Robot Identification Research Articles

Dynamic Parameter Identification of Collaborative Robot Based on WLS-RWPSO Algorithm

Parameter identification of the dynamic model of collaborative robots is the basis of the development of collaborative robot motion state control, path tracking, state monitoring, fault diagnosis, and fault tolerance systems, and is one of the core contents of collaborative robot research. Aiming at the identification of dynamic parameters of the collaborative robot, this paper proposes an identification algorithm based on weighted least squares and random weighted particle swarm optimization (WLS-RWPSO). Firstly, the dynamics mathematical model of the robot is established using the Lagrangian method, the dynamic parameters of the robot to be identified are determined, and the linear form of the dynamics model of the robot is derived taking into account the joint friction characteristics. Secondly, the weighted least squares method is used to obtain the initial solution of the parameters to be identified. Based on the traditional particle swarm optimization algorithm, a random weight particle swarm optimization algorithm is proposed for the local optimal problem to identify the dynamic parameters of the robot. Thirdly, the fifth-order Fourier series is designed as the excitation trajectory, and the original data collected by the sensor are denoised and smoothed by the Kalman filter algorithm. Finally, the experimental verification on a six-degree-of-freedom collaborative robot proves that the predicted torque obtained by the identification algorithm in this paper has a high degree of matching with the measured torque, and the established model can reflect the dynamic characteristics of the robot, effectively improving the identification accuracy.

ИДЕНТИФИКАЦИЯ В СФЕРЕ ИСКУССТВЕННОГО ИНТЕЛЛЕКТА И РОБОТОТЕХНИКИ: СРАВНИТЕЛЬНОЕ ИССЛЕДОВАНИЕ

The article examines the identification of artificial intelligence and robotic systems. The authors conducted an analysis of regulatory and recommendatory acts of foreign countries, which demonstrates the main trends of the use of identification in the framework of legal regulation. Empirical material, based on which the study was conducted, includes information on identification on the territory of the USA, European Union, China, Japan, South Korea, UAE, Singapore, Canada, UK, Germany. As a result, the authors identified not only the main approaches, goals and objectives of the use of identification of artificial intelligence and robots, but also structured the legal principles derived from them, which are interconnected with the branch of information law.

Improved subspace modal identification of industrial robots

AbstractIndustrial robots have become key components for manufacturing automations due to their larger workspaces and flexibility. However, low stiffness and high compliance of industrial robots may inevitably lead to vibration by self‐excitation or periodic force dependent on workspace configuration. Therefore, the knowledge of the robot's modal properties should be accurately required to enhance the operation accuracy of industrial robots. To improve the identification accuracy of experimental modal parameters of field industrial robots, an improved subspace identification method is proposed to perform nonlinear iterative optimization for updating the state parameters of industrial robots. Experimental response measurement of a six‐degrees‐of‐freedom industrial robot is carried out to obtain modal parameters under various poses. The identification results of the improved subspace modal method are preferable to that of the traditional method. Moreover, the reconstructed three‐dimension working frequency space is presented to exactly characterize experimental modal frequencies throughout its workspace. The proposed method effectively improves the identification accuracy of modal parameters when compared with the traditional algorithms and the influence of robots' pose change on modal parameters is also investigated by experimental modal measurements.

Kinematic Parameter Identification of Industrial Robot Based on Binocular Vision

Kinematic Parameter Identification of Industrial Robot Based on Binocular Vision

A Review of Cuspidal Serial and Parallel Manipulators

Abstract Cuspidal robots can move from one inverse or direct kinematic solution to another without ever passing through a singularity. These robots have remained unknown because almost all industrial robots do not have this feature. However, in fact, industrial robots are the exceptions. Some robots appeared recently in the industrial market can be shown to be cuspidal, but, surprisingly, almost nobody knows it and robot users meet difficulties in planning trajectories with these robots. This article proposes a review on the fundamental and application aspects of cuspidal robots. It addresses the important issues raised by these robots for the design and planning of trajectories. The identification of all cuspidal robots is still an open issue. This article recalls in details the case of serial robots with three joints, but it also addresses robots with more complex architectures such as 6-revolute-jointed robot and parallel robots. We hope that this article will help disseminate more wide knowledge on cuspidal robots.

