Pose Deviation Research Articles

Underwater fluid-driven soft dock for dynamic recovery of AUVs with improved pose tolerance

Recovering autonomous underwater vehicles (AUVs) by a mobile platform is a complex challenge. Traditional docking stations require strict pose deviation from the underwater vehicle. To overcome this issue, we propose a novel solution: an in-situ fluid-driven soft dock. This system comprises three soft robotic manipulators that possess guiding, capturing, and securing functionalities, respectively. We present the design, fabrication, and control methods for each manipulator considering the requirements of underwater docking operations. The theoretically allowable docking pose deviation range during AUV docking is analyzed. Additionally, the required force of soft grippers was evaluated through simulation and equivalent experimental tests. To enable dynamic recovery of AUVs while the soft robotic manipulators remain mobile on the experimental platform, we introduce a hydraulic control method based on attitude and pressure feedback. The test results indicate that the designed soft manipulators can operate and maintain good sealing performance under an external pressure of no less than 11 MPa. Moreover, the soft dock successfully recovered and secured AUVs of two different diameters in 20 dynamic tests, achieving a 90% success rate with a maximum AUV velocity of 1.6 m/s.

Deep learning-based predicting and compensating method for the pose deviations of parallel robots

The static pose accuracy is regarded as a crucial performance indicator for parallel robots, which is inevitably affected by the geometric and nongeometric errors. However, an accurate error model for parallel robots is highly complex, especially for mathematical modeling and identifying non-geometric errors. This limitation hampers the application of parallel robots in high-precision processing and manufacturing fields. To enhance the performance of parallel robots and address the complexities in establishing their error models, a deep learning-based predicting and compensating method is investigated, which can accurately predict their pose deviations. This method ingeniously integrates the spatial feature extraction capabilities of convolutional neural networks, the bidirectional dependency capturing prowess of bilateral long short-term memory networks, and the feature significance discernment offered by squeeze-and-excitation networks. Subsequently, the pose deviations are definitely predicted by this method and are pre-compensated into nominal pose so as to improve the performance. A pose-deviation pairs dataset is established to accomplish the comparison of the investigated method with the two commonly used artificial neural network and long short-term memory on the 6-UPS parallel robot. Experiment on the 6-UPS parallel robot against traditional kinematic calibration methods demonstrate the investigated method achieves satisfactory pose accuracies, with the ability to reduce pose deviations by 88.60 %. Meanwhile, the effectiveness and general applicability of this method have also been validated by successful implementation on a 6-UCU parallel robot.

A cluster-based disambiguation method using pose consistency verification for structure from motion

Structure from motion (SfM) recovers scene structures and camera poses based on feature matching, and faces challenges from ambiguous scenes. There are a large number of ambiguous scenes in real environment, which contain many duplicate structures and textures. The ambiguity leads to incorrect feature matches between images with similar appearance, and makes geometric misalignment in SfM. To address this problem, recent methods have focused on investigating the inconsistencies in feature topology among multi-view images. However, the feature topology is directly derived from 2D images. Thus, it is susceptible to feature occlusion caused by changes in perspective. Therefore, we propose a new method that disambiguates scenes using pose consistency rather than feature consistency. The pose consistency is conducted in 3D geometric space which is less sensitive to feature occlusion. Thus, the pose consistency is more robust than feature consistency. Our core motivation lies that the incorrect matches between ambiguous images will cause pose deviation from the global poses generated by correct matches. To detect this pose deviation, we first combine local and global information of the scene to generate the global reliable camera poses. The local information of each image is obtained by image clustering, and it strengthens the global information that is represented as the verified maximum spanning tree of clusters. Then, the global poses serve as the reference for further pose consistency verification. The global poses also enable us to perform both rotation and translation consistency verification for uncertain matches. During the pose consistency verification, the pose deviation calculated on image-level may be too small to be noticed. Thus, we propose to perform pose consistency verification at cluster-level instead of image-level to amplify the pose deviation. In the experiments, we compared our approach with several state-of-the-art methods, including COLMAP, Geodesic-SfM and TC-SfM, on both ambiguous and regular datasets. The results demonstrate that our approach achieves the best robustness, only our approach succeeds on all ambiguous image sequences (14/14). The quantitative evaluation results on image sequences with ground truth also show that our approach achieves the best accuracy (average RMSE of translation = 0.109, average RMSE of rotation = 0.827) among all methods. The source code of our approach is publicly available at https://github.com/gongyeted/MA-SfM.

