Distance Error Research Articles

Deep learning model for automatic limb detection and gripping in a novel meat factory cell

The goal of this work has been the development of a deep-learning model which may be used in conjunction with a novel so-called “Meat Factory Cell” platform, namely to enable an industrial robot within the system to identify and successfully grip the limbs of an entire pig carcass. The model consists of three main components: (1) a U-Net-based deep learning model that predicts heatmaps with a probability distribution of gripping and key point locations on the limbs, within RGB-D images; (2) a post-processing element for the extraction of keypoints from heatmaps, and transferral of these points into 3D space using a pinhole camera model; and (3) gripper orientation estimation, which uses the predicted limb key points to define gripper orientation in 3D space. The proposed system demonstrates high precision and robustness in estimating gripping points on pig limbs based on a data test set, which includes two gripping definitions: Norwegian and Danish. These gripping definitions account for variation in the slaughter process in two different European countries. The Norwegian definition gives mAP(0.5…0.95) = 0.971, mAR(0.5…0.95) = 0.982, and distance error 13 mm, while the Danish definition gives mAP(0.5…0.95) = 0.985, mAR(0.5…0.95) = 0.995, and distance error 14 mm. The model was validated in practice during experimental trials at the Meat Factory Cell test facility at the Norwegian University of Life Science (Ås, Norway), with whole pig carcasses (n=25).

Monocular Vision Guidance for Unmanned Surface Vehicle Recovery

The positioning error of the GPS method at close distances is relatively large, rendering it incapable of accurately guiding unmanned surface vehicles (USVs) back to the mother ship. Therefore, this study proposes a near-distance recovery method for USVs based on monocular vision. By deploying a monocular camera on the USV to identify artificial markers on the mother ship and subsequently leveraging the geometric relationships among these markers, precise distance and angle information can be extracted. This enables effective guidance for the USVs to return to the mother ship. The experimental results validate the effectiveness of this approach, with positioning distance errors of less than 40 mm within a 10 m range and positioning angle errors of less than 5 degrees within a range of ±60 degrees.

Cardio-respiratory motion compensation for coronary roadmapping in fluoroscopic imaging.

Inferring the shape and position of coronary artery poses challenges when using fluoroscopic image guidance during percutaneous coronary intervention (PCI) procedure. Although angiography enables coronary artery visualization, the use of injected contrast agent raises concerns about radiation exposure and the risk of contrast-induced nephropathy. To address these issues, dynamic coronary roadmapping overlaid on fluoroscopic images can provide coronary visual feedback without contrast injection. This paper proposes a novel cardio-respiratory motion compensation method that utilizes cardiac state synchronization and catheter motion estimation to achieve coronary roadmapping in fluoroscopic images. For more accurate cardiac state synchronization, video frame interpolation is applied to increase the frame rate of the original limited angiographic images, resulting in higher framerate and more adequate roadmaps. The proposed method also incorporates a multi-length cross-correlation based adaptive electrocardiogram (ECG)matching to address irregular cardiac motion situation. Furthermore, a shape-constrained path searching method is proposed to extract catheter structure from both fluoroscopic and angiographic image. Then catheter motion is estimated using a cascaded matching approach with an outlier removal strategy, leading to a final corrected roadmap. Evaluation of the proposed method on clinical x-ray images demonstrates its effectiveness, achieving a 92.8% F1 score for catheter extraction on 589 fluoroscopic and angiographic images. Additionally, the method achieves a 5.6-pixel distance error of the coronary roadmap on 164 intraoperative fluoroscopic images. Overall, the proposed method achieves accurate coronary roadmapping in fluoroscopic images and shows potential to overlay accurate coronary roadmap on fluoroscopic image in assisting PCI.

Topology Perception and Relative Positioning of UAV Swarm Formation Based on Low-Rank Optimization

In a satellite-denied environment, a swarm of drones is capable of achieving relative positioning and navigation by leveraging the high-precision ranging capabilities of the inter-drone data link. However, because of factors such as high drone mobility, complex and time-varying channel environments, electromagnetic interference, and poor communication link quality, distance errors and even missing distance values between some nodes are inevitable. To address these issues, this paper proposes a low-rank optimization algorithm based on the eigenvalue scaling of the distance matrix. By gradually limiting the eigenvalues of the observed distance matrix, the algorithm reduces the rank of the matrix, bringing the observed distance matrix closer to the true value without errors or missing data. This process filters out distance errors, estimates and completes missing distance elements, and ensures high-precision calculations for subsequent topology perception and relative positioning. Simulation experiments demonstrate that the algorithm exhibits significant error filtering and missing element completion capabilities. Using the F-norm metric to measure the relative deviation from the true value, the algorithm can optimize the relative deviation of the observed distance matrix from 11.18% to 0.25%. Simultaneously, it reduces the relative positioning error from 518.05 m to 35.24 m, achieving robust topology perception and relative positioning for the drone swarm formation.