Efficient System Identification of a Two-Wheeled Robot (TWR) Using Feed-Forward Neural Networks

System identification of a Two-Wheeled Robot (TWR) through nonlinear dynamics is carried out in this paper using a data-driven approach. An Artificial Neural Network (ANN) is used as a kinematic estimator for predicting the TWR’s degree of movement in the directions of x and y and the angle of rotation Ψ along the z-axis by giving a set of input vectors in terms of linear velocity ‘V’ (i.e., generated through the angular velocity ‘ω’ of a DC motor). The DC motor rotates the TWR’s wheels that have a wheel radius of ‘r’. Training datasets are achieved via simulating nonlinear kinematics of the TWR in a MATLAB Simulink environment by varying the linear scale sets of ‘V’ and ‘(r ± ∆r)’. Perturbation of the TWR’s wheel radius at ∆r = 10% is introduced to cater to the robustness of the TWR wheel kinematics. A trained ANN accurately modeled the kinematics of the TWR. The performance indicators are regression analysis and mean square value, whose achieved values met the targeted values of 1 and 0.01, respectively.

Optimized System Identification of Humanoid Robots with Physical Consistency Constraints and Floating-based Exciting Motions

Generally, robots are initially designed via computer-aided software to obtain their parameters. However, the given parameters are not entirely true due to their unmodeled parts; therefore, system identification is needed, and physical conditions are crucial to guarantee feasible solutions. This study uses a quadratic programming regression model accompanied by physical consistency constraints and designs specific exciting motions for humanoid robots. The proposed constraints are designed based on the geometric approximation of link objects, the physically reasonable mass and inertia and the total mass of the robot being correct. The proposed exciting motions include the general walking motion and the single-leg support motion, which enable a more flexible and stable way to cause excitation in the floating-base system. The identified parameters are evaluated on the humanoid robot NINO. Furthermore, the error between the feedback information of the zero moment point and the command information of the center of mass are used for evaluating the identified dynamic parameters. According to the experiments with the proposed exciting motions, the identified parameters are found to be obviously better than the original computer-aided design parameters, especially in the [Formula: see text] direction.

Variable Stiffness Identification and Configuration Optimization of Industrial Robots for Machining Tasks

Industrial robots are increasingly being used in machining tasks because of their high flexibility and intelligence. However, the low structural stiffness of a robot significantly affects its positional accuracy and the machining quality of its operation equipment. Studying robot stiffness characteristics and optimization methods is an effective method of improving the stiffness performance of a robot. Accordingly, aiming at the poor accuracy of stiffness modeling caused by approximating the stiffness of each joint as a constant, a variable stiffness identification method is proposed based on space gridding. Subsequently, a task-oriented axial stiffness evaluation index is proposed to quantitatively assess the stiffness performance in the machining direction. In addition, by analyzing the redundant kinematic characteristics of the robot machining system, a configuration optimization method is further developed to maximize the index. For numerous points or trajectory-processing tasks, a configuration smoothing strategy is proposed to rapidly acquire optimized configurations. Finally, experiments on a KR500 robot were conducted to verify the feasibility and validity of the proposed stiffness identification and configuration optimization methods.

Ultrasound–integrated robotic identification of an isolated deep infiltrating endometriosis nodule of the sigmoid colon

In cases of isolated sigmoid colon deep infiltrating endometriosis (DIE), intraoperative inspection might not be enough for delineation of the lesion. Here, we present a novel approach where an intraoperative ultrasound–integrated robotic system is utilized to scan the sigmoid colon for identifying the affected segment to limit resection only to the involved area (Figure 1). Different surgical approaches including shaving, discoid excision, and segmental resection can be utilized to treat rectosigmoid DIE.

Weld Seam Identification and Tracking of Inspection Robot Based on Deep Learning Network

The weld seams of large spherical tank equipment should be regularly inspected. Autonomous inspection robots can greatly enhance inspection efficiency and save costs. However, the accurate identification and tracking of weld seams by inspection robots remains a challenge. Based on the designed wall-climbing robot, an intelligent inspection robotic system based on deep learning is proposed to achieve the weld seam identification and tracking in this study. The inspection robot used mecanum wheels and permanent magnets to adsorb metal walls. In the weld seam identification, Mask R-CNN was used to segment the instance of weld seams. Through image processing combined with Hough transform, weld paths were extracted with a high accuracy. The robotic system efficiently completed the weld seam instance segmentation through training and learning with 2281 weld seam images. Experimental results indicated that the robotic system based on deep learning was faster and more accurate than previous methods, and the average time of identifying and calculating weld paths was about 180 ms, and the mask average precision (AP) was about 67.6%. The inspection robot could automatically track seam paths, and the maximum drift angle and offset distance were 3° and 10 mm, respectively. This intelligent weld seam identification system will greatly promote the application of inspection robots.

