Accuracy Of Robot Research Articles

Efficient data-driven joint-level calibration of cable-driven surgical robots

Accurate joint position estimation is crucial for the control of cable-driven laparoscopic surgical robots like the RAVEN-II. However, any slack and stretch in the cable can lead to errors in kinematic estimation, complicating precise control. This work proposes an efficient data-driven calibration method, requiring no additional sensors post-training. The calibration takes 8–21 min and maintains high accuracy during a 6-hour heavily loaded operating. The Deep Neural Network (DNN) model reduces errors by 76%, achieving accuracy of 0.104∘, 0.120∘, and 0.118 mm for joints 1, 2, and 3, respectively. Compared to end-to-end models, the DNN achieves better accuracy and faster convergence by correcting original inaccurate joint positions. Additionally, a linear regression model offers 160 times faster inference speed than the DNN, suitable for RAVEN’s 1000 Hz control loop, with slight compromises in accuracy. This approach should significantly enhance the accuracy of similar cable-driven robots.

Application of task-autonomous dental robot for lateral window preparation in the maxillary sinus.

The study aimed to investigate the feasibility and accuracy of task-autonomous dental robots for lateral window preparation in the maxillary sinus, as well as to propose 3 indexes for assessing the accuracy of lateral window preparation. Twenty 1:1 resin maxilla models were fabricated, all of which underwent preoperative CBCT and utilized the data to design 40 lateral windows. A task-autonomous dental robot was used to autonomously perform the preparation of 20 lateral windows according to the design under supervision, while another 20 lateral windows were prepared with freehand as control. Morphology of the postoperative lateral windows was obtained using oral scans for accuracy analysis. Three indexes (center displacement, area overlap ratio, and area difference) were used to evaluate the accuracy of lateral window preparation in 2 groups. The Shapiro-Wilk test was used to assess the normal distribution of all variables (α=0.05), and the values of the 3 indexes were evaluated in both groups using 2 independent samples t-tests or rank sum tests, respectively. The lateral window prepared by the robot group had an area overlap ratio of 0.906±0.038, an area difference of 1.65 (0.51, 2.58) mm2, and a center displacement of 0.19±0.09mm, which was better than those in the freehand group (0.730±0.105, 4.86 (1.22, 6.77) mm2, and 1.19±0.60mm). The difference between the 2 groups was statistically significant (P<0.05). The task-autonomous dental robot for maxillary sinus lateral window preparation proposed in this study is feasible, and the indexes used to evaluate the accuracy of window preparation are available. The task-autonomous dental robot prepared the lateral window with higher accuracy than the freehand preparation.

Digital twin-driven virtual commissioning for robotic machining enhanced by machine learning

Robotic machining has been increasingly applied in intelligent manufacturing production lines. Compared with the traditional machine tools, commissioning for robotic machining system (RMS) is particularly important due to the low accuracy of industrial robots (IRs). Traditional site commissioning has large workload and is difficult to handle the multi-source errors. Since digital twin (DT) provides strategies for staying synchronized with the physical entities in whole lifecycle, a DT-driven virtual commissioning (VC) system for RMS is developed in this study to improve machining accuracy and reduce the difficulty of commissioning. Firstly, the framework of DT-driven VC system is designed including several function modules such as interaction, data pre-processing, DT model of RMS (RMSDT), and optimization service. Since RMSDT is the kernel of precise VC, a machine learning-enhanced RMSDT oriented to actual machining path prediction is then constructed based on a proposed joint error equivalent strategy, which can fully consider the coupled multi-source errors of machining robot. After that, a practical consistency retention method for RMSDT is proposed based on a stepwise updating strategy, where the model performance can be maintained with low updating costs. Finally, a visual VC system is developed for the experimental 6-degree of freedom robotic milling platform to verify the feasibility and effectiveness of the VC framework. Multiple experiments are also performed to test the performance of RMSDT and contour error compensation. This study has useful reference for the enterprises engaged in RMS and has positive significance for promoting the robotic machining.

Simultaneous Localization and Mapping Methods for Snake-like Robots Based on Gait Adjustment.