Research on a Method of Robot Grinding Force Tracking and Compensation Based on Deep Genetic Algorithm

In the grinding process of complex-shaped cast workpieces, discrepancies between the workpiece’s contours and their corresponding three-dimensional models frequently lead to deviations in the machining trajectory, resulting in instances of under-grinding or over-grinding. Addressing this challenge, this study introduces an advanced robotic grinding force automatic tracking technique, leveraging a combination of deep neural networks and genetic algorithms. Harnessing the capability of force sensing, our method dynamically recalibrates the grinding path, epitomizing truly flexible grinding. Initially, in line with the prerequisites for force and pose tracking, an impedance control strategy was developed, integrating pose deviations with force dynamics. Subsequently, to enhance steady-state force tracking, we employed a genetic algorithm to compensate for force discrepancies caused by positional errors. This was built upon the foundational concepts of the three-dimensional model, impedance control, and environmental parameter estimation, leading to an optimized grinding trajectory. Following tracking tests, it was observed that the grinding’s normal force was consistently controlled within the bracket of 20 ± 2.5 N. To further substantiate our methodology, a specialized experimental platform was established for grinding complex-shaped castings. Optimized strategies were employed under anticipated forces of 5 N, 10 N, and 15 N for the grinding tests. The results indicated that the contact forces during the grinding process remained stable at 5 ± 1 N, 10 ± 1.5 N, and 15 ± 2 N. When juxtaposed with conventional teaching grinding methods, our approach manifested a reduction in grinding forces by 71.4%, 70%, and 75%, respectively. Post-grinding, the workpieces presented a pronounced enhancement in surface texture, exhibiting a marked increase in surface uniformity. Surface roughness metrics, originally recorded at 17.5 μm, 17.1 μm, and 18.7 μm, saw significant reductions to 1.5 μm, 1.6 μm, and 1.4 μm, respectively, indicating reductions by 76%, 73%, and 78%. Such outcomes not only meet the surface finishing standards for complex-shaped castings but also offer an efficacious strategy for robot-assisted flexible grinding.

Docking Pose Measurement Method for Large Components Based on Draw-Wire Displacement Sensors

Abstract A method for measuring the docking pose of large components based on the draw-wire displacement sensor is proposed. In this method, coordinate systems and measurement points are established on the docking surfaces of fixed and moving components. The draw-wire displacement sensor is used to measure the distances between these measurement points. A mathematical model based on the distances between the measurement points is established, and the three-sphere rendezvous positioning principle is optimized to obtain the spatial positions of the measurement points. Consequently, the pose deviations of the fixed and moving components in all six degrees of freedom (6DOF) are determined. A simulation analysis of the measurement uncertainty of the obtained pose deviations is performed, resulting in a composite standard uncertainty obtained from the measurement standard uncertainties of different sensors. The simulation results show that the composite standard uncertainty is most affected in the x-axis translation direction and least affected in the x-axis rotation direction. With this method, only the distances between the measurement points need to be measured to determine the corresponding pose relationships. The cost of the equipment is low, and it is not easily affected by external factors such as the environment.

Robotic Polishing of Unknown-Model Workpieces With Constant Normal Contact Force Control

Industrial robots are increasingly being considered for application in performing polishing operations. Most research has been performed on workpieces with a priori (CAD) model, and used impedance control or hybrid force-position control to achieve constant force operation. For workpieces without priori models, it is still difficult to maintain a constant normal contact force during the polishing process. To address this challenge, this paper proposes a cooperative force-position control method consisting of three parts: constructing a model between contact forces and robotic poses during polishing operations and obtaining a real-time pose deviation of the current tool-workpiece contact state and the desired (normal) contact state; based on the deviation, a method of real-time adjustment of 2D predefined polishing paths to 3D actual polishing paths is proposed; finally, constant normal contact force control is achieved by a direct force control algorithm based on the results obtained from the above method. The proposed method is based on a macro-mini robotic system with an active force control polishing device, and its effectiveness was tested by various unknown-model workpiece polishing scenarios. The results demonstrate that the proposed method can achieve stable normal force tracking and high-quality surfaces during unknown-model workpiece polishing.

