Angular Error Research Articles

FSKT‐GE: Feature maps similarity knowledge transfer for low‐resolution gaze estimation

AbstractThe limited of texture details information in low‐resolution facial or eye images presents a challenge for gaze estimation. To address this, FSKT‐GE (feature maps similarity knowledge transfer for low‐resolution gaze estimation) is proposed, a gaze estimation framework consisting of both a high resolution (HR) network and low resolution (LR) network with the identical structure. Rather than mere feature imitation, this issue is addressed by assessing the cosine similarity of feature layers, emphasizing the distribution similarity between the HR and LR networks. This enables the LR network to acquire richer knowledge. This framework utilizes a combination loss function, incorporating cosine similarity measurement, soft loss based on probability distribution difference and gaze direction output, along with a hard loss from the LR network output layer. This approach on low‐resolution datasets derived from Gaze360 and RT‐Gene datasets is validated, demonstrating excellent performance in low‐resolution gaze estimation. Evaluations on low‐resolution images obtained through 2×, 4×, and 8× down‐sampling are conducted on two datasets. On the Gaze360 dataset, the lowest mean angular errors of 10.97°, 11.22°, and 13.61° were achieved, while on the RT‐Gene dataset, the lowest mean angular errors of 6.73°, 6.83°, and 7.75° were obtained.

The effectiveness of fatigue on repositioning sense of lower extremities: systematic review and meta-analysis.

An injury can significantly harm both individual and team performance. One of the most important risk factors for sports-related injuries, especially non-collision injuries, is fatigue. It seems that poor proprioception may play an essential role to impose athletes to further injuries. This systematic review and meta-analysis aimed to examine the effectiveness of fatigue on the repositioning sense of the lower extremity joints. The electronic databases, including PubMed, Web of Science, Scopus, and Google Scholar were systematically searched from inception to 11January 2024. The obtained records were exported to the EndNote Software version 8. Then, two investigators examined the records independently to find eligible studies based on the inclusion/exclusion criteria. In the case of disagreements, a consequence method was utilized. The quality of the eligible studies was evaluated using the Downs and Black checklist. Comprehensive Meta-Analysis (CMA) software ver. 3 software was used for statistical analysis. Q-test and I2 were employed to examine the data homogeneity. In addition, considering the risk of bias, the Funnel Plot and trim-and-fill method were used. After reviewing the titles and abstracts of 3883 studies found in the selected databases, 43 articles were found to be eligible to include in meta-analyses. The results showed that fatigue led to a significant increase in the active absolute error of the knee (SDM = 0.524, 95% CI = 0.406-0.841), ankle in the horizontal plane (SDM = 0.541, 95% CI = 0.367-0.715), ankle in the sagittal plane (SDM = 0.443, 95% CI = 0.088-0.798), and hip (SDM = 0.988, 95% CI = 0.135-1.841). However, fatigue had no significant effects on the passive absolute error of the knee and ankle in horizontal plane and relative angular error of the knee. Fatigue can diminish the active joint position sense of the lower extremities and thus may increase the risk of injury by reducing proprioception. Therefore, future research could be conducted to investigate the potential impact of integrated fatigue-mitigating exercises into athletes' training programs, with the aim of reducing the incidence of sports-related injuries.

Fusion of Time-of-Flight Based Sensors with Monocular Cameras for a Robotic Person Follower

Human-robot collaboration (HRC) is becoming increasingly important in advanced production systems, such as those used in industries and agriculture. This type of collaboration can contribute to productivity increase by reducing physical strain on humans, which can lead to reduced injuries and improved morale. One crucial aspect of HRC is the ability of the robot to follow a specific human operator safely. To address this challenge, a novel methodology is proposed that employs monocular vision and ultra-wideband (UWB) transceivers to determine the relative position of a human target with respect to the robot. UWB transceivers are capable of tracking humans with UWB transceivers but exhibit a significant angular error. To reduce this error, monocular cameras with Deep Learning object detection are used to detect humans. The reduction in angular error is achieved through sensor fusion, combining the outputs of both sensors using a histogram-based filter. This filter projects and intersects the measurements from both sources onto a 2D grid. By combining UWB and monocular vision, a remarkable 66.67% reduction in angular error compared to UWB localization alone is achieved. This approach demonstrates an average processing time of 0.0183s and an average localization error of 0.14 meters when tracking a person walking at an average speed of 0.21 m/s. This novel algorithm holds promise for enabling efficient and safe human-robot collaboration, providing a valuable contribution to the field of robotics.