Snake robots require autonomous localization and mapping capabilities for field applications. However, the characteristics of their motion, such as large turning angles and fast rotation speeds, can lead to issues like drift or even failure in positioning and map building. In response to this situation, this paper starts from the gait motion characteristics of the snake robot itself, proposing an improved gait motion method and a tightly coupled method based on IMU and visual information to solve the problem of poor algorithm convergence caused by head-shaking in snake robot SLAM. Firstly, the adaptability of several typical gaits of the snake robot to SLAM methods was evaluated. Secondly, the serpentine gait was selected as the object of gait improvement, and a head stability control method for the snake robot was proposed, thereby reducing the interference of the snake robot's motion on the sensors. Thirdly, a visual-inertial tightly coupled SLAM method for the snake robot's serpentine gait and Arc-Rolling gait was proposed, and the method was verified to enhance the robustness of the visual SLAM algorithm and improve the positioning and mapping accuracy of the snake robot. Finally, experiments proved that the methods proposed in this paper can effectively improve the accuracy of positioning and map building for snake robots.

Neural network–based transfer learning to improve stiffness modeling of industrial robots with small experimental data sets

Stiffness modeling is an essential subject for the composition of robot control. Accurate stiffness modeling is helpful for improving the control accuracy of industrial robots, particularly under dynamic load circumstances. The classic virtual joint modeling (VJM) method is challenging in predicting the deformation of the end-effector throughout the full workspace due to the nonlinear deformation of the robot joint and its serial articulated structure. This paper proposes a full-space stiffness modeling method for robots based on the integration of a multi-layer perceptual (MLP) model and VJM. To provide enough training data for the MLP model, VJM is used to build a stiffness model with a small set of experimental data to generate 106,400 training data. A model-based transfer learning approach is proposed to improve the model’s accuracy and generalization regarding the difference between generated training data and actual experimental data. The VJM stiffness model is compared with the MLP stiffness model and the existing CNN-based transfer learning model based on the same experimental data. Considering the deformation prediction in the three directions in Cartesian space, the mean absolute error, standard deviation, and maximum error of the MLP model are decreased by at least 24.90%, 14.20%, and 8.50%, respectively, than the VJM. These prediction results demonstrate that the proposed modeling technique can significantly increase the accuracy of robot stiffness modeling, which is essential for position compensation in precise motion control of robots under dynamic load.

A survey of offline precision calibration of industrial robots

Abstract. As the need for precision and efficiency grows in industrial manufacturing, the accuracy of industrial robots assumes paramount importance. Nevertheless, factors, such as mechanical structures and assembly processes often introduce errors, compromising robots' positioning and repeatability accuracy. Consequently, precise calibration and compensation of these errors are paramount for optimizing robots performance. A thorough analysis of error sources and the establishment of error models in industrial robots are conducted in the present study, with special attention paid to offline calibration methods. This paper reviews the robot error model building methods and offline accuracy calibration techniques, summarizes the technical difficulties of the calibration task, and proposes the future development direction for the difficulties such as the complexity of error modeling, the difficulty of non-motor calibration calculation, and the traditional stiffness compensation that does not meet the needs of the robot's operation process. The importance of this research lies in its potential to improve the accuracy and reliability of industrial robots, thus contributing to the development of industrial automation.

Robot Localization Method Based on Multi-Sensor Fusion in Low-Light Environment

When robots perform localization in indoor low-light environments, factors such as weak and uneven lighting can degrade image quality. This degradation results in a reduced number of feature extractions by the visual odometry front end and may even cause tracking loss, thereby impacting the algorithm’s positioning accuracy. To enhance the localization accuracy of mobile robots in indoor low-light environments, this paper proposes a visual inertial odometry method (L-MSCKF) based on the multi-state constraint Kalman filter. Addressing the challenges of low-light conditions, we integrated Inertial Measurement Unit (IMU) data with stereo vision odometry. The algorithm includes an image enhancement module and a gyroscope zero-bias correction mechanism to facilitate feature matching in stereo vision odometry. We conducted tests on the EuRoC dataset and compared our method with other similar algorithms, thereby validating the effectiveness and accuracy of L-MSCKF.