A constant plunge depth control strategy for robotic FSW based on online trajectory generation

Robotic friction stir welding (RFSW) usually comes with a huge upsetting force, and the stiffness of the welding system distributes unevenly over the position, which leads to a large deviation of the plunge depth of the tool at the end of the robot. The conventional constant distance tracking control suffers from the problem of unsmooth compensation leading to the vibration of the robot and thus degrading the weld quality. For this problem, a constant plunge depth control based on online trajectory generation for RFSW is studied, which can generate an accurate welding trajectory according to the rough initial reference path and smoothly compensate for the plunge deviation. Initially, three laser-ranging sensors are utilized to measure the pose deviation of the tool in real-time and generate the ideal welding trajectory according to the projection vector method. Then, a deformation compensation model is established to realize the real-time prediction of the correct value. To ensure the smoothness and rapidity of the dynamic tracking process of displacement deviation, we adopt an online trajectory generator as the core of optimization control to meet the process constraints such as speed, acceleration, and jerk during the compensation process. Finally, simulation and experiment are carried out. The results show that the proposed method can effectively reduce the vibration caused by compensation during the welding process and reduce flash, which can improve the welding quality.

A Freehand 3D Ultrasound Reconstruction Method Based on Deep Learning

In the medical field, 3D ultrasound reconstruction can visualize the internal structure of patients, which is very important for doctors to carry out correct analyses and diagnoses. Furthermore, medical 3D ultrasound images have been widely used in clinical disease diagnosis because they can more intuitively display the characteristics and spatial location information of the target. The traditional way to obtain 3D ultrasonic images is to use a 3D ultrasonic probe directly. Although freehand 3D ultrasound reconstruction is still in the research stage, a lot of research has recently been conducted on the freehand ultrasound reconstruction method based on wireless ultrasonic probe. In this paper, a wireless linear array probe is used to build a freehand acousto-optic positioning 3D ultrasonic imaging system. B-scan is considered the brightness scan. It is used for producing a 2D cross-section of the eye and its orbit. This system is used to collect and construct multiple 2D B-scans datasets for experiments. According to the experimental results, a freehand 3D ultrasonic reconstruction method based on depth learning is proposed, which is called sequence prediction reconstruction based on acoustic optical localization (SPRAO). SPRAO is an ultrasound reconstruction system which cannot be put into medical clinical use now. Compared with 3D reconstruction using a 3D ultrasound probe, SPRAO not only has a controllable scanning area, but also has a low cost. SPRAO solves some of the problems in the existing algorithms. Firstly, a 60 frames per second (FPS) B-scan sequence can be synthesized using a 12 FPS wireless ultrasonic probe through 2–3 acquisitions. It not only effectively reduces the requirement for the output frame rate of the ultrasonic probe, but also increases the moving speed of the wireless probe. Secondly, SPRAO analyzes the B-scans through speckle decorrelation to calibrate the acousto-optic auxiliary positioning information, while other algorithms have no solution to the cumulative error of the external auxiliary positioning device. Finally, long short-term memory (LSTM) is used to predict the spatial position and attitude of B-scans, and the calculation of pose deviation and speckle decorrelation is integrated into a 3D convolutional neural network (3DCNN). Prepare for real-time 3D reconstruction under the premise of accurate spatial pose of B-scans. At the end of this paper, SPRAO is compared with linear motion, IMU, speckle decorrelation, CNN and other methods. From the experimental results, it can be observed that the spatial pose deviation of B-scans output using SPRAO is the best of these methods.

Method for the Relative Pose Reconstruction of Hydraulic Supports Driven by Digital Twins

The undulating coal seam floor in a mine leads to the complicated posture of the hydraulic supports. The existing methods for monitoring the pose of hydraulic supports have a poor monitoring effect, and are especially characterized by a lack of support position information. Therefore, this article proposes a relative pose reconstruction method for hydraulic supports driven by digital twins. First, the pose plane and relative pose matrix of the hydraulic support are defined to describe the pose state of the support by analyzing the pose deviation between adjacent supports. Then, a digital twin system is built for a hydraulic support model, and a pose deduction method based on ray detection is proposed. The accurate position and attitude of the hydraulic support are deduced in the virtual space driven by actual laser sensor information, and 3-D pose reconstruction is realized. Finally, a relative pose reconstruction experiment of the hydraulic support model is designed and conducted. The results show that the relative pose data obtained by the virtual reconstruction method are very close to the experimental measurements, and the highest reconstruction accuracy is found to be 97.44%. The feasibility of the laser sensor layout scheme and the virtual reconstruction method of the pose of the hydraulic support is proven. This method provides a new way to monitor the pose of hydraulic supports, and can provide a reference for the support operation of hydraulic supports in the real fully mechanized mining process.

