Control Of Industrial Manipulators Research Articles

Inverted Pendulum Control: A Comparative Study from Conventional Control to Reinforcement Learning

The rise of deep reinforcement learning in recent years has led to its usage in solving various challenging problems, such as chess and Go games. However, despite its recent success in solving highly complex problems, a question arises on whether this class of method is best employed to solve control problems in general, such as driverless cars, mobile robot control, or industrial manipulator control. This paper presents a comparative study between various classes of control algorithms and reinforcement learning in controlling an inverted pendulum system to evaluate the performance of reinforcement learning in a control problem. A test was performed to test the performance of root locus-based control, state compensator control, proportional-derivative (PD) control, and a reinforcement learning method, namely the proximal policy optimization (PPO), to control an inverted pendulum on a cart. The performances of the transient responses (such as overshoot, peak time, and settling time) and the steady-state responses (namely steady-state error and the total energy) were compared. It is found that when given a sufficient amount of training, the reinforcement learning algorithm was able to produce a comparable solution to its control algorithm counterparts despite not knowing anything about the system’s properties. Therefore, it is best used to control plants with little to no information regarding the model where testing a particular policy is easy and safe. It is also recommended for a system with a clear objective function.

An adaptive type-2 fuzzy sliding mode tracking controller for a robotic manipulator

<abstract> <p>With the wide application of intelligent manufacturing and the development of diversified functions of industrial manipulator, the requirements for the control accuracy and stability of the manipulator servo system are also increasing. The control of industrial manipulator is a time-varying system with nonlinear and strong coupling, which is often affected by uncertain factors, including parameter changing, environmental interference, joint friction and so on. Aiming at the problem of the poor control accuracy of the manipulator. Under the complex disturbance environment, control accuracy of the manipulator will be greatly affected, so this paper proposes an adaptive type-2 fuzzy sliding mode control (AT2FSMC) method applied to the servo control of the industrial manipulator, which realizes the adaptive adjustment of the boundary layer thickness to suppress the trajectory error caused by the external disturbance and weakens the chattering problem of the sliding mode control. The simulation results on a two-axis manipulator indicate that, with the presence of external disturbances, the proposed control method can help the manipulator maintain control signal stability and improve tracking accuracy. It also suppressed chattering produced by sliding mode control (SMC) and strengthening the robustness of the system. Compared with other conventional trajectory tracking control methods, the effectiveness of the proposed method can be reflected. Finally, the proposed method is tested in an actual manipulator to complete a practical trajectory to prove its feasibility.</p> </abstract>

Real-time vision-based control of industrial manipulators for layer-width setting in concrete 3D printing applications

In this paper, to have control over geometry specifications of rectangular bar-shaped layers in a robotic concrete 3D printing process, a real-time vision-based control framework is developed and proposed. The proposed control system is able to set the layer-width by automatically adjusting the velocity of an industrial manipulator during the 3D printing process of concrete based materials relying on a vision system feedback. Initially, details related to the control system, vision and processing units, and robotic platform are discussed. In continue, technical descriptions related to the printhead design, conversion process from a digital 3D drawing model to numerical motion control commands of an industrial manipulator and building material used in this work are reported. The reliability and responsiveness of the developed system is then evaluated through experimental tests by printing several single bar-shaped layers with different wideness by means of an unique printhead geometry and also by printing two layers with the same dimension centrally above another. Overall, the high accuracy and responsiveness of the developed system demonstrate a great potential for real-time vision-based control of industrial manipulators for layer-width setting in concrete 3D printing applications.

Desired compensation adaptive robust repetitive control of a multi-DoFs industrial robot

In the presence of system coupling and dynamic uncertainties, extensive research has been conducted on the precise motion control of industrial manipulators with general reference trajectories. Since repetitive operations are common tasks in industrial applications, it is an essential and practical problem to further improve the control accuracy by taking advantage of the periodicity of the reference trajectory. In this paper, a desired compensation adaptive robust repetitive control is proposed for multi-DoFs industrial manipulators to perform repetitive tasks. Specifically, the link dynamics identified offline is compensated directly to decouple the system and capture the main characteristics of the link effect. Then, the uncertain friction is dealt with through an online adaptation scheme, in which the desired compensation is utilized to avoid measurement noise and chattering at low speed. And periodic disturbances are approximated by Fourier series expansion with unknown Fourier coefficients, which will be learned online. Finally, the robust feedback is designed to guarantee transient control accuracy and robustness against dynamic uncertainties. Comparative experiments on an industrial manipulator show that the proposed controller possesses better transient and steady-state control accuracy and error convergence rate.

Command and control of industrial manipulator through speech-based interfaces in Indic Languages

Human–robot interaction has been a challenging task, and it involves various criteria to be considered including robot operator’s caliber and his/her safety. Here in this project, we bring speech recognition to the rescue of robot operator, which has become a popular interface for human–computer interaction to recognize the speech of robot operator, to command and control the industrial robot. In this project, the five degree of freedom robotic arm is controlled through speech-based interfaces in Indic Languages, namely English (Indian accent), Hindi and Tamil. Python speech recognition API along with PocketSphinx is used for converting robot operator’s speech commands to text form, and the command is translated and fed to the sophisticated servo controller for the actuation of robotic arm. A mobile application was also developed that can control the robot arm using HC-05 Bluetooth technology through speech-based interfaces.