An analysis and reliability-based optimization design method of trajectory accuracy for industrial robots considering parametric uncertainties

To address the challenges of poor trajectory accuracy in industrial robots, which has emerged as a technological bottleneck hindering further robots’ applications in high-precision manufacturing industries, this paper proposes a method for the analysis and reliability-based optimization design for industrial robots’ trajectory accuracy considering parametric uncertainties. Firstly, the dynamic equation of an articulated industrial robot with six degrees of freedom is derived, incorporating the Stribeck joint friction model, followed by the uncertain parameter identification of this dynamic model. Subsequently, an uncertainty simulation system for the robot is established based on the constructed dynamic model and the sensitivity of system uncertain parameters to the robot trajectory accuracy is analyzed, where 10 key parameters are obtained among 54 uncertain parameters. Finally, a reliability-based multi-objective optimization design methodology is proposed synthesizing the robot trajectory accuracy, manufacturing cost, and quality loss, to achieve tolerance design of the robot's parameters, and enables minimizing costs and quality losses while ensuring the robot's trajectory accuracy reliability. The performance and practicality of the proposed method were validated using a six-degree-of-freedom rotary joint serial industrial robot as an example.

Innovative Application of Optoelectronic Control Engineering for Safety Assurance of Surgical Robots

As an emerging technology, optoelectronic control engineering has demonstrated a wide range of application potential in surgical robot safety and security. Through a literature review, this paper provides an in-depth discussion on the innovative applications of optoelectronics technology in enhancing the positioning accuracy, environment sensing, supple control and remote operation of surgical robots. At the same time, this paper summarizes the current research hotspots and future research directions, with a view to providing a reference for promoting the technological progress in this field. The current research focuses on improving the operating precision of surgical robots, enhancing the environment sensing ability and the application of force feedback system, while the future research will mainly focus on interdisciplinary cooperation and new technology development.

Suitability of UR5 Robot for Robotic 3D Printing

The present paper describes the measurement of the drift of unidirectional pose accuracy, repeatability, and static compliance of a collaborative robot employing a measurement methodology that relies on the description of a virtual ISO cube placed in the robot’s workspace. The measurements aimed to investigate and assess the suitability of the UR5 six-axis collaborative robot for its application in robotic 3D printing. An experimental laboratory measurement workstation was constructed to perform the measurements, and control measurements were performed. The measurements involved describing the TCP point of the robot tool at five measurement points located in a virtual ISO cube during a minimum of 30 repeated measurement cycles. A camera and six linear incremental sensors with assessment units were used for the measurements. The measurements were performed in compliance with the regulations of STN ISO 9283 standard for this type of measurement. As a result of the measurements, the technical specifications of the drift and static compliance of the controlled robotic arm were verified, and the results were compared with the values specified by the manufacturer. Following the measurements and assessment of the results, it was possible to assess the suitability of the used UR5 robotic arm for its application in robotic 3D printing and to propose possible recommendations for the calibration of the robot and the process settings of the printing system for the production of objects using FDM technology.

Calibration of a dual-robot collaborative system for drilling tasks on spacecraft core cabins

Purpose This study aims to propose a calibration method to enhance the positioning accuracy in dual-robot collaborative operations, aiming to address the challenge of drilling hole spacing errors in spacecraft core cabin brackets that require an accuracy of less than 0.5 mm. Design/methodology/approach Initially, the cooperative error of dual robots is defined. Subsequently, an integrated model is constructed that encompasses the kinematic model errors of the dual robots, as well as the establishment errors of the base and tool frames. A calibration method for optimizing the cooperative accuracy of dual robots is proposed. Findings The application of the proposed method satisfies the collaborative drilling requirements for the spacecraft core cabin. The average cooperative positioning error of the dual robots was reduced from 0.507 to 0.156 mm, with the maximum value and standard deviation decreasing from 1.020 and 0.202 mm to 0.603 and 0.097 mm, respectively. Drilling experiments conducted on a core cabin simulator demonstrated that after calibration, the maximum hole spacing error was reduced from 1.219 to 0.403 mm, with all spacing errors falling below the 0.5 mm threshold, thus meeting the requirements. Originality/value This paper addresses the drilling accuracy requirements for spacecraft core cabins by using a calibration method to reduce the cooperative error of dual robots. The algorithm has been validated through experiments using ER 220 robots, confirming its effectiveness in fulfilling the drilling task requirements.