A Relationship between Classical and Bayesian Estimation Procedures through Fisher Information

The aim of this article is to investigate the association between the classical and Bayesian approaches through Fisher information. For any particular distribution, the computation of Fisher information is quite significant, as it provides the amount of information about the unknown parameter inferred from the observed data and is related to classical methods of estimation. Also, in the light of some prior knowledge, we may estimate the unknown parameter through Bayesian approach. Specifically, we want to see a relationship between information and Bayes estimation. In this article, the scale parameter of the one-parameter exponential distribution is estimated under the weighted squared error and Kullback-Leibler distance loss functions. The information acquired from both the classical and Bayesian methodologies have been connected through the risk intensity and error intensity which have been introduced in this article. The results of extensive simulation studies using these intensity measures show that the Bayes estimator performs more intensely as the amount of Fisher information increases. It is seen that the Fisher information, which is pivotal to many classical estimation methods, has a relationship with the Bayesian method depending on prior distribution, at least in this case, as the intensity measures of the Bayes estimator decrease with the increase in information. Further, to comprehend the theoretical notion of association, two real-life datasets have been included to show usefulness in practical field.

VSFL: Trajectory prediction framework based on validity-aware semi-asynchronous federated learning in internet of vehicles

Accurate prediction of vehicle trajectories on the Internet of Vehicles is crucial for improving traffic safety. Federated learning has been proposed to address the issue of islands in shared data. Traditional synchronous federated learning requires waiting for each node to complete training before model aggregation can occur, and the aggregation algorithm of the server cannot adjust the aggregation weight in real-time, which leads to increased communication overhead, time cost, and decreased accuracy. To balance these issues, this paper proposes a Validity-aware Semi-asynchronous Federated Learning-based framework for predicting vehicle trajectories. The framework makes the following improvements - firstly, based on the asynchronous cooperation algorithm of generalization research, the models of vehicle nodes within the same RoadSide Unit (RSU) range are aggregated into this RSU to reduce communication overhead and time costs. To further ensure the privacy and security of all participants, we added differential privacy algorithms during the model training process. Secondly, the server uses a weighted aggregation algorithm based on effective perception to aggregate all RSU models into a global model to address potential accuracy issues. This article uses a Social-LSTM like model to validate the effectiveness of this framework in the Next Generation Simulation (NGSIM) Vehicle Trajectories and Support Data dataset. Compared with traditional federated averaging algorithms and trust aware federated learning algorithms, this framework reduces distance errors by 27.80 % and 19.23 %, respectively, and improves accuracy by 22.56 % and 13.59 %.

Augmented‐reality‐based surgical navigation for endoscope retrograde cholangiopancreatography: A phantom study

AbstractBackgroundEndoscope retrograde cholangiopancreatography is a standard surgical treatment for gallbladder and pancreatic diseases. However, surgeons is at high risk and require sufficient surgical experience and skills.Methods(1) The simultaneous localisation and mapping technique to reconstruct the surgical environment. (2) The preoperative 3D model is transformed into the intraoperative video environment to implement the multi‐modal fusion. (3) A framework for virtual‐to‐real projection based on hand‐eye alignment. For the purpose of projecting the 3D model onto the imaging plane of the camera, it uses position data from electromagnetic sensors.ResultsOur AR‐assisted navigation system can accurately guide physicians, which means a distance of registration error to be restricted to under 5 mm and a projection error of 5.76 ± 2.13, and the intubation procedure is done at 30 frames per second.ConclusionsCoupled with clinical validation and user studies, both the quantitative and qualitative results indicate that our navigation system has the potential to be highly useful in clinical practice.

Automated multivolume placental reconstruction using three-dimensional power Doppler ultrasound and infrared camera tracking.