Study on error analysis and correction for catadioptric imaging system: A method for annular inner wall structure measurement

Annular inner wall widely exists in industrial parts, however, because of the limitation of internal narrow space and 360-degree panoramic inspection requirements, the detection of such structures is always difficult. Catadioptric imaging is an effective and rapid detection method for inner wall detection. However, serious distortion always exists due to the alignment deviation and the pose deviation of the structure to be measured, which limits the application of this method. In this paper, firstly, we analyze the main causes and laws of distortion from the perspective of simulation, secondly, based on the simulation result, methods of eliminating distortion are proposed and verified based on the simulation data. Finally, we demonstrate the effectiveness of our proposed method through experiments, based on the experiments, it is proved that the proposed method can solve the limitations of the measurement for catadioptric imaging, and the proposed method can correct distortion to pixel level.

Exploring the usage of supervised driving automation in naturalistic conditions

This study reports usage of supervised automation and driver attention from longitudinal naturalistic driving observations. Automation inexperienced drivers were provided with instrumented vehicles with adaptive cruise control (ACC) and lane keeping (LK) features (SAE level 2). Data was collected comparing one month of driving without support to two months where drivers were instructed to use automation as desired.On highways, level 2 automation was used respectively 63% and 57% of the time by Tesla and BMW users, with peak usage during slow stop-and-go traffic (0–30 km/h) and higher speeds (>80 km/h). On roads with speed limits below 70 km/h, automation was used less than 8%, and use on urban roads was incidental rather than habitual. Automation usage increased with time in trip, but no clear time of day effects were found. Head pose data could not classify driver attention, and we recommend gaze tracking in future studies. Head pose deviation was selected as alternative indicator for monitoring activity. Comparing among forms of automation usage on the highway, head heading deviation was smallest during ACC use, but did not differ between automation and baseline manual driving. Head heading deviation during manual driving was smaller in the baseline than the experimental phase, which suggests that motives for manual highway driving may be attention related. Automation usage did not change much over the first 12 weeks of the experimental condition, and there were no longitudinal changes in head pose deviation.

Combined Predictive and Feedback Contour Error Control With Dynamic Contour Error Estimation for Industrial Five-Axis Machine Tools

This article proposes a real-time method to control the contour error for industrial five-axis machine tools by combining the generalized predictive control (GPC) and the feedback correction (FBC) with dynamic contour error estimation (CEE). The CEE is developed by well considering the curve’s curvature and torsion based on Taylor series expansion and Frenet frame theory. By utilizing the spherical linear interpolation, the tool orientation and the tool tip position are synchronized with respect to the curve length. A novel dynamic foot point searching procedure is established to weaken the influences of the tracking errors’ magnitude on the CEE precision. To tackle the transmission effect, the GPC is adopted to predict the servo systems’ outputs, and then, the induced tool pose deviations, which are subsequently utilized to counteract the contour errors, are predicted by constructing Jacobian matrixes. Especially, the FBC loops are constructed to suppress the influences of disturbances and further to reduce the magnitudes of contour errors. Simulations and experiments are conducted to verify the effectiveness of the proposed methods.

Eye-referenced dynamic bounding box for face recognition using light convolutional neural network

Face recognition systems have imprinted its presence in many applications from offices to security to daily use as in personal digital gadgets. With many Face recognition systems in use, still there is scope for its performance improvement. The performance of such systems suffers due to presence of covariates like non-uniform illumination, pose deviations, occlusions, low resolution etc. Extracting the region of interest from input face images is very crucial steps in face recognition system. We proposed methodology to create a bounding box for every sample face image. This bounding box dynamically tries to fit the face image to cover the relevant face features useful for recognition purpose. We used a light CNN structure to perform the experiment on MUCT face dataset using three different methodologies for extracting region of interests from sample face images using bounding box. These are 1) min-max based ROI 2) OpenCV face alignment and 3) eye-reference based ROI. It is observed that the proposed eye-reference based face alignment method works better than conventional methods of min-max based ROI and OpenCV face alignment with considerable amount of improvement in the recognition accuracy. Our future work includes use of other structured datasets with various covariates for face recognition.

