Reinforcement learning control for autorotation of a simple point-mass helicopter model

Download
2018
Kopşa, Kadircan
This study presents an application of an actor-critic reinforcement learning method to a simple point-mass model helicopter guidance problem during autorotation. A point-mass model of an OH-58A helicopter in autorotation was built. A reinforcement learning agent was trained by a model-free asynchronous actor-critic algorithm, where training episodes were parallelized on a multi-core CPU. Objective of the training was defined as achieving near-zero horizontal and vertical kinetic energies at the instant of touchdown. During each training episode, the agent was presented a reward at each discrete time-step according to a multi-conditional reward function. Reward function was programmed to output the negative of a weighted sum of squared vertical and horizontal velocities at touchdown. The agent consists of two separate neural network function approximators, namely the actor and the critic. The critic approximates the value of a set of states. The actor generates a set of actions given a set of states, sampled from a Gaussian distribution with mean values as output set of the actor network. Updates to the parameters of both networks were calculated from accumulated gradients during each episode and applied once per episode to improve training stability. RMSProp algorithm was used for optimization. Results achieved by the agent indicates that the method is successful at guiding the point-mass helicopter to the ground with minimal kinetic energy for most initial conditions. Controls generated by the reinforcement learning agent were found to be similar to a helicopter pilot’s technique.

Suggestions

Reinforcement learning control for helicopter landing in autorotation
Kopsa, Kadircan; Kutay, Ali Türker (2018-01-01)
This study presents an application of an actor-critic reinforcement learning method to the nonlinear problem of helicopter guidance during autorotation in order to achieve safe landing following engine power loss. A point mass model of an OH-58A helicopter in autorotation was built to simulate autorotation dynamics. The point-mass model includes equations of motion In vertical plane. The states of the point-mass model are the horizontal and vertical velocities, the horizontal and vertical positions, the rot...
Mobile Robot Heading Adjustment Using Radial Basis Function Neural Networks Controller and Reinforcement Learning
BAYAR, GÖKHAN; Konukseven, Erhan İlhan; Koku, Ahmet Buğra (2008-10-28)
This paper proposes radial basis function neural networks approach to the Solution of a mobile robot heading adjustment using reinforcement learning. In order to control the heading of the mobile robot, the neural networks control system have been constructed and implemented. Neural controller has been charged to enhance the control system by adding some degrees of strength. It has been achieved that neural networks system can learn the relationship between the desired directional heading and the error posi...
Effective subgoal discovery and option generation in reinforcement learning
Demir, Alper; Polat, Faruk; Department of Computer Engineering (2016)
Subgoal discovery is proven to be a practical way to cope with large state spaces in Reinforcement Learning. Subgoals are natural hints to partition the problem into sub-problems, allowing the agent to solve each sub-problem separately. Identification of such subgoal states in the early phases of the learning process increases the learning speed of the agent. In a problem modeled as a Markov Decision Process, subgoal states possess key features that distinguish them from the ordinary ones. A learning agent ...
Reinforcement learning with internal expectation for the random neural network
Halıcı, Uğur (Elsevier BV, 2000-10-01)
The reinforcement learning scheme proposed in Halici (1977) (Halici, U., 1997. Journal of Biosystems 40 (1/2), 83-91) for the random neural network (Gelenbe, E., 1989b. Neural Computation 1 (4), 502-510) is based on reward and performs well for stationary environments. However: when the environment is not stationary it suffers from getting stuck to the previously learned action and extinction is not possible. In this paper, the reinforcement learning scheme is extended by introducing a weight update rule wh...
Reinforcement learning using potential field for role assignment in a multi-robot two-team game
Fidan, Özgül; Erkmen, İsmet; Department of Electrical and Electronics Engineering (2004)
In this work, reinforcement learning algorithms are studied with the help of potential field methods, using robosoccer simulators as test beds. Reinforcement Learning (RL) is a framework for general problem solving where an agent can learn through experience. The soccer game is selected as the problem domain a way of experimenting multi-agent team behaviors because of its popularity and complexity.
Citation Formats
K. Kopşa, “Reinforcement learning control for autorotation of a simple point-mass helicopter model,” M.S. - Master of Science, Middle East Technical University, 2018.