Design and Control Simulation Analysis of Tender Tea Bud Picking Manipulator

Aiming at the current complex problem of the mechanized high-quality picking of tender tea buds, this paper designs a tender tea bud-picking manipulator. In the picking process, the quality of the petiole and leaf blade of the tender tea bud is crucial, as the traditional cutting picking method destroys the cell structure of the tender tea buds, resulting in rapid oxidation of the cuts, thus losing the bright green appearance and pure taste. For this reason, this paper draws on the quality requirements of tender tea buds and traditional manual picking technology, simulating the process of the manual picking action, putting forward a ‘rotary pull-up’ clamping and ripping picking method, and designing the corresponding actuating structure. Using PVDF material piezoelectric thin-film sensors to detect the clamping force of the tender tea bud picking, the corresponding sensor hardware circuit is designed. In addition, the finite element analysis method is also used to carry out stress analysis on the mechanical fingers to verify the rationality of the automatic mechanism to ensure the high-quality picking of tender tea buds. In terms of the control of the manipulator, an SMC-PID control method is designed by using MATLAB/Simulink 2021 and Adam 2020 software for joint simulation. The way to control the closed-loop system angle and angular velocity error feedback is by adjusting the PID parameters, which quickly converts the sliding mode control to the sliding mode surface. The simulation results show that the SMC-PID control method proposed in this paper can meet the demand in tender tea bud picking and simultaneously has high control accuracy, response speed, and stability.

Research on Some Control Algorithms to Compensate for the Negative Effects of Model Uncertainty Parameters, External Interference, and Wheeled Slip for Mobile Robot

In this article, the research team systematically developed a method to model the kinematics and dynamics of a 3-wheeled robot subjected to external disturbances and sideways wheel sliding. These models will be used to design control laws that compensate for wheel slippage, model uncertainties, and external disturbances. These control algorithms were developed based on dynamic surface control (DSC). An adaptive trajectory tracking DSC algorithm using a fuzzy logic system (AFDSC) and a radial neural network (RBFNN) with a fuzzy logic system were used to overcome the disadvantages of DSC and expand the application domain for non-holonomic wheeled mobile robots with lateral slip (WMR). However, this adaptive fuzzy neural network dynamic surface control (AFNNDSC) adaptive controller ensures the closed system is stable, follows the preset trajectory in the presence of wheel slippage model uncertainty, and is affected by significant amplitude disturbances. The stability and convergence of the closed-loop system are guaranteed based on the Lyapunov analysis. The AFNNDSC adaptive controller is evaluated by simulation on the Matlab/simulink software R2022b and in a steady state. The maximum position error on the right wheel and left wheel is 0.000572 (m) and 0.000523 (m), and the angular velocity tracking error in the right and left wheels of the control method is 0.000394 (rad/s). The experimental results show the theoretical analysis’ correctness, the proposed controller’s effectiveness, and the possibility of practical applications. Orbits are set as two periodic functions of period T as follows.

Localization of Low- and High-Frequency Sounds in Cochlear Implant Recipients Using a Contralateral Hearing Aid.

The ability to localize sounds is partly recovered in patients using a cochlear implant (CI) in one ear and a hearing aid (HA) on the contralateral side. Binaural processing seems effective at least to some extent, despite the difference between electric and acoustic stimulation in each ear. To obtain further insights into the mechanisms of binaural hearing in these listeners, localization of low- and high-frequency sounds was tested. The study used a within-subject design, where participants were tasked with localizing sound sources in the horizontal plane. The experiment was conducted in an anechoic chamber, where an array of seven loudspeakers was mounted along the 24 azimuthal angle span from -90° to +90°. Stimuli were applied with different frequencies: broadband noise and high- and low-frequency noise. Ten CI recipients participated in the study. All had an asymmetric hearing loss with a CI in the poorer ear and an HA on the contralateral side. Accuracy of sound localization in terms of angular error and percentage of correct localization scores. The median angular error was 40° in bimodal conditions for both broadband noise and high-frequency noise stimuli. The angular error increased to 47° for low-frequency noise stimuli. In the unilaterally aided condition with an HA, only a median angular error of 78° was observed. Irrespective of the frequency composition of the stimuli, this group of bimodal listeners showed some ability to localize sounds. Angular errors were larger than those reported in the literature for bilateral CI users or single-sided deaf listeners with a CI. In the unilateral listening condition with HA, only localization of sounds was not possible for most subjects.

RGB color constancy using multispectral pixel information.

Multispectral imaging is a technique that captures data across several bands of the light spectrum, and it can be useful in many computer vision fields, including color constancy. We propose a method that exploits multispectral imaging for illuminant estimation, and then applies illuminant correction in the raw RGB domain to achieve computational color constancy. Our proposed method is composed of two steps: first, a selected number of existing camera-independent algorithms for illuminant estimation, originally designed for RGB data, are applied in generalized form to work with multispectral data. We demonstrate that the sole multispectral extension of such algorithms is not sufficient to achieve color constancy, and thus we introduce a second step, in which we re-elaborate the multispectral estimations before conversion into raw RGB with the use of the camera response function. Our results on the NUS dataset show that an improvement of 60% in the color constancy performance, measured in terms of reproduction angular error, can be obtained according to our method when compared to the traditional raw RGB pipeline.

Research on Time Series-Based Pipeline Ground Penetrating Radar Calibration Angle Prediction Algorithm.

The pipeline ground-penetrating radar stands as an indispensable detection device for ensuring underground space security. A wheeled pipeline robot is deployed to traverse the interior of urban underground drainage pipelines along their central axis. It