Placental insufficiency contributes to many obstetric pathologies however there is no bedside clinical tool to evaluate placental perfusion. We have developed a method to acquire multiple three-dimensional power Doppler ultrasound (3D PD-US) volumes of placental vasculature with infrared camera tracking providing global coordinates. These are automatically reconstructed ('stitched') into a model of the entire placenta. The purpose of the study was to evaluate the accuracy of automated reconstruction in an US phantom and apply this technique to human placentas. A custom-designed acrylic phantom was constructed with dimensions mimicking a third-trimester placenta, containing 12 quadrilateral towers of varying heights submersed in tissue-mimicking solution. Triplicated three-dimensional ultrasound volumes of this phantom were acquired at three different acquisition angles using infrared camera tracking. Data was transformed into a three-dimensional cartesian volume and automatically stitched. A single-centre, cross-sectional feasibility study was conducted on uncomplicated second-to-third trimester singleton pregnancies using standardised obstetric settings. Multiple 3D PD-US and grayscale volumes of the placenta were acquired with infrared camera tracked coordinates. Volumes were stitched to create a model of placental vasculature. 6 phantom datasets were reconstructed at each of 3 volume angles with a median of 9 volumes required. Perfect volume alignment occurred in 66.7% of 648 datapoints. Mean distance error for volume misalignment was 2.92mm. Measurements of 210 distances in each stitched volume (2160 total distances) differed an average of 1.51mm from true measurements. These compare favourably with recent literature, though for a substantially larger phantom. 17 participants were scanned with 92% reconstruction success per placental volume set and 100% participant achievability. Median reconstruction time was 10 minutes. Placental vasculature was qualitatively assessed to be present, continuous, and detailed throughout. Volume measurement of entire segmented placentas was highly repeatable (ICC 0.96). We present an automated method to model the entire structure and vasculature of second-to-third trimester placentas, with verified accuracy and clinical feasibility for grayscale and power Doppler. This study builds the foundation to develop a practical screening tool for detecting placental insufficiency, and expansion to adult organ perfusion evaluation. This article is protected by copyright. All rights reserved.

Coupled-Error-Based Formation Control for Rapid Formation Completion by Omni-Directional Robots

This paper proposes a coupled-error-based formation control algorithm for the rapid formation completion of multi-robot systems. We consider a multi-robot system with omni-directional robots with swerve-driving mechanisms and a communication system with minimized constraints. This paper introduces a coupled error that links the distance errors with the leading robot and the following robot through a coupling ratio. We propose a controller using the coupled error to achieve the control objectives of this paper. Unlike existing results that only use the information of the preceding robot, this algorithm couples the information of both the preceding robot and one’s follower. Using the proposed error-coupling-based formation control algorithm, multi-robot systems can quickly establish formations for collaboration, allowing tasks to commence swiftly and reducing deformations in formations due to speed variations. With stability analysis and simulation results for the practical application of the proposed algorithm, the approach has been verified to improve the speed of both the completion of the formation and overall system trajectory tracking, balancing trade-offs between them.

Moving horizon estimation for localization of mobile robots with measurement outliers

This paper investigates the moving horizon estimation (MHE) problem of mobile robots with measurement outliers. To deal with measurement outliers, the Euclidean distance of measurement error is introduced to detect and remove abnormal data. Then, we use dimension expansion methods to preprocess the data of heterogeneous sensors, such as UWB and IMU. An MHE-based method is proposed that deals with the localization of mobile robots with measurement outliers in the presence of bounded noise. An MHE-based estimator is obtained by solving a regularized least-squares problem. We analyze the convergence of the estimation error system using the properties of norm inequalities, and an upper bound is derived for the estimation error system by using norm inequality. Finally, simulation and experiment examples are given to verify the effectiveness and applicability of the proposed approach.

Feasibility of a novel augmented reality overlay for cervical screw placement in phantom spine models.

Feasibility study. A phantom model was used to evaluate the accuracy of a novel augmented reality (AR) system for cervical screw placement. The use of navigation systems is becoming increasingly common in spine procedures. However, numerous factors limit the feasibility of regular and widespread use of navigation tools during spine surgery. AR is a new technology that has already demonstrated utility as a navigation tool during spine surgery. However, advancements in AR technology are needed to increase its adoption by the medical community. AR technology that uses a fiducial-less registration system was tested in a preclinical cervical spine phantom model study for accuracy during spinal screw placement. A three-dimensional reconstruction of the spine along with trajectory lines was superimposed onto the phantom model using an AR headset. Participants used the AR system to guide screw placement, and post-instrumentation scans were compared for accuracy assessment. Twelve cervical screws were placed under AR guidance. All screws were placed in an acceptable anatomic position. The average distance error for the insertion point was 2.73±0.55 mm, whereas that for the endpoint was 2.71±0.69 mm. The average trajectory angle error for all insertions was 2.69°±0.59°. This feasibility study describes a novel registration approach that superimposes spinal anatomy and trajectories onto the surgeon's real-world view of the spine. These results demonstrate reasonable accuracy in the preclinical model. The results of this study demonstrate that this technology can assist with accurate screw placement. Further investigation using cadaveric and clinical models is warranted.