Experimental study on a novel simultaneous control and identification of a 3-DOF delta robot using model reference adaptive control

Delta robot is one of the most widely used parallel robots in the robotics industry. Therefore, it is vital to employ appropriate methods to control Delta robot in order to perform a specific task. Modeling parallel robots is a complex and time consuming task where model-based methods which are mainly dependent to accurate modeling, lose their performance in confronting with model uncertainties and disturbances. In this paper, a novel simultaneous control-and-identification structure is proposed for Multi-Input Multi-Output (MIMO) time-varying systems with unknown parameters which guarantees closed-loop stability and simultaneous identification in presence of model uncertainties and disturbances. Therefore, the unknown parameters of system can be acquired without any prior knowledge from the outset; thus, the suggested method becomes more attractive for robotics system having sophisticated models. For the purpose of this paper, the proposed algorithm is practically implemented on a 3 Degrees-of-Freedom (DOF) Delta parallel robot. The result of simulation and practical implementation are compared with three well known methods which have been previously implemented on the robot, namely PID, adaptive method, and sliding mode control algorithm. In this regard, the results both in simulation and practical implementation reveal remarkable performance for the suggested method in compare with other aforementioned algorithms.

Team robot identification theory (TRIT): robot attractiveness and team identification on performance and viability in human–robot teams

Prior literature suggests that shared identity and social attraction between team members and their robots can be vital for the human–robot interaction. However, more attention is needed to understand the potential performance benefits associated with team identification (TI) and robot attractiveness in human–robot teams. We proposed a theoretical framework of team robot identification theory. We conducted a laboratory experiment to examine the impacts of TI and social attraction toward robots on team performance and viability in 30 human–robot teams comprising two humans and two physical robots. Results showed that TI in human–robot teams led to better performance and team viability. Both effects were mediated by the social attraction between team members and their robots. These results evidenced the direct links between TI and objective and subjective team outcomes, explained through social attraction toward robots. We discuss the results and their theoretical and practical implications.

Non-redundant inertial parameters determination for dynamic identification of branched articulated robots

PurposeBranched articulated robots (BARs) are highly non-linear systems; accurate dynamic identification is critical for model-based control in high-speed and heavy-load applications. However, due to some dynamic parameters being redundant, dynamic models are singular, which increases the calculation amount and reduces the robustness of identification. This paper aims to propose a novel methodology for the dynamic analysis and redundant parameters elimination of BARs.Design/methodology/approachAt first, the motion of a rigid body is divided into constraint-dependent and constraint-independent. The redundancy of inertial parameters is analyzed from physical constraints. Then, the redundant parameters are eliminated by mapping posterior links to their antecedents, which can be applied for re-deriving the Newton–Euler formulas. Finally, through parameter transformation, the presented dynamic model is non-singular and available for identification directly.FindingsNew formulas for redundant parameters elimination are explicit and computationally efficient. This unifies the redundant parameters elimination of prismatic and revolute joints for BARs, and it is also applicable to other types of joints containing constraints. The proposed approach is conducive to facilitating the modelling phase during the robot identification. Simulation studies are conducted to illustrate the effectiveness of the proposed redundant parameters elimination and non-singular dynamic model determination. Experimental studies are carried out to verify the result of the identification algorithm.Originality/valueThis work proposes to determine and directly identify the non-redundant dynamic model of robots, which can help to reduce the procedure of obtaining the reversible regression matrix for identification.

Team Robot Identification Theory (TRIT): Robot Attractiveness and Team Identification on Performance and Viability in Human–Robot Teams

Team Robot Identification Theory (TRIT): Robot Attractiveness and Team Identification on Performance and Viability in Human–Robot Teams

FESM-based approach for stiffness modeling, identification and updating of collaborative robots

PurposeThe purpose of this paper is to introduce a method for stiffness modeling, identification and updating of collaborative robots (cobots). This method operates in real-time and with high precision and can eliminate the modeling error between the actual stiffness model and the theoretical stiffness model.Design/methodology/approachTo simultaneously ensure the computational efficiency and modeling accuracy of the stiffness model, this method introduces the finite element substructure method (FESM) into the virtual joint method (VJM). The stiffness model of the cobots is built by integrating several 6-degree of freedom virtual joints that represent the elastic deformation of the cobot modules, and the stiffness matrices of these modules can be identified and obtained by the FESM. A model-updating method is proposed to identify stiffness influence coefficients, which can eliminate the modeling error between the actual prototype model and the theoretical finite element model.FindingsThe average relative error and the cycle time of the proposed method are approximately 6.14% and 1.31 ms, respectively. Compared with other stiffness modeling methods, this method not only has high modeling accuracy in high dexterity poses but also in low dexterity poses.Originality/valueA hybrid stiffness modeling method is introduced to integrate the modeling accuracy of the FESM into the VJM. Stiffness influence coefficients are proposed to eliminate the modeling error between the theoretical and actual stiffness models.