SMCSPO 기반 조립용 산업 매니퓰레이터의 강인한 제어 연구

SMCSPO 기반 조립용 산업 매니퓰레이터의 강인한 제어 연구

SMCSPO 기반 조립용 산업 매니퓰레이터의 강인한 제어 연구

SMCSPO 기반 조립용 산업 매니퓰레이터의 강인한 제어 연구

The Industrial Manipulator Control System Based on Programmable Logic Controller

Industrial manipulator has become an important and indispensable part of the modern industrial production, This paper studies the industrial manipulator control system based on programmable controller, This paper mainly introduces the software design of PLC control system, analyzes the various modules of the composition manipulator control system , Adopt Mitsubishi PLC design of manipulator system was put forward, the function and the control method of Mitsubishi PLC was studied; Experimental results show that the manipulator can eventually exercise according to the requirements of the control program ,and implement the monitoring system of this manipulator intuitive image observation, reached the design purpose and the requirements of this paper.

Kinematic Kalman Filter (KKF) for Robot End-Effector Sensing

In control of industrial manipulators, the position from the motor encoder has been the only sensor measurement for axis control. In this case, it is not easy to estimate the end-effector motion accurately because of the kinematic errors of links, joint flexibility of gear mechanisms, and so on. Direct measurement of the end-effector using the vision sensor is considered as a solution but its performance is often limited by the slow sampling rate and the latency. To overcome these limitations, this paper extends the basic idea of the kinematic Kalman filter (KKF) to general rigid body motion leading to the formulation of the multidimensional kinematic kalman filter (MD-KKF). By combining the measurements from the vision sensor, the accelerometers and the gyroscopes, the MD-KKF can recover the intersample values and compensate for the measurement delay of the vision sensor providing the state information of the end-effector fast and accurately. The performance of the MD-KKF is verified experimentally using a planar two-link robot. The MD-KKF will be useful for widespread applications such as the high speed visual servo and the high-performance trajectory learning for robot manipulators, as well as the control strategies which require accurate velocity information.

A new nonlinear filter for parameters identification in dynamic systems and application to a transmission channel

In this paper we propose general nonlinear models for off-line and on-line parameters identification in dynamic systems. These numerical filters can be applied to any nonlinear system represented by a state equation and an observation equation both nonlinear. The theory of hidden Markov models is used to derive these algorithms starting from a of Baum & Welch type method. The proposed identification algorithm has two levels: the first level is an iterative and global algorithm (IGA), it estimates iteratively the parameters from a block of data. The second level is an ergodic recursive algorithm (ERA), it estimates the parameters in an adaptive manner. The estimators defined by these algorithms converge almost surely to the true values of the model parameters studied in [A. Khoukhi, T. Aliziane, M. Souilah, Un Algorithme Multi-Niveau d’Identification d’un Canal en Communication Numérique, JESA 36(4) (2002) 519–537; M. Souilah, A. Khoukhi, T. Aliziane, A new multi-level algorithm for identification and stochastic adaptive control of industrial manipulators, Eng. Simulation 26(4) (2004) 83– 98; M. Souilah, A new strategy for identification and control of mobile robots, Eng. Simulation 28(3) (2006) 35–48]. The advantage of the proposed nonlinear filters in relation to classical autoregressive models is the fact that the nonlinearity of the model is taken into account as it is and no linearizations are made around a nominal position. The variances of the added noises are also estimated. The mathematical convergence of the algorithms IGA and ERA is an open problem in the general case. We propose to this end an interesting conjecture based on ergodic theory. These algorithms are applied to identify the parameters of a transmission channel in data communication. Some simulation results showing the convergence of these algorithms are given.

Theoretical Investigation of Time Suboptimal Control of Industrial Manipulators Along Specified Paths

A method for the time suboptimal control of an industrial manipulator from an initial position and orientation to a final position and orientation as it moves along a specified path is proposed. Nonlinear system equations that describe the manipulator motion are linearized at each time step along the path. A method which gives the control inputs (joint angular velocities) for time suboptimal control of the manipulator is developed. In the formulation, joint angular velocity and acceleration limitations are also taken into consideration. A six degree of freedom elbow type manipulator is used in numerical examples to verify the method developed.

Friction compensation in hybrid force/velocity control of industrial manipulators

This paper deals with the implementation of a hybrid force/velocity controller for the automatic edge following of two-dimensional unknown planar contours performed by an industrial robot manipulator. In particular, the authors address the problem of compensating the joint friction effects that have to be taken into account in the controller design in order to achieve a reasonable performance with regards to normal force and tangential velocity errors. For that reason, two model-based friction-compensation methods are compared: a static method, based on a previously identified model, and an adaptive method, where joint friction parameters are recursively updated. By means of an extensive experimental activity, it is shown that, in spite of its simplicity and despite the friction effects changing in time during the robot operations, the devised adaptive procedure obtains a high performance in different operating conditions.

