelligent robots and systems (IROS) (pp. 5113–5120). IEEE.

  28. Neunert, M., de Crousaz, C., Furrer, F., Kamel, M., Farshidian, F., Siegwart, R., Buchli, J. (2016). Fast nonlinear model predictive control for unified trajectory optimization and tracking. In 2016 IEEE international conference on robotics and automation (ICRA) (pp. 1398–1404). IEEE.

  29. Oosedo, A., Abiko, S., Konno, A., & Uchiyama, M. (2017). Optimal transition from hovering to level-flight of a quadrotor tail-sitter UAV. Autonomous Robots, 41(5), 1143–1159.

    Article  Google Scholar 

  30. Pfeiffer, M., Schaeuble, M., Nieto, J., Siegwart, R., & Cadena, C. (2016). From perception to decision: A data-driven approach to end-to-end motion planning for autonomous ground robots. arXiv preprint arXiv:1609.07910.

  31. Santamaria-Navarro, A., Loianno, G., Solà, J., Kumar, V., & Andrade-Cetto, J. (2018). Autonomous navigation of micro aerial vehicles using high-rate and low-cost sensors. Autonomous Robots, 42(6), 1263–1280.

    Article  Google Scholar 

  32. Sarabakha, A., Fu, C., Kayacan, E., & Kumbasar, T. (2018). Type-2 fuzzy logic controllers made even simpler: From design to deployment for UAVs. IEEE Transactions on Industrial Electronics, 65(6), 5069–5077.

    Article  Google Scholar 

  33. Sutton, R. S., & Barto, A. G. (1998). Reinforcement learning: An introduction (Vol. 1). Cambridge: MIT Press.

    Google Scholar 

  34. Tang, J., Singh, A., Goehausen, N., & Abbeel, P. (2010). Parameterized maneuver learning for autonomous helicopter flight. In 2010 IEEE international conference on robotics and automation (ICRA) (pp. 1142–1148). IEEE.

  35. Ure, N. K., & Inalhan, G. (2012). Autonomous control of unmanned combat air vehicles: Design of a multimodal control and flight planning framework for agile maneuvering. IEEE Control Systems, 32(5), 74–95.

    MathSciNet  Article  MATH  Google Scholar 

Download references


This work is financially supported by the Singapore Ministry of Education (RG185/17).

Author information



Corresponding author

Correspondence to Erdal Kayacan.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (mp4 5631 KB)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Camci, E., Kayacan, E. Learning motion primitives for planning swift maneuvers of quadrotor. Auton Robot 43, 1733–1745 (2019). https://doi.org/10.1007/s10514-019-09831-w

Download citation


  • Reinforcement learning
  • Path planning
  • Quadrotor
  • Agile maneuvers