An Approach for Predicting Stiffness of a 5-DOF Hybrid Robot for Friction Stir Welding

This paper presents an approach for stiffness identification of a 5-DOF hybrid robot named TriMule for friction stir welding. The novelty of this approach is to visualize the realistic robotic system that considers the elastic deflections of all joints and links as a fictitious robotic system that only considers the elastic deflections of joints along their axes. Thus the number of parameters to be identified is reduced significantly. The stiffness identification is essentially implemented by the following four steps: (1) formulating the Cartesian stiffness model that maps the joint compliances of the fictitious system to the deflection twist of the end-effector, (2) parameterizing the joint compliances by a set of polynomial functions in terms of nominal actuated joint variables, (3) constructing the multiple linear regression equations by projecting the measured elastic deflections from the operational space onto the joint space, and (4) estimating the polynomial coefficients by robust biased estimation. The stiffness identification experiment and offline compensation experiment for the tool path deviations are carried out on a prototype machine to demonstrate the effectiveness of the proposed approach.

Disruptive technology identification of intelligent logistics robots in AIoT industry: Based on attributes and functions analysis

AbstractThis research constructs a disruptive technology identification framework based on attributes and functions and selects intelligent logistics robot technology for empirical analysis in the artificial intelligence & Internet of Things (AIoT) industry. We take the three attributes of technological novelty, breakthrough, and influence as measurement indicators to identify disruptive technologies and perform functional analysis of the technology to find potential markets for disruptive technologies. The research demonstrates that two‐dimensional code technology, sensing technology, intelligent control technology, artificial intelligence technology, and wireless communication technology are disruptive technologies in intelligent logistics robots. The future development directions of intelligent logistics robots include efficient, intelligent control operations, good human‐computer interaction, accurate safety obstacle avoidance, and accurate and efficient position detection. This research has put forward the future development direction of disruptive technology in AIoT and provided a reference for the R&D and manufacture of intelligent logistics robots.

Research on risk prediction method of software robot based on artificial intelligence

Aiming at the problem of software robot’s recognition of life scenes, this paper studies the recognition and judgment method based on AI edge computing. Based on artificial intelligence methods and the theory of edge computing, through the analysis of the overall architecture of edge computing, the scene judgment rules and recognition algorithms are clarified. Mainly, the feature extraction and recognition part of the software robot image recognition function is arranged in the edge server, so that the judgment and recognition can be quickly realized and the system operation efficiency can be improved. The experimental verification shows that: under the same conditions, the software robot identification error of the method in this paper is lower, and the calculation time is shorter than that of other software robots, which is far superior to the traditional identification method. At the same time, by changing the comparison of data receiving methods, it can also be proved that the use of edge computing is more efficient, and the recognition problems in the work of software robots can be realized.

Operational kinematic parameter identification of industrial robots based on a motion capture system through the recurrence way

This article introduces a new kinematic identification approach for serial robots using a motion capture system in the recurrence way. This method is based on the motion capture system as a measuring instrument, which can measure and identify the robot’s movements in any feasible domain. Different from the traditional method of obtaining measurement information from the end effector of a robot, multiple markers pasted on a robot each joint are identified and tracked by a motion capture system to obtain the 3-D coordinates of markers of each joint in every frame when the robot is being moved continuously. After optimally fitting the rotation matrix and the translation vector of each joint according to the singular value decomposition, the joint axis vectors and DH parameters can be reconstructed in the recurrence way. Both simulation and experiment of a six revolute joint robot are conducted to verify the effectiveness and efficiency of the method. The identification results including 3 invariants are close to the accuracy of the laser tracker. Interestingly, the identified joint angle is in close proximity to that obtained by the control system of the calibration robot.

Dynamic Modeling of a Nonlinear Two-Wheeled Robot Using Data-Driven Approach

A system identification of a two-wheeled robot (TWR) using a data-driven approach from its fundamental nonlinear kinematics is investigated. The fundamental model of the TWR is implemented in a Simulink environment and tested at various input/output operating conditions. The testing outcome of TWR’s fundamental dynamics generated 12 datasets. These datasets are used for system identification using simple autoregressive exogenous (ARX) and non-linear auto-regressive exogenous (NLARX) models. Initially the ARX structure is heuristically selected and estimated through a single operating condition. We conclude that the single ARX model does not satisfy TWR dynamics for all datasets in term of fitness. However, NLARX fitted the 12 estimated datasets and 2 validation datasets using sigmoid nonlinearity. The obtained results are compared with TWR’s fundamental dynamics and predicted outputs of the NLARX showed more than 98% accuracy at various operating conditions.