Evaluation of a Fully Digital, In-House Virtual Surgical Planning Workflow for Bimaxillary Orthognathic Surgery

The advantages of virtual surgical planning (VSP) for orthognathic surgery are clear. Previous studies have evaluated in-house VSP; however, few fully digital, in-house protocols for orthognathic surgery have been studied. The purpose of this study was to evaluate the difference between the virtual surgical plan and actual surgical outcome for orthognathic surgery using a fully digital, in-house VSP workflow. This is a prospective cohort study from September 2020 to November 2022 of patients at the Victoria General Hospital in Halifax, NS, Canada who underwent bimaxillary orthognathic surgery. Patients were excluded if they had previously undergone orthognathic surgery or were diagnosed with a craniofacial syndrome. The primary outcome variables were the mean 3-dimensional (3D) (Euclidean) distance error, as well as mean error and mean absolute error in the transverse (x axis), vertical (y axis), and anterior-posterior (z axis) dimensions. Covariates included age, sex, and surgical sequence (mandible-first or maxilla-first). The primary outcome was tested using Z and t critical value confidence intervals. The P value was set at .05. The 3D distance error for mandible-first and maxilla-first groups was compared using a 2-sample t-test as well as analysis of variance. The study sample included 52 subjects (24 males and 28 females) with a mean age of 27.7 (± 12.1) years. Forty three subjects underwent mandible-first surgery and 9 maxilla-first surgery. The mean absolute distance error was largest in the anterior-posterior dimension for all landmarks (except posterior nasal spine, left condyle, and gonion) and exceeded the threshold for clinical acceptability (2mm) in 16 of 23 landmarks. Additionally, mean distance error in the anterior-posterior dimension was negative for all landmarks, indicating deficient movement in that direction. The effect of surgical sequence on 3D distance error was not statistically significant (P=.37). In general, the largest contributor to mean 3D distance error was deficient movement in the anterior-posterior direction. Otherwise, mean absolute distance error in the vertical and transverse dimensions was clinically acceptable (< 2mm). These findings were felt to be valuable for treatment planning purposes when using a fully digital, in-house VSP workflow.

A Reappraisal of the Accuracy of the Tactile Method for the Detection of the Subgingival Cementoenamel Junction: An In Vivo Study.

This article reappraises the accuracy and factors associated with the detection of the cementoenamel junction (CEJ) using the tactile method. A total of 111 tooth sites of 7 patients scheduled for flap surgery were selected for the study. The CEJ was detected in a blind manner using the conventional tactile method with a standard periodontal probe by a single, trained examiner. A custom-made stent was prepared to standardize the measurements and the distance from a fixed reference point on the stent to the CEJ was measured before (apparent CEJ) and after (real CEJ) opening a gingival flap. To evaluate the effect of local anesthesia (LA) on the measurement error, assessment with and without LA given prior to the measurement was also evaluated. The bone crest-CEJ distance at each site was also recorded in all sites. The measurement error of apparent versus real distance, if any, was compared using Cohen's weighted kappa coefficient (WKC) (± 1 mm). A weak WKC (WKC = 0.539) was found between the apparent and real CEJ distance. Higher WKCs were noted at posterior and proximal sites than the anterior and buccal/lingual sites, respectively (0.840 and 0.545 vs. 0.475 and 0.488). A higher confluence of the agreements was noted when CEJ distance was measured in anesthetized sites (WKC = 0.703). Sites without bone loss showed more coronal deviation of CEJ detection, as opposed to apical deviation seen at sites with bone loss. The conventional CEJ detection using the tactile method was relatively imprecise depending on the anatomical location of the tooth and the bone loss at the site of measurement. However, the detection accuracy improved when the sites were anesthetized. In clinical terms, our data, reported here for the first time imply that, in the absence of visual cues, posterior tooth site measurements of periodontal attachment loss were more reliable in comparison to the other sites. The bone crest level also impacted the measurement deviation to some extent, implying that, possible overestimate of clinical attachment loss may occur at sites without bone loss.