On the use of velocity feedback in hybrid force/velocity control of industrial manipulators

This paper deals with the implementation of a hybrid force/velocity control for contour tracking tasks of unknown objects performed by industrial robot manipulators. In particular, we address the problem of the configuration dependent dynamics of the manipulator in constrained motion and we propose a method, based on inertial and stiffness ellipses, that allows to predict the presence of the consequent force oscillations. We also show that these oscillations can be highly reduced by employing an additional normal velocity feedback loop. A large number of experimental results obtained with a two degrees-of-freedom SCARA robot are shown.

Time suboptimal control of industrial manipulators along specified paths while keeping an end-effector orientation unchanged

A method for the time suboptimal control of an industrial manipulator that moves along a specified path while keeping its end-effector orientation unchanged is proposed. Nonlinear system equations that describe the manipulator motion are linearized at each time step along the path. A method which gives control inputs (joint angular velocities) for time suboptimal control of the manipulator is developed. In the formulation, joint angular velocity and acceleration limitations are also taken into consideration. A six degree of freedom elbow type manipulator is used in a case study to verify the method developed.

Dynamic Control of Industrial Manipulators by Software and their Controller

We present the design of a pre-shaping module that feeds an industrial robot controller with a pseudo-reference trajectory and guarantees that the controller output acts as a required nonlinear control scheme. This is to enable the rapid testing and prototyping of control schemes on real robots without having to intervene with the hardware and low level software of their industrial controllers.

Modelling and control of a deformable-link flexible-joint robot

Prsent studies on industrial manipulator control either completely neglect structural flexibility or only consider manipulator link flexibility. Ignoring joint flexibility may cause significant errors in gross motion control if the joint elastic effect is predominant. A control scheme that can effectively compensate for the motion disturbances due to simultaneous existence of link and joint flexibility is presented. The manipulator dynamics is first formulated by a superposition of two models. An assumed modes of vibration is proposed to model the flexible links and a linear torsional spring to model the elastic joint. Then, a non-linear feedback rate servo control system is developed that compensates for the gross motion bias introduced by both joint elasticity and link flexibility. Motion simulation results show that the proposed modelling technique can effectively describe the dynamic behaviour of a flexible-link, elastic-joint robot. They also verify that the proposed controller is robust in that it c...

Formulation and control of robots with link and joint flexibility

SUMMARYPresent study on industrial manipulator control either completely neglects structural flexibility or only considers manipulator link flexibility. Ignoring joint flexibility may cause significant errors in gross motion control if the joint elastic effect is predominant. This paper presents an effective control scheme which can compensate for the motion errors generated by simultaneous existence of both link and joint flexibility. The manipulator dynamics is formulated comprehensively by a superposition of two models, namely, an assumed modes of vibration model for links and a torsional spring model.for joints. Then, a nonlinear feedback rate servo control system is developed that compensates for the gross motion errors introduced by both joint elasticity and link flexibility. Motion simulation results show that the proposed formulation can effectively describe the dynamic behavior of a flexible-link, elastic-joint robot. They also verify that the proposed controller is robust in that it can satisfactorily suppress the manipulator end oscillations and yield an accurate gross motion.

Model‐based control of industrial manipulators: An experimental analysis

AbstractModel‐based control techniques for industrial robotic manipulators were experimentally analyzed. The case study for the analysis was the first three joints of a PUMA‐560. Development of an advanced control evaluation environment removed the computational restrictions of previous studies. The specific issues of: incomplete and/or asynchronous dynamic compensation, feedback paradigm selection, payload sensitivity, and drive systems effects were experimentally analyzed. Evaluation results clearly demonstrate that the performance improvement capability of model‐based control is not restricted to research robots. A model‐based controller with complete feedforward compensation and sliding mode feedback reduced the maximum tracking error by at least a factor of five when compared to feedback alone. End‐effector payload invariant tracking only requires mass information. Tracking performance is not dependent on dynamic compensation at the servo rate. Evaluation results provide insight for adaptive control law design and a baseline to compare their performance against.

Control of Industrial Manipulators With Bounded Uncertainties

Present on-line control schemes for robotic manipulators require high computing power to perform real-time estimation and adaptation and/or an exact model of the manipulator. These requirements result in impractical control schemes for real industrial manipulators. This paper presents a new robust tracking control technique for industrial manipulators in the presence of various uncertainties. It does not require an exact model of the manipulator and it compensates for uncertainties in the system dynamics, such as friction, and uncertain inputs including load variations. The controller consists of two portions: one for the nominal part of the system, and the other portion for uncertainties compensation. This control scheme is simulated for a General Electric P50 robot and the results are presented.

Comments on "Suboptimal control of industrial manipulators with a weighted minimum time-fuel criterion

In the above paper, a method for weighted minimum time-fuel control was introduced and successfully applied to robotic manipulator control. This note discusses an input inequality constraint required to guarantee its success in other applications.