Path Tracking of Underground Mining Boom Roadheader Combining BP Neural Network and State Estimation

This paper proposes a path correction scheduling strategy for the underground mining boom roadheader by ably combining a back propagation (BP) neural network and state estimation. First, a pose deviation-based tracking model is designed for the roadheader, and it is then further studied and optimized by incorporating the benefits of BP neural networks into the model adaptation. Considering the fact that there is skidding between tracks on the ground and errors during the instant pose detection of the roadheader underground, singular value decomposition (SVD)–Unscented Kalman filtering is applied to estimate the real pose deviation, based on the summarized distribution regularities of the track skidding ratios and the pose detection errors, instead of complicated analysis mechanisms. The BP neural network and states estimation are well combined in structure, enabling this scheduling strategy to update the control law and revise the control instruction simultaneously in the procedure. The proposed path tracking model for the roadheader is simple and clear, without adding extra devices or massive algorithms, which is attractive in terms of industrial use. The path tracking simulations show that this proposed strategy achieves path tracking well in different scenarios and is of high adaptability when facing complex trajectory while still giving stable control instructions for the roadheader.

Augmented Reality to Assist Skin Paddle Harvesting in Osteomyocutaneous Fibular Flap Reconstructive Surgery: A Pilot Evaluation on a 3D-Printed Leg Phantom.

BackgroundAugmented Reality (AR) represents an evolution of navigation-assisted surgery, providing surgeons with a virtual aid contextually merged with the real surgical field. We recently reported a case series of AR-assisted fibular flap harvesting for mandibular reconstruction. However, the registration accuracy between the real and the virtual content needs to be systematically evaluated before widely promoting this tool in clinical practice. In this paper, after description of the AR based protocol implemented for both tablet and HoloLens 2 smart glasses, we evaluated in a first test session the achievable registration accuracy with the two display solutions, and in a second test session the success rate in executing the AR-guided skin paddle incision task on a 3D printed leg phantom.MethodsFrom a real computed tomography dataset, 3D virtual models of a human leg, including fibula, arteries and skin with planned paddle profile for harvesting, were obtained. All virtual models were imported into Unity software to develop a marker-less AR application suitable to be used both via tablet and via HoloLens 2 headset. The registration accuracy for both solutions was verified on a 3D printed leg phantom obtained from the virtual models, by repeatedly applying the tracking function and computing pose deviations between the AR-projected virtual skin paddle profile and the real one transferred to the phantom via a CAD/CAM cutting guide. The success rate in completing the AR-guided task of skin paddle harvesting was evaluated using CAD/CAM templates positioned on the phantom model surface.ResultsOn average, the marker-less AR protocol showed comparable registration errors (ranging within 1-5 mm) for tablet-based and HoloLens-based solution. Registration accuracy seems to be quite sensitive to ambient light conditions. We found a good success rate in completing the AR-guided task within an error margin of 4 mm (97% and 100% for tablet and HoloLens, respectively). All subjects reported greater usability and ergonomics for HoloLens 2 solution.ConclusionsResults revealed that the proposed marker-less AR based protocol may guarantee a registration error within 1-5 mm for assisting skin paddle harvesting in the clinical setting. Optimal lightening conditions and further improvement of marker-less tracking technologies have the potential to increase the efficiency and precision of this AR-assisted reconstructive surgery.

Improved Coding Landmark-Based Visual Sensor Position Measurement and Planning Strategy for Multiwarehouse Automated Guided Vehicle

The application of vision-guided multiwarehouse automated guided vehicles (AGVs) is becoming more extensive. This article mainly studies the position measurement and corresponding path planning of AGV guided by visual sensors. An improved vehicle-mounted visual sensor model is proposed, which effectively reduces the cost of the sensor and achieves position prediction. The proposed manual coding landmark significantly improves the decoding speed and accuracy while ensuring the information coding capacity. An improved heuristic path planning algorithm combined with the visual sensor system is implemented, considering the planning effectiveness and directionality. Finally, simulations and experiments verify the reliability of the visual guidance method in position measurement and the advancement of the planning strategy. Compared with the traditional 2-D code and bottom visual model, the improved visual sensor position measurement effectively reduces motion blur and corresponding pose deviation. The decoding speed and accuracy are improved by more than 41.21% and 53.85%, respectively. Planning performance comparison is achieved between the same type of heuristic algorithms (A*, D*, and algorithm deployment). The significant improvement in core system indicators includes task efficiency (up to 70.02% improvement), parking time (up to 72% reduction), deadlock (up to 85.05% reduction), and planning time (up to 89.39% reduction).

