• Transactions on Control, Automation and Systems Engineering
• /
• v.4 no.1
• /
• pp.100-107
• /
• 2002

The advanced bilateral control algorithm, which can enlarge a reflected force by combining force reflection and compliance control, greatly enhances workability in teleoperation. In this scheme the maximum boundaries of a compliance controller and a force reflection gain guaranteeing stability and good task performance greatly depend upon characteristics of a slave arm, a master arm, and an environment. These characteristics, however, are generally unknown in teleoperation. It is, therefore, very difficult to determine such maximum boundary of the gain. The paper presented a novel method for design of an advanced bilateral controller. The factors affecting task performance and stability in the advanced bilateral controller were analyzed and a design guideline was presented. The neurofuzzy compliance model (NFCM)-based bilateral control proposed herein is an algorithm designed to automatically determine the suitable compliance for a given task or environment. The NFCM, composed of a fuzzy logic controller (FLC) and a rule-learning mechanism, is used as a compliance controller. The FLC generates compliant motions according to contact forces. The rule-learning mechanism, which is based upon the reinforcement learning algorithm, trains the rule-base of the FLC until the given task is done successfully. Since the scheme allows the use of large force reflection gain, it can assure good task performance. Moreover, the scheme does not require any priori knowledge on a slave arm dynamics, a slave arm controller and an environment, and thus, it can be easily applied to the control of any telerobot systems. Through a series of experiments effectiveness of the proposed algorithm has been verified.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.38 no.4
• /
• pp.11-19
• /
• 2001

In this paper, we study the convergence property of iterative learning control (ILC). First, we present a new method to prove the convergence of ILC using sup-norm. Then, we propose a new type of ILC algorithm adopting intervalized learning scheme and show that the monotone convergence of the output error can be obtained for a given time interval when the proposed ILC algorithm is applied to a class of linear dynamic systems. We also show that the divided time interval is affected from the learning gain and that convergence speed of the proposed learning scheme can be increased by choosing the appropriate learning gain. To show the effectiveness of the proposed algorithm, two numerical examples are given.

• Journal of Advanced Navigation Technology
• /
• v.14 no.6
• /
• pp.874-881
• /
• 2010

A automatic flight control system(AFCS) of UAS needs to control its flight path along target path exactly as adjusts flight coefficient itself depending on static or dynamic changes of airplane's features such as type, size or weight. In this paper, we propose system which tunes control gain autonomously depending on change of airplane's feature in flight as adding MLM(Machine Learning Module) on AFCS. MLM is designed with Linear Regression algorithm and Reinforcement Learning and it includes EvM(Evaluation Module) which evaluates learned control gain from MLM and verified system. This system is tested on beaver FDC simulator and we present its analysed result.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.50 no.3
• /
• pp.107-113
• /
• 2001

This paper deals with speed control of DC servo motor using a PID controller with a gain tuning based on a Back-Propagation(BP) Learning Algorithm. Conventionally a PID controller has been used in the industrial control. But a PID controller should produce suitable parameters for each system. Also, variables of the PID controller should be changed according to environments, disturbances and loads. In this paper described by a experiment that contained a method using a PID controller with a gain tuning based on a Back-Propagation(BP) Learning Algorithm, we developed speed characteristics of a DC servo motor on variable loads. The parameters of the controller are determined by neural network performed on on-line system after training the neural network on off-line system.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.23 no.4
• /
• pp.399-406
• /
• 2020

In this paper, we propose a time-varying proportional navigation guidance law that determines the proportional navigation gain in real-time according to the operating situation. When intercepting a target, an unidentified evasion strategy causes a loss of optimality. To compensate for this problem, proper proportional navigation gain is derived at every time step by solving an optimal control problem with the inferred evader's strategy. Recently, deep reinforcement learning algorithms are introduced to deal with complex optimal control problem efficiently. We adapt the actor-critic method to build a proportional navigation gain network and the network is trained by the Proximal Policy Optimization(PPO) algorithm to learn an evasion strategy of the target. Numerical experiments show the effectiveness and optimality of the proposed method.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1150-1156
• /
• 2019

This paper explores a model-free value-based approach for solving survival gridworld problem. Survival gridworld problem opens up a challenge involving taking risks to gain better rewards. Classic value-based approach in model-free reinforcement learning assumes minimal risk decisions. The proposed method involves a hybrid on-policy and off-policy updates to experience roll-outs using a modified Q-based update equation that introduces a parametric linear rectifier and motivational discount. The significance of this approach is it allows model-free training of agents that take into account risk factors and motivated exploration to gain better path decisions. Experimentations suggest that the proposed method achieved better exploration and path selection resulting to higher episode scores than classic off-policy and on-policy Q-based updates.

• Proceedings of the KIEE Conference
• /
• 2003.11c
• /
• pp.717-719
• /
• 2003

Recently Neural Network techniques have widely used in adaptive and learning control schemes for production systems. However, generally it costs a lot of time for learning in the case applied in control system. Furthermore, the physical meaning of neural networks constructed as a result is not obvious. And in practice since it is difficult to the PID gains suitably lots of researches have been reported with respect to turning schemes of PID gains. A Neural Network-based PID control scheme is proposed, which extracts skills of human experts as PID gains. This controller is designed by using three-layered neural networks. The effectiveness of the proposed Neural Network-based PID control scheme is investigated through an application for a production control system. This control method can enable a plant to operate smoothy and obviously as the plant condition varies with any unexpected accident.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.335-338
• /
• 1996

In this paper, we are going to design an iterative learning controller with the robust properties for initial error. For this purpose, the PID-type learning law will be considered and the design guide-line will be presented for the selection of the learning gain. Also, we are going to suggest a condition for the convergence of control input for a plant with input delay. Several simulation results are presented, which shows the effectiveness of the proposed algorithms.

• Journal of the Korean Society for Precision Engineering
• /
• v.24 no.12
• /
• pp.57-64
• /
• 2007

There have been many researches for optimal controllers in multivariable systems, and they generally use accurate linear models of the plant dynamics. Real systems, however, contain nonlinearities and high-order dynamics that may be difficult to model using conventional techniques. Therefore, it is necessary a PID gain tuning method without explicit modeling for the multivariable plant dynamics. The PID tuning method utilizes the sign of Jacobian and gradient descent techniques to iteratively reduce the error-related objective function. This paper, especially, focuses on the role of I-controller when there is a steady state error. However, it is not easy to tune I-gain unlike P- and D-gain because I-controller is mainly operated in the steady state. Simulations for an overhead crane system with dynamic friction show that the proposed PID-LC algorithm improves controller performance, even in the steady state error.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.41 no.3
• /
• pp.17-24
• /
• 2004

We present a P-type iterative learning control(ILC) scheme for uncertain robotic systems that perform the same tasks repetitively. The proposed ILC scheme comprises a linear feedback controller consisting of position error, and a feedforward and feedback teaming controller updated by current velocity error. As the learning iteration proceeds, the joint position and velocity mrs converge uniformly to zero. By adopting the learning gain dependent on the iteration number, we present joint position and velocity error bounds which converge at the arbitrarily tuned rate, and the joint position and velocity errors converge to zero in the iteration domain within the adopted error bounds. In contrast to other existing P-type ILC schemes, the proposed ILC scheme enables analysis and tuning of the convergence rate in the iteration domain by designing properly the learning gain.