Dissertation > Excellent graduate degree dissertation topics show

Research on Control Method for Micro Unmanned Helicopter via Reinforcement Learning

Author: CaiWenLan
Tutor: MaHongXu
School: National University of Defense Science and Technology
Course: Control Science and Engineering
Keywords: Unmanned Helicopter Reinforcement Learning Model Identification K-mean Cramer-Rao Inequality Markov Decision Processes GSBF Policy Search Pegasus
CLC: TP273
Type: Master's thesis
Year: 2007
Downloads: 175
Quote: 1
Read: Download Dissertation

Abstract


The micro unmanned helicopter presents a complicated non-linear dynamics system with high-dimensional and strong-coupling, and it’s always a challenging problem in building model and designing stable flight controller. In this paper, which is based on Raptor30 remote model helicopter, the state-space model is achieved by system identification, and the unmanned helicopter’s attitude controller in hovering is designed via the reinforcement learning method.Based on the model of micro helicopter and reinforcement learning algorithm, the following issues are researched:First, parameters of 6-DOF helicopter state-space model are identified by frequency domain system identification and the hovering state-space model is achieved. In the process of identification, a search method is presented that the K-mean theory in pattern recognition is used in the cost function, which can promote the efficiency of identification. Meanwhile, the identified parameters are analyzed by the theory of Cramer-Rao inequality and insensitivity, and compared with the actual flight data, the identification result is excellent.Second, on the base of value function of the reinforcement learning algorithm, the attitude controller is designed by tabular method and Gaussian Softmax Basis Function (GSBF) neural network method. And the simulation result shows that when the system state is a continuing high-dimensional space, the GSBF algorithm has great promotion in study efficiency and controller characteristic than the tabular one.Last, in order to overcome the disadvantages of value function of the reinforcement learning algorithm, the policy search reinforcement learning is introduced. A new gradient search algorithm, which is based on Pegasus ideal, is presented, and according to the algorithm, the attitude controller of the unmanned helicopter is designed. The simulation result shows that the controller can stabilize the helicopter that hovers in place, and the conclusion of this algorithm is coincident with the actual flight more than the value function algorithm does.

Related Dissertations

  1. Convergence and Stability of Numerical Solution of Stochastic Differential Equations with Piecewise Continuous Arguments,O211.63
  2. Research on Cooperative Orbit Determination in Satellite Network Based on Multi-Agent System Theory,V474
  3. Temperature Drift Modeling and Compensation of Fiber-Optic Gyroscopes,V241.5
  4. Research on Methods of Medical Ultrasound Image Denoising,TP391.41
  5. Based on statistics of the lognormal distribution heteroscedasticity model inferred,O212.1
  6. Origin as one, which vary by track,B948
  7. Tracking Cells in High Density Image Sequences Based on Mean Shift Algorithm Combined with Topological Constraint,Q25
  8. The Clinical Evaluation of Measuring the Horizontal Sulcus to Sulcus Distance by Ultrasound Biomicroscopy,R770.4
  9. DanceSport plantar pressure on young people and the impact of gait,G804.2
  10. OCT in early diagnosis of primary glaucoma clinical application of,R775
  11. Any area on the uniform design and construct,TQ460.1
  12. Crossing the Boundaries of Chinese and Western Painting,J205
  13. A Research on the Group Infringement of No-will-contact Through Internet,D913
  14. In the standard model based on VaR Equity Fund Risk Assessment Study,F224
  15. Researches on Improved Genetic Algorithm Base on Reinforcement Learning,TP18
  16. Research and Application on Ant Colony Clustering Based on Reinforcement Learning,TP18
  17. Research of Video-based Human-Computer Interaction Mode,TP391.41
  18. Research on Object Detection and Tracking Method in Active Vision System,TP391.41
  19. Stability of a class of stochastic delay system,TP13
  20. Research of Image Enhancing of Vein Based on Fuzzy Theory,TP391.41
  21. Decomposition Analysis of Industrial Pollution Influence Factors,X502

CLC: > Industrial Technology > Automation technology,computer technology > Automation technology and equipment > Automation systems > Automatic control,automatic control system
© 2012 www.DissertationTopic.Net  Mobile