Lumbar and Thoracic Vertebrae Segmentation in CT Scans Using a 3D Multi-Object Localization and Segmentation CNN.

Radiation treatment of cancers like prostate or cervix cancer requires considering nearby bone structures like vertebrae. In this work, we present and validate a novel automated method for the 3D segmentation of individual lumbar and thoracic vertebra in computed tomography (CT) scans. It is based on a single, low-complexity convolutional neural network (CNN) architecture which works well even if little application-specific training data are available. It is based on volume patch-based processing, enabling the handling of arbitrary scan sizes. For each patch, it performs segmentation and an estimation of up to three vertebrae center locations in one step, which enables utilizing an advanced post-processing scheme to achieve high segmentation accuracy, as required for clinical use. Overall, 1763 vertebrae were used for the performance assessment. On 26 CT scans acquired for standard radiation treatment planning, a Dice coefficient of 0.921 ± 0.047 (mean ± standard deviation) and a signed distance error of 0.271 ± 0.748 mm was achieved. On the large-sized publicly available VerSe2020 data set with 129 CT scans depicting lumbar and thoracic vertebrae, the overall Dice coefficient was 0.940 ± 0.065 and the signed distance error was 0.109 ± 0.301 mm. A comparison to other methods that have been validated on VerSe data showed that our approach achieved a better overall segmentation performance.

Two-step calibration of 6-DOF industrial robots by grouping kinematic parameters based on distance constraints

The positioning accuracy of industrial robots is critical for their applications, which can be improved through calibration. This paper proposes a two-step calibration method for six-degree-of-freedom (6-DOF) industrial robots to reduce couplings of their modified Denavit-Hartenberg (MD-H) model parameters during optimization processes of kinematic calibration. In this method, a distance error model is established based on the distance constraints, and the MD-H model parameters of the industrial robots are identified group by group using the Levenberg-Marquardt (LM) algorithm. To determine the optimal MD-H model parameter grouping, the different grouping strategies are simulated and analyzed. In the proposed method, the coordinate system transformation between the measurement frame and the robot base frame can be avoided based on the distance error model, thereby reducing the errors introduced by the coordinate system transformation during the calibration process. Finally, the proposed two-step calibration method is verified through an experiment. The experimental result shows that the distance/positioning accuracy on the robot end-effector is improved from 0.602 mm/2.7317 mm to 0.151 mm/0.717 mm after calibration. The presented study may be beneficial for improving performance of industrial robots.

Improved 3D human face reconstruction from 2D images using blended hard edges

This study reports an effective and robust edge-based scheme for the reconstruction of 3D human faces from input of single images, addressing drawbacks of existing methods in case of large face pose angles or noisy input images. Accurate 3D face reconstruction from 2D images is important, as it can enable a wide range of applications, such as face recognition, animations, games and AR/VR systems. Edge features extracted from 2D images contain wealthy and robust 3D geometric information, which were used together with landmarks for face reconstruction purpose. However, the accurate reconstruction of 3D faces from contour features is a challenging task, since traditional edge or contour detection algorithms introduce a great deal of noise, which would adversely affect the reconstruction. This paper reports on the use of a hard-blended face contour feature from a neural network and a Canny edge extractor for face reconstruction. The quantitative results indicate that our method achieves a notable improvement in face reconstruction with a Euclidean distance error of 1.64 mm and a normal vector distance error of 1.27 mm when compared to the ground truth, outperforming both traditional and other deep learning-based methods. These metrics show particularly significant advancements, especially in face shape reconstruction under large pose angles. The method also achieved higher accuracy and robustness on in-the-wild images under conditions of blurring, makeup, occlusion and poor illumination.

Study on the contact performance of the variable hyperbolic circular arc tooth trace cylindrical gear with installation errors

