Kinematic analysis of a novel 3-DOF actuation redundant parallel manipulator using artificial intelligence approach
Introduction
A parallel kinematic manipulator is a closed-loop mechanism, in which the end-effector is connected to the base by at least two independent kinematic chains. Generally, it comprises two platforms, which are connected by joints and legs acting in parallel [1]. Nowadays, many applications of parallel robots can be found in various industrial fields, such as manufacturing production configurations [2], micro-motion parallel robot for medical applications [3], assembly robot in automotive applications [4], deep sea exploration [5], and so on. More recently, they have been used in the development of high precision machine tools [6].
Redundancy in parallel manipulators is divided into kinematic redundancy and actuation redundancy [7]. This paper introduces a novel 3-DOF parallel manipulator with actuation redundancy, which can be used as a micro-motion platform. Because the design and analysis of a parallel manipulator with actuation redundancy is very complex, therefore, only the kinematic analysis is given, the issues regarding dynamic, stiffness analysis, and workspace optimization will be presented in other sources.
Kinematic analysis includes inverse kinematics and forward kinematics. Forward kinematic problem (FKP) is to compute the position and orientation of the end-effector of the manipulator based on a set of joint angles. In most cases, joint angles can be computed independently. However, the forward kinematics problem of parallel manipulators is generally complicated.
Different efforts have been made in solving FKP either in general cases or in special cases. Generally, there are four different methods to solve this problem: analytical approaches; use of additional sensors or transducers; numerical methods; and neural network based approaches [8]. Some scholars applied Newton–Raphson method [9], [10], [11] or other analytical approaches for solving the FKP [12], [13], [14], [15], [16], [17]. However, most of these analytical approaches were devised for special configurations of parallel manipulators [8]. To address this issue of generalization, numerical approaches, e.g., Newton–Raphson method, have been proposed [18], [19], [20], [21], [22]. Recently, artificial neural network methodology has received considerable attention for solving the FKP of parallel robots, and some meaningful results have been achieved [8], [23], [24].
Although artificial neural network (ANN) is a useful tool for solving the FKP of parallel robot, it still has some intrinsic disadvantages: (1) the multi-layer neural networks cannot be adapted for on-line application, while the control system of a parallel robot requires real-time processing. (2) The ability of the artificial neural network to map the input and output relation is completely dependent on the accurate training of the system, the sample size is large and the training method is crucial. A very large amount of data is required in order to ensure that the results are statistically accurate. (3) It has the problems such as slow convergence speed, local minima, and poor generalization. Therefore, it is necessary to investigate other methods in order to solve the FKP of parallel robots.
Unlike empirical risk minimization used in other methods, Support Vector Machine (SVM) introduced by Vapnik [26], is based on the principle of structural risk minimization. It is originated in modern statistical learning theory, and has found a wide range of real-world applications recently. In good generalization, the absence of local minima and the sparse representation of solution are the advantages of considering SVM as one of the powerful tools for classification and regression. Zha [27] used SVM for solving the FKP of a 6-SPS Stewart platform, some basic results were obtained.
In this paper, we plan to investigate an SVM regression for solving the FKP of the novel 3-DOF parallel manipulator with actuation redundancy. The results show that SVM is more powerful for FKP of robots compared with other intelligent methods, such as MLP and RBF neural networks.
In the following sections, first, geometric modeling and kinematic analysis of the parallel robot are developed, and then an overview of an SVM is presented. The results from the applications of the SVM and neural networks to solve the FKP of the parallel manipulator are presented and the results are compared. Finally, the conclusion and future work are given.
Section snippets
Geometric modeling
The proposed 3-DOF parallel manipulator with actuation redundancy and a passive leg is shown in Fig. 1, Fig. 2. This manipulator is composed of a moving plate, a fixed base, four (4) limbs with identical kinematic structure and one (1) passive limb. The four (4) limbs connect the fixed base by a universal joint followed by a prismatic joint and a spherical joint attached to the moving plate. A linear actuator drives each prismatic joint. The 5th leg is fixed on the base platform, followed by a
An overview of support vector machine
Suppose that there is a training data set , each xi⊂Rm represents the input space of the sample and has a corresponding target value yi⊂R for i=1, … , m, where m corresponds to the size of the training data [26], [29]. The purpose of support vector machine regression is to construct a hyperplane that can approximate a nonlinear input–output mapping accurately to determine a specific nonlinear function with the black box method.