Inspection robot GPS outages localization based on error Kalman filter and deep learning

In urban environments, inspection robots face complex terrain and variable motion states, posing high demands on their positioning systems. Although the integration of Micro-Electro-Mechanical Systems Inertial Navigation Systems (MEMS-INS) with the Global Positioning System (GPS) provides continuous positioning information, high buildings and tunnels in cities can block GPS signals, leading to signal interruptions and increased positioning errors. During GPS outages, MEMS-INS gradually accumulates errors, severely affecting positioning accuracy. To address this issue, this paper proposes an adaptive error state Kalman Filter (AESKF), which employs an adaptive mechanism to eliminate the noise impact of MEMS-INS and reduce reliance on the process model. Additionally, a deep learning framework based on the Self-Attention mechanism of the Transformer and a custom loss function Long Short-Term Memory (LSTM) module is proposed to predict position increments of the inspection robot. Combining AESKF with Transformer-LSTM achieves optimized positioning accuracy of the inspection robot during GPS outages in dynamic urban environments. Simulation and practical experimental results demonstrate that the combination of AESKF and Transformer-LSTM significantly improves positioning accuracy. Compared to other mature methods, the Root Mean Square Error (RMSE) of positioning is reduced by up to 83.64 % in the north direction and 89.56 % in the east direction. When the GPS signal interruption lasts for 10 s and 60 s, the maximum position error standard deviation (STD) is 0.1186 m and 1.0417 m, respectively.

Industrial robot calibration optimization method based on R-optimal criterion and improved IOOPS algorithm

Abstract In this paper, a novel kinematic parameter calibration method based on the R-optimal criterion and the improved iterative one-by-one pose search (IOOPS) algorithm is proposed to improve the end-effector positioning accuracy of industrial robots. First, a novel industrial robot error calibration model based on the product of exponential model and generalized error model is established, and the ideal pose transformation matrix from the robot base coordinate system to the laser tracker measurement coordinate system is obtained using the least-squares method, thereby obtaining the initial parameter vector of the robot calibration system. Second, various joint angle values at different positions within the robot’s workspace and the corresponding end-effector coordinate data, namely calibration sampling point data, are collected. Subsequently, the improved IOOPS algorithm combined with the observability index O R proposed by the R-optimal criterion is used to select the optimized calibration sampling points. Finally, the optimized sampling point data are combined with the Levenberg–Marquardt algorithm to optimize the parameters and obtain the optimal kinematic parameters. The experimental results show that the average end-effector error of the robot decreases from 0.5822 to 0.2492 mm after calibration using this method, demonstrating the effectiveness of the optimized sampling points in the calibration process achieved through the improved algorithm and the new observability index.

Application of 3D vision and networking technology for measuring the positional accuracy of industrial robots

Application of 3D vision and networking technology for measuring the positional accuracy of industrial robots

Comparison of Positioning Error Prediction Results of Industrial Robots Based on Three Different Types of Neural Networks

ABSTRACTWith the increasing development of industry, the market demand for manufacturing has shifted to large‐scale customized production. This poses new challenges to the production flexibility of industrial robots. The offline programming method can perfectly meet this challenge. But its disadvantage is that it relies heavily on the absolute positioning accuracy of industrial robots. In recent years, there has been an increasing number of studies using neural networks (NN) to predict the positioning errors of industrial robots to improve their absolute positioning accuracy. However, most of these studies only focus on the application of NNs, and do not compare the prediction results and performance of different kinds of NNs. This paper selects three typical network models: backpropagation neural network (BPNN), particle swarm algorithm optimization BPNN (PSO‐BPNN), and radial basis function neural network (RBFNN). Through in‐depth experiments and analysis of these networks, the purpose is to reveal their respective prediction effects and characteristics and to summarize their advantages and disadvantages. Experimental results show that BPNN performs poorly in predicting positioning errors. As an optimization method, the particle swarm algorithm can effectively improve the prediction performance of BPNN. In contrast, the RBFNN performs well, which makes it very suitable for predicting the positioning error of industrial robots.

A stepwise parameter identification strategy for probe-based robot on-machine measurement system calibration based on sensitivity analysis

The probe-based measurement presents an economical and efficient on-machine measurement (OMM) method. However, the low position accuracy of robot presents significant challenges for probe-based robot OMM. To improve the measurement accuracy of robot OMM system, this paper calibrates the geometric parameters of robot OMM system through a closed-loop calibration method with sphere constraint. First, the geometric error model for robot OMM system is established. Given the difficulty in model parameter identification, this paper defines a new index, the relative distance sensitivity index (RDSI), to reveal the contribution of model parameter to relative distance accuracy. Subsequently, sensitivity analysis is conducted on model parameters based on RDSI and model parameters are grouped according to the analysis results. In parameter identification, parameters are identified step by step according to the grouping results. Experiment results show that after calibration, the max distance measurement error of robot OMM system is reduced from 0.54 mm to 0.12 mm.

