Hovering control of UAV based on autonomous mapping approach

The autonomous learning capability of UAV (unmanned aerial vehicle) has gained more and more attentions of researchers. As far as helicopter steering is concerned, instead of calculating dynamics of UAV in a relative short interval, pilots just take their experience and consciousness instantaneously, known as similar status has similar action, to keep the helicopter hovering. The experience and the consciousness of pilots store the mapping from the similar environment to the corresponding similar decisions. Motivated by the process, we establish the UAV mapping base from environment to decision with IHDR (Incremental Hierarchical Discriminant Regression) algorithm. UAV learns to build the mapping relation offline and online alternatively. The retrieval process from the mapping base has higher efficiency for its less mathematics complexity. Simulation results show that the approach we proposed in this paper has better performance than traditional neural network.

[1]  Pieter Abbeel,et al.  An Application of Reinforcement Learning to Aerobatic Helicopter Flight , 2006, NIPS.

[2]  Juyang Weng,et al.  Incremental Hierarchical Discriminant Regression , 2007, IEEE Transactions on Neural Networks.

[3]  Anthony J. Calise,et al.  Nonlinear adaptive flight control using neural networks , 1998 .

[4]  S. Shankar Sastry,et al.  Autonomous Helicopter Flight via Reinforcement Learning , 2003, NIPS.

[5]  Juyang Weng,et al.  Hierarchical Discriminant Regression , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  George A. Bekey,et al.  Learning helicopter control through "teaching by showing" , 1998, Proceedings of the 37th IEEE Conference on Decision and Control (Cat. No.98CH36171).

[7]  Brett Browning,et al.  A survey of robot learning from demonstration , 2009, Robotics Auton. Syst..

[8]  Boguslaw Szlachetko,et al.  Fuzzy flight control system for helicopter intelligence in hover , 2005, 5th International Conference on Intelligent Systems Design and Applications (ISDA'05).

[9]  Guangjun Liu,et al.  Modeling a Small-size Unmanned Helicopter Using Optimal Estimation in The Frequency Domain , 2008, 2008 15th International Conference on Mechatronics and Machine Vision in Practice.

[10]  Eric Feron,et al.  Scaling effects and dynamic characteristics of miniature rotorcraft , 2004 .

[11]  Pieter Abbeel,et al.  Learning for control from multiple demonstrations , 2008, ICML '08.

[12]  H. Jin Kim,et al.  Feedback linearization vs. adaptive sliding mode control for a quadrotor helicopter , 2009 .