DOI QR코드

DOI QR Code

Path Generation Method of UAV Autopilots Using Max-Min Algorithm

  • Kwak, Jeonghoon (Dept. of Superintelligence Lab. and Department of Multimedia Engineering, Dongguk University) ;
  • Sung, Yunsick (Dept. of Superintelligence Lab. and Department of Multimedia Engineering, Dongguk University)
  • Received : 2018.07.31
  • Accepted : 2018.10.05
  • Published : 2018.12.31

Abstract

In recent times, Natural User Interface/Natural User Experience (NUI/NUX) technology has found widespread application across a diverse range of fields and is also utilized for controlling unmanned aerial vehicles (UAVs). Even if the user controls the UAV by utilizing the NUI/NUX technology, it is difficult for the user to easily control the UAV. The user needs an autopilot to easily control the UAV. The user needs a flight path to use the autopilot. The user sets the flight path based on the waypoints. UAVs normally fly straight from one waypoint to another. However, if flight between two waypoints is in a straight line, UAVs may collide with obstacles. In order to solve collision problems, flight records can be utilized to adjust the generated path taking the locations of the obstacles into consideration. This paper proposes a natural path generation method between waypoints based on flight records collected through UAVs flown by users. Bayesian probability is utilized to select paths most similar to the flight records to connect two waypoints. These paths are generated by selection of the center path corresponding to the highest Bayesian probability. While the K-means algorithm-based straight-line method generated paths that led to UAV collisions, the proposed method generates paths that allow UAVs to avoid obstacles.

Keywords

E1JBB0_2018_v14n6_1457_f0001.png 이미지

Fig. 2. Result of collecting four flight records: (a) 1st flight record, (b) 2nd flight record, (c) 3th flight record, and (d) 4th flight record.

E1JBB0_2018_v14n6_1457_f0002.png 이미지

Fig. 3. K waypoints are generated using the K-means algorithm by classifying the points included in the four flight records.

E1JBB0_2018_v14n6_1457_f0003.png 이미지

Fig. 4. Resultant flight path generated. (a) is the result of generating the flight path using the proposed method, and (b) is the result of generating the flight path based on the K-means algorithm-based straightline method.

E1JBB0_2018_v14n6_1457_f0004.png 이미지

Fig. 5. It is the result of extracting the temporal path Sk,k',r connecting the two waypoints, μk and μk' , in the flight record Pr.

E1JBB0_2018_v14n6_1457_f0005.png 이미지

Fig. 6. Flight records collected by three flights.

E1JBB0_2018_v14n6_1457_f0006.png 이미지

Fig. 7. Comparison between the proposed method and the K-means algorithm-based straight-line method. (a) Result of generating the flight path by the proposed method. (b) Result of generating the Kmeans algorithm-based straight-line method.

E1JBB0_2018_v14n6_1457_f0007.png 이미지

Fig. 1. Generation a path using the user’s records consists of four stages: Path Record, Point Classification, Temporal Path Generation, and Concreted Path Generation.

References

  1. P. Fahlstrom and T. Gleason, Introduction to UAV Systems, 4th ed. Chichester, UK: John Wiley & Sons, 2012.
  2. L. Merino, F. Caballero, J. R. Martinez-De-Dios, I. Maza, and A. Ollero, "An unmanned aircraft system for automatic forest fire monitoring and measurement," Journal of Intelligent & Robotic Systems, vol. 65, no. 1-4, pp. 533-548, 2012. https://doi.org/10.1007/s10846-011-9560-x
  3. L. Zhang, B. Wang, W. Peng, C. Li, Z. Lu, and Y. Guo, "A method for forest fire detection using UAV," Advanced Science and Technology Letters, vol. 81, pp. 69-74, 2015.
  4. J. Kwak and Y. Sung, "Beacon-based indoor location measurement method to enhanced common chordbased trilateration," Journal of Information Processing Systems, vol. 13, no. 6, pp. 1640-1651, 2017. https://doi.org/10.3745/JIPS.04.0053
  5. F. Zhang, D. Gao, and I. W. Joe, "A tier-based duty-cycling scheme for forest monitoring," Journal of Information Processing Systems, vol. 13, no. 5, pp. 1320-1330, 2017. https://doi.org/10.3745/JIPS.04.0043
  6. M. T. N. Truong and S. Kim, "Parallel implementation of color-based particle filter for object tracking in embedded systems," Human-centric Computing and Information Sciences, vol. 7, article no. 2, 2017.
  7. L. V. Santana, A. S. Brandao, and M. Sarcinelli-Filho, "Outdoor waypoint navigation with the AR.Drone quadrotor," in Proceedings of 2015 International Conference on Unmanned Aircraft Systems (ICUAS), Denver, CO, 2015, pp. 303-311.
  8. L. V. Santana, A. S. Brandao, and M. Sarcinelli-Filho, "An automatic flight control system for the AR.Drone quadrotor in outdoor environments," in Proceedings of 2015 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED-UAS), Cancun, Mexico, 2015, pp. 401-410.
  9. J. Kwak and J. H. Park, "Linear motor primitive generation method based on observation spots," Advanced Science Letters, vol. 22, no. 9, pp. 2566-2569, 2016. https://doi.org/10.1166/asl.2016.7843
  10. J. Kwak, J. H. Park, and Y. Sung, "Unmanned aerial vehicle flight point classification algorithm based on symmetric big data," Symmetry, vol. 9, article no. 1, 2017.
  11. T. Eiter and H. Mannila, "Computing discrete Frechet distance," Information Systems Department, Technical University of Vienna, Report No. CD-TR 94/64, 1994.