3D printing lunar architecture with a novel cable-driven printer

Considerable attention has been paid to the exploration of moon, especially the construction of lunar habitat. However, few studies are found working on the construction equipment being suitable for trans planetary transportation, assembly, and working in lunar environment. This paper proposed a novel cable-driven printer used to build lunar architecture. The pose measurement and control strategy of the printing system is proposed. To study the reconfiguration characteristic of the cable-driven printer, several trees with arbitrary locations were selected as the rack to reconstruct the system outdoors. The key factors such as the sensitivity of pose deviation to system parameters affecting the reconstruction performance is discussed. The forming space of the cable-driven printer is analyzed theoretically and the forming ability of the system is verified experimentally. It is found that the cable-driven printer has the advantages of simple structure, small weight, large forming space and good reconfiguration characteristic, which shows the great potential of the proposed cable-driven printer in the construction of lunar architecture.

Error modeling and singularity analysis of planar parallel mechanisms using optimized expression of joint clearances and link deformation

A fast error modeling method is proposed to analyze the pose deviation of 3-RPR planar parallel mechanisms with multiple revolute joint clearances. The pose error arisen from clearances and limb deformation is modeled from the point of inverse kinematics and estimated numerically. Manipulator poses are represented by elements of the Lie group SE(2) and the discontinuous deformation of limbs due to clearances are modeled by the Heaviside function, which is then approximated with the hyperbolic tangent function. After establishing the error model, an efficient error compensation method is introduced. The proposed error modeling and accuracy analysis method are validated by case study of a 3-RPR mechanism. The results show that the hyperbolic tangent function runs faster than the step function and it provides better convergence. Finally, the singularity of the 3-RPR mechanism with load is analyzed and the results reveal the effects of loads and clearances on mechanism singularities.

A combined backstepping and adaptive fuzzy PID approach for trajectory tracking of autonomous mobile robots

A combined backstepping and adaptive fuzzy PID approach for a nonholonomic autonomous mobile robot to follow the desired path is proposed in this paper. Two adaptive fuzzy PID controllers are adopted at the dynamic control level for velocity tracking and steering control of the robot. The fuzzy PID controller consists of a PID controller which is designed by a trial-and-error approach, optimized using the cross-entropy method, and a fuzzy controller based on relational models with two inputs and three outputs. Adaptive adjustment of the PID controllers is implemented by means of the fuzzy controllers. The pose deviations of the robot when trajectory tracking will be eliminated by the backstepping control technique at the kinematic level using a kinematic model. The simulation validation results demonstrate that the proposed control system can offer good performances for the robot in terms of small distance error, rapid response, high stability, and trajectory tracking more accuracy.

Elasto-geometrical error modeling and compensation of a five-axis parallel machining robot

Parallel manipulators have the potentials of high efficiency and high precision in the field of machining and manufacturing. However, accuracy improvement of the parallel manipulator is still an essential and challenging issue, encountering two important problems. Firstly, the ignorance of elastic deformation caused by gravity or deviations of static stiffness model restricts further improvement of accuracy. To solve this problem, an elasto-geometrical error modeling method is proposed. The comprehensive effects of structural errors, elastic deformation under gravity and compliance parameter errors on pose deviations are disclosed. On this basis, the identification equation of actual structural errors and compliance parameter errors can be established. Secondly, the ill-conditioned identification matrix and the identification equation with anisotropic residual error can lead to inaccurate identification results. To solve this problem, a weighted regularization method is proposed. The identification equation with isotropic residual error is built, and accurate identification can be realized with the regularization method. Based on the proposed methods, the error compensation experiment is conducted on the prototype of a five-axis parallel machining robot using a laser tracker. Experiment results show that the accuracy of the machining robot is significantly improved after compensation. An M1_160 test piece and an S-shaped test piece are machined and measured to further validate the effectiveness of the proposed methods. The elasto-geometrical error modeling method and the weighted regularization method can be applied to other parallel manipulators’ accuracy improvement.