Abstract. Installation errors are important factor for the contact performance of the variable hyperbolic circular arc tooth trace (VH-CATT) cylindrical gear; the study of the relationship between installation errors and contact performances is beneficial for gear vibration and noise reduction. Firstly, based on the meshing theory, the tooth surface equation and contact ellipse of the VH-CATT cylindrical gear were deduced, and the tooth surface imprinting experiment was realized. Next, the tooth contact analysis model of the VH-CATT cylindrical gear was developed to investigate the influence of the installation errors on the elliptical contact area. Then, the calculation formulas of the tooth surface gap and contact point flexibility matrix were carried out to develop the load tooth contact analysis model of the VH-CATT cylindrical gear. Finally, the influence of the installation errors on the load distribution was investigated. Research shows that the elliptical contact area of the VH-CATT cylindrical gear is a line contact within a certain range and is located in the middle section of the tooth width. The elliptical contact area of the VH-CATT cylindrical gear increases or decreases rapidly when meshing in and out, and all the installation errors have a certain influence on the elliptical contact area, except for the center distance error. The single-tooth meshing area with the installation errors is greater than that of the ideal gear pair. The load distribution area with the installation errors deviates from the middle section, except for the center distance error. The installation rotation errors around the x and y axis have a certain influence on the maximum load of the single-tooth meshing area. The research results provide a basis for improving the bearing capacity of the VH-CATT cylindrical gear and optimizing the design.

Low-Power Approximate Unsigned and Signed Multipliers with Configurable Error Recovery

In the field of Digital Signal Processing and similar applications, Approximate circuits are being explored as a means to enhance performance and energy efficiency by sacrificing a degree of accuracy. Within these circuits, Multipliers play a crucial role and are being investigated for their potential impact on overall system optimization. In this paper, a novel approximate multiplier with a low power consumption and a short critical path is proposed for high-performance DSP applications. This multiplier leverages a newly designed approximate adder that limits its carry propagation to the nearest neighbours for fast partial product accumulation. Different levels of accuracy can be achieved by using either OR gates or the proposed approximate adder in a configurable error recovery. The multipliers using these two error reduction strategies are referred to as Approximate Multiplier 1 (AM1) and Approximate Multiplier 2 (AM2), respectively. Both AM1 and AM2 have a low mean error distance, i.e., most of the errors are not significant in magnitude. Compared with a Unsigned multiplication multiplier, with the signed multiplication. The signed multiplication tends to have lower power consumption is observed. By utilizing an appropriate error recovery, the proposed approximate multipliers achieve similar processing accuracy as traditional exact multipliers, but with significant improvements in power.

A Time Headway Control Scheme for Virtually Coupled Heavy Haul Freight Trains

Abstract Virtual coupling of railway trains is an emerging technology that has the potential to significantly increase railway operational efficiency by reducing the train following distance from absolute braking distances to relative braking distances. Current research in this topic is mainly focused on passenger trains and uses distance-based headways. This paper studied virtual coupling for heavy haul freight trains and demonstrated that the distance headway scheme was challenging and sometimes impractical for heavy haul trains to achieve virtual coupling. A time-based headway scheme was then proposed to set the follower train to be a certain time behind the schedule of the leader train rather than a distance headway. The time-based headway required the follower train to reproduce the leader train's operational status at the same track location. This also allowed the follower train to copy any optimized train driving strategies from the leader train. Demonstrative simulations were carried out without the consideration of communication errors and train localization errors. The results show that a conventional distance headway simulation had maximum distance and speed errors of 716 m (36%, reference 2 km) and 24 km/h (66%, reference 36 km/h), respectively. A time-based headway simulation reduced the maximum distance and speed errors to 0.07 m (0%, reference 2 km) and 0.1 km/h (9%, reference 1.18 km/h), respectively.

Automatic loading method for robot guided by 3D vision for scattered and stacked shoe soles

This paper primarily introduces a method for the automated feeding of scattered stacked shoe soles using a 3D visual-guided robot. Initially, addressing issues like slow speed in pose estimation and poor robustness during the robot sorting and feeding process, we introduce an enhanced pose estimation algorithm. This algorithm combines the improved Super 4-Point Congruent Sets (Super 4PCS) with the Truncated Least Squares Semidefinite Relaxation (TEASER) algorithm, significantly boosting the speed and robustness of pose estimation during sole sorting, and achieving precise target pose estimation. Building upon this foundation, we present a sorting strategy for disordered stacked shoe soles. This strategy integrates spatial positional information of each sole, employing multi-objective decision-making and recognition algorithms to determine optimal grasping targets. Finally, an experimental platform for automated sole feeding is designed to validate the proposed method. The experimental results indicate that the pose estimation method proposed in this paper achieves an average distance error of 2.04 mm and an average angular error of 2.72°, with the robot’s average success rate in grasping reaching 97.08%. Moreover, the average processing time of the vision algorithm is only 1.34 s, demonstrating good efficiency, precision, and robustness. This method effectively meets the automated feeding needs of scattered and stacked shoe soles in the actual production processes of shoemaking enterprises.