• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.43 no.5
• /
• pp.838-847
• /
• 1994

Although there is an analytical proof of modeling capability of the neural network, the convergency error in nonlinearity modeling is inevitable, since the steepest descent based practical larning algorithms do not guarantee the convergency of modeling error. Therefore, it is difficult to apply the neural network to control system in critical environments under an on-line learning scheme. Although the convergency of modeling error of a neural network is not guatranteed in the practical learning algorithms, the convergency, or boundedness of tracking error of the control system can be achieved if a proper feedback control law is combined with the neural network model to solve the problem of modeling error. In this paper, the neural network is introduced for compensating a system uncertainty to control a nonlinear dynamic system. And for suppressing inevitable modeling error of the neural network, an iterative neural network learning control algorithm is proposed as a virtual on-line realization of the Adaptive Variable Structure Controller. The efficiency of the proposed control scheme is verified from computer simulation on dynamics control of a 2 link robot manipulator.

• Journal of the Korean Society for Precision Engineering
• /
• v.17 no.3
• /
• pp.90-101
• /
• 2000

In this paper, we propose a controller for differentially steered wheeled mobile robots. The controller uses input-output linearization algorithm and artificial neural network to stabilize the dynamic model and compensate uncertainties. The proposed neural network part has 6 inputs, 1 hidden layer, 2 torque outputs and features fast online learning and good performance on structure error learning basis. Simulation results show that the proposed controller perform precisely tracking of reference path and is robust to uncertainties.

• International Journal of Precision Engineering and Manufacturing
• /
• v.3 no.4
• /
• pp.94-100
• /
• 2002

The conventional sliding mode control (SMC) technique requires a priori knowledge of the upperbounds of disturbances and/or modeling uncertainties to assure robustness. This, however, may not be easy to obtain in practical situation. This paper presents a new methodology, a sliding mode control with disturbance estimator (SMCDE), which offers a robust control performance without a priori knowledge about the disturbance. The proposed technique is featured by an average value of the imposed disturbance over a certain period. A nonlinear spring-mass-damper system and a two-link robot system are adopted as illustrative application examples. Control performances such as estimation error and tracking error are compared between the proposed methodology and conventional scheme.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.37 no.5
• /
• pp.46-55
• /
• 2000

This paper presents a direct adaptive control of robot system using chaotic neural networks and PD controller. The chaotic neural networks have robust nonlinear dynamic characteristics because of the sufficient nonlinearity in neuron itself, and the additional self-feedback and inter-connecting weights between neurons in same layer. Since the structure and the learning method are not appropriate for applying in control system, this neural networks have not been applied. In this paper, a modified chaotic neural networks is presented for dynamic control system. To evaluate the performance of the proposed neural networks, these networks are applied to the trajectory control of the three-axis PUMA robot. The structure of controller consists of PD controller and chaotic neural networks in parallel for conforming the stability in initial learning phase. Therefore, the chaotic neural network controller acts as a compensating controller of PD controller.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.8
• /
• pp.842-847
• /
• 2008

This paper proposes a new sliding-surface-based tracking control system for nonholonomic mobile robots with disturbance. To design a robust controller, we consider the kinematic model and the dynamic model of mobile robots with disturbance. We also propose a new sliding surface to solve the problem of previous study. That is, since the new sliding surface is composed of differentiable functions unlike the previous study, we can obtain the control law for arbitrary trajectories without any constraints. From the Lyapunov stability theory, we prove that the position tracking errors and the heading direction error converge to zero. Finally, we perform the computer simulations to demonstrate the performance of the proposed control system.

• 제어로봇시스템학회:학술대회논문집
• /
• 1990.10a
• /
• pp.7-12
• /
• 1990

In this paper, we propose a new manipulator control scheme based on the CMAG neural network. The proposed control consists of two components. The feedforward component is an output of trained CMAC neural network and the feedback component is a modified sliding mode control. The CMAC accepts the position, velocity and acceleration of manipulator as input and outputs two values for the controller : One is the nominal torque used for feedforward compensation(M1 network) and the other is the inertia matrix related information used for the feedback component(M2 network). Since the used control algorithm guarantees the robust trajectory tracking in spite of modeling errors, the CMAC mapping errors due to the memory limitation are little worth consideration.

• International Journal of Control, Automation, and Systems
• /
• v.5 no.6
• /
• pp.674-680
• /
• 2007

The probabilistic roadmap (PRM) method, which is a popular path planning scheme, for a manipulator, can find a collision-free path by connecting the start and goal poses through a roadmap constructed by drawing random nodes in the free configuration space. PRM exhibits robust performance for static environments, but its performance is poor for dynamic environments. On the other hand, reinforcement learning, a behavior-based control technique, can deal with uncertainties in the environment. The reinforcement learning agent can establish a policy that maximizes the sum of rewards by selecting the optimal actions in any state through iterative interactions with the environment. In this paper, we propose efficient real-time path planning by combining PRM and reinforcement learning to deal with uncertain dynamic environments and similar environments. A series of experiments demonstrate that the proposed hybrid path planner can generate a collision-free path even for dynamic environments in which objects block the pre-planned global path. It is also shown that the hybrid path planner can adapt to the similar, previously learned environments without significant additional learning.

• The Journal of Korea Robotics Society
• /
• v.12 no.4
• /
• pp.419-424
• /
• 2017

Twisted string actuators (TSAs) are tendon-driven actuators that provide high transmission ratios. Twisting a string reduces the length of the string and generates a linear motion of the actuators. In particular, TSAs have characteristic properties (compliance) that are advantageous for operations that need to interact with the external environment. This compliance has the advantage of being robust to disturbance in force control, but it is disadvantageous for precise control because the modeling is inaccurate. In fact, many previous studies have covered the TSA model, but the model is still inadequate to be applied to actual robot control. In this paper, we introduce a modified variable radius model of TASs and experimentally demonstrate that the modified variable radius model is correct compared to the conventional variable radius string model. In addition, the elastic characteristics of the TSAs are discussed along with the experimental results.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.7
• /
• pp.654-661
• /
• 2015

Stairs are the most popular obstacles in buildings and factories. To enlarge the application areas of a field robotic platform, stair-climbing is very important mission. One important reason why a stair-climbing is difficult is that stairs are various in sizes. To achieve autonomous climbing of various-sized stairs, dynamic modeling is essential. In this research, an inverse dynamic modeling is performed to enable an autonomous stair climbing. Stair-climbing robotic platform with flip locomotion, named FilpBot, is analyzed. The FlipBot platform has advantages of robust stair-climbing of various sizes with constant speed, but the autonomous operation is not yet capable. Based on external constraints and the postures of the robot, inverse dynamic models are derived. The models are switched by the constraints and postures to analyze the continuous motion during stair-climbing. The constraints are changed according to the stair size, therefore the analysis results are different each other. The results of the inverse dynamic modeling are going to be used in motor design and autonomous control of the robotic platform.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1853-1858
• /
• 2004

This paper presents the development of a full order sliding mode controller for tracking problem of a class of uncertain dynamical system, in particular, the direct drive robot manipulators. By treating the arm as an uncertain system represented by its nominal and bounded parametric uncertainties, a new robust fullorder sliding mode tracking controller is derived such that the actual trajectory tracks the desired trajectory as closely as possible despite the non-linearities and input couplings present in the system. A proportional-integral sliding surface is chosen to ensure the stability of overall dynamics during the entire period i.e. the reaching phase and the sliding phase. Application to a three DOF direct drive robot manipulator is considered.