Vision-guided robot calibration using photogrammetric methods

We propose novel photogrammetry-based robot calibration methods for industrial robots that are guided by cameras or 3D sensors. Compared to state-of-the-art methods, our methods are capable of calibrating the robot kinematics, the hand–eye transformations, and, for camera-guided robots, the interior orientation of the camera simultaneously. Our approach uses a minimal parameterization of the robot kinematics and hand–eye transformations. Furthermore, it uses a camera model that is capable of handling a large range of complex lens distortions that can occur in cameras that are typically used in machine vision applications. To determine the model parameters, geometrically meaningful photogrammetric error measures are used. They are independent of the parameterization of the model and typically result in a higher accuracy. We apply a stochastic model for all parameters (observations and unknowns), which allows us to assess the precision and significance of the calibrated model parameters. To evaluate our methods, we propose novel procedures that are relevant in real-world applications and do not require ground truth values. Experiments on synthetic and real data show that our approach improves the absolute positioning accuracy of industrial robots significantly. By applying our approach to two different uncalibrated UR3e robots, one guided by a camera and one by a 3D sensor, we were able to reduce the RMS evaluation error by approximately 85% for each robot.

A feedforward kinematic error controller with an angular positioning deviations model for backlash compensation of industrial robots

The accuracy of industrial robots, typically on the order of several millimeters, has inhibited their adoption in advanced aerospace manufacturing applications, such as robotic machining. For this reason, extensive investigations have been conducted to develop solutions to improve their accuracy. These solutions can be categorized into offline and online compensation strategies, both of which have advantages and limitations. Offline compensation has been shown to improve the accuracy of industrial robots by two to three orders of magnitude; however, the sensitivity of these solutions to environmental changes and external disturbances can degrade their performance. In contrast, online compensation, which utilizes real-time measurement and compensation, is robust to these changes; however, the performance of these solutions is limited by the causality of time, preventing them from compensating fast changing errors such as backlash. In this work, a novel kinematic modeling strategy, which models the robot’s angular positioning deviations to predict when backlash will occur, is integrated into a novel online kinematic error compensation framework to leverage the advantages of both solutions. By integrating the proposed kinematic model into the online compensation framework, backlash errors can be predicted and preemptively compensated to improve performance. The performance of the combined system was evaluated using ball bar measurements, where it was shown to improve the circularity of the ball bar motion by 25 %.

Method for robot kinematic parameters identification based on position and orientation data obtained with laser tracker.

How to quickly and accurately identify the kinematic parameter errors is an important prerequisite for robot accuracy compensation. The laser tracker is used to measure and identify the kinematic parameters of the robot. The influence of laser tracker layout in robot pose measurement is analyzed, and the evaluation function of laser tracker layout is constructed to determine the optimal layout position. Then, the mapping relationship between the position and orientation deviation of the robot end and the deviation of each kinematic parameter is established, and the kinematic parameter identification model integrating the position and orientation information is constructed. The identification model is compared to the identification model based on position information to clarify the intrinsic reason of high accuracy. Next, aiming at the problem that the genetic algorithm is easy to prematurely converge to the local optimal solution, a hybrid genetic algorithm is constructed by introducing the simplex method to determine the optimal calibration pose set of the robot. On this basis, the results of robot kinematics parameter identification based on position measurement data, pose measurement data, and optimal calibration pose set are compared and analyzed through experiments, which verifies the effectiveness of the robot kinematics parameter identification model based on pose measurement data and optimization strategy.

Research on Visual Recognition of Service Robots Based on YOLO Algorithm

In modern society, based on the aging of population and the rapid development of intelligent technology, the demand for intelligent service robots is increasing, and visual recognition is one of the key technologies of service robots. The rapid development of deep learning technology provides new solutions for visual recognition. Existing target recognition algorithms have the problem of complex model and slow inference speed. According to the above problems, this paper proposes a visual recognition algorithm based on YOLO series, which is used for the visual recognition design scheme of service robot. It can ensure the detection accuracy, reduce the speed of the model complexity, speed up the reasoning, and determine whether to meet the actual needs. Through randomly selected pictures, the results show that the design scheme can effectively improve the detection accuracy and real-time of the service robot on targets, and enhance its autonomous service ability in various complex environments.