The generic support vector regression (SVR)
Workspace analysis and training data set
Based on the kinematic model developed, the structural parameters can be optimized in the sense that the motion range of the end-effector can be maximized. As shown in Table 2, the motion range of the z-translation is 130–180 mm. The motion ranges of x-and y-rotations are about ±15°. To get the training data set, we use the closed-form solution of the inverse kinematic position within the workspace of the robot, i.e., four actuator displacements were from solution of the inverse kinematics
A comparison of SVM and ANN methods
Neural networks are used for solving FKP in the sense that they are able to create internal representations through training example sets. Due to their learning capabilities, they are often applied as adaptive function estimators to estimate the input–output relation of a system. Therefore, they are utilized to represent the mapping from the joint space to the work space. Forward neural network with back propagation algorithm and radial basis function (RBF), which is the most widely used neural
Conclusions
In this paper, a novel 3-DOF parallel manipulator with an actuation redundancy is introduced and an SVM based modeling method is applied for FKP solution of the proposed parallel robot. The same as ANN, SVM can learn any highly nonlinear functions when it is used for regression, but adopting a completely different way. The formulation embodies the structural risk minimization principle, as opposed to the empirical risk minimization, which ANN is based on. This feature makes SVM have good
Acknowledgment
The authors would like to acknowledge the financial support from the Natural Sciences and Engineering Research Council of Canada (NSERC). The first author gratefully acknowledges the financial support from the Canada Research Chairs program.
References (34)
Forward displacement analysis of general six-in-parallel SPS (Stewart) platform manipulators using soma coordinates
Mech Mach Theory
(1996)- et al.
Forward kinematics of the general 6–6 Stewart platform using algebraic elimination
Mech Mach Theory
(2001) - et al.
Forward kinematics solution of Stewart platform using neural networks
Neurocomputing
(1997) - et al.
Predicting defect-prone software modules using support vector machines
J Syst Software
(2008) Parallel robots
(2000)- et al.
Low speed motion control of a mechanical system
Dyn Control
(1993) - Merlet J.P., 2001, Micro parallel robot MIPS for medical applications. In IEEE Int. Conf. Emerg Technol Fact Autom,...
Industrial robots: fast, nimble at 30
Control Eng
(2002)Field and service applications – exploring deep sea by teleoperated robot – an underwater parallel robot with high navigation capabilities
IEEE Robot Autom Mag
(2007)- Zhang D., Bi Z. Development of reconfigurable parallel kinematic machines using modular design approach, 3rd CDEN/RCCI...
Advances in robot kinematics: analysis and design
Solving the forward kinematics problem in parallel manipulators using an iterative artificial neural network strategy
Int J Adv Manuf Technol
Solving the forward kinematics of a Gough-type parallel manipulator with interval analysis
Int J Robot Res
Direct kinematic solution of a Stewart platform
IEEE Trans Robot Autom
Kinematics of a hybrid series-parallel manipulation system
J Dyn Syst Meas Control
Direct kinematics of the 6–4 fully parallel manipulator with position and orientation decoupled
A closed-form forward kinematics solution for the 6–6p Stewart platform
IEEE Trans Robot Autom
Cited by (77)
Comparison of different supervised learning algorithms for position analysis of the slider-crank mechanism
2024, Alexandria Engineering JournalTime-varying external archive differential evolution algorithm with applications to parallel mechanisms
2023, Applied Mathematical ModellingSimultaneous path placement and trajectory planning optimization for a redundant coordinated robotic workcell
2018, Mechanism and Machine TheoryCitation Excerpt :In [20], the authors derive the inverse dynamics for an actuated redundant 3-DOF PM by optimizing the driving force using the least squares approach. Various artificial intelligent methods are proposed by Zhang and Lei [21] to solve the IKP of an actuation-redundant 3-DOF PM, such as Multilayer Perceptron Neural Networks (MLPNN), Radial Basis Functions (RBFNN), and Support Vector Machines (SVM). In [22], the authors present a novel approach to on-line collision-free path planning of a two-arm manipulator system.
Modeling and Control of Robotic Manipulators Based on Artificial Neural Networks: A Review
2023, Iranian Journal of Science and Technology - Transactions of Mechanical Engineering