Abstract
Without local adjustment mechanism for planning paths of unmanned aerial vehicles (UAVs), traditional path planning methods based on reinforcement learning are capable of global path planning only, requiring repeated training to adapt to potential changes in the environment. For solving the collaborative path planning problem of a UAV cluster in a dynamic obstacle environment, in this paper, an adaptive risk-free method is proposed for multiple UAVs to design coordinated trajectory with environment adaptability. The method integrates a type of Q-learning algorithm, which is risk free for its awareness of risk avoidance, and dynamic window approach, which can generate adaptability to dynamic changes of environmental risks. Built on the Reynold cluster model to describe a generalized UAV cooperative motion mathematically and designed with the principle of repulsion to ensure the safety of the cluster, a typical task of multi-UAV risk-free movement is established to verify the proposed coordinated path planning method. The simulation results have demonstrated that during the entire process, the cluster keeps a safe distance from dynamic obstacles, showing effectiveness of security and coordination and strong adaptability to the dynamic obstacle environment.
Similar content being viewed by others
References
Shen H, Li P (2020) Unmanned aerial vehicle (UAV) path planning based on improved pre-planning artificial potential field method. In: 2020 Chinese control and decision conference (CCDC), pp 2727–2732
Jiang C, Gao Y, Yang P (2021) Mobile robot obstacle avoidance based on improved artificial potential field method. In: The 3rd international conference on robotics and computer vision (ICRCV), pp 18–23
Turker T, Sahingoz OK, Yilmaz G (2015) 2D path planning for UAVs in radar threatening environment using simulated annealing algorithm. In: 2015 international conference on unmanned aircraft systems (ICUAS), pp 56–61
Yue X, Zhang W (2020) UAV path planning based on K-means algorithm and simulated annealing algorithm. Chinese Control Conference (CCC) 2018:2290–2295
Song Y, Ma P (2021) Research on mobile robot path planning based on improved A-star algorithm. In: 2021 international conference on electronic information engineering and computer science (EIECS), pp 683–687
Chen X, Chen X (2014) The UAV dynamic path planning algorithm research based on Voronoi diagram. In: The 26th Chinese control and decision conference (CCDC), pp 1069–1071
Li R, Fu L, Wang L, Hu X (2019) Improved Q-learning based route planning method for UAVs in unknown environment. In: 2019 IEEE 15th international conference on control and automation (ICCA), pp 118–123
Reynolds CW et al (1987) Flocks herds and schools: a distributed behavioral model. Comput Graph 21(4):25–34
Vicsek T, Cziroók A et al (1995) Novel type of phase transition in a system of self-deriven particles. Phys Rev Lett 75(6):1226–1229
Olfati-Saber R et al (2006) Flocking for multi-agent dynamic systems: algorithms and theory. IEEE Trans Autom Control 51(3):401–420
Vasarhelyi G, Viragh C, Somorjai G et al (2018) Optimized flocking of autonomous drones in cofined environments. Sci Robot 3(20):3536
Wang XK, Shen LC, Liu ZH et al (2019) Coordinated flight control of miniature fixed-wing UAV swarms: methods and experiments. Sci China Inf Sci 62(11):204–212
Gao Y, Li Y, Guo Z (2021) A Q-learning based UAV path planning method with awareness of risk avoidance. In: 2021 Chinese Automation Congress (CAC), 2021, pp 669–673
Funding
This work is supported by Natural Science Foundation of China (51822502; 42074038) and in part by Fundamental Research Funds for China Central Universities (ZYGX2014J098).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Rights and permissions
About this article
Cite this article
Gao, Y., Li, Y., Guo, Z. et al. Adaptive risk-free coordinated trajectory planning for UAV cluster in dynamic obstacle environment. AS 5, 419–428 (2022). https://doi.org/10.1007/s42401-022-00144-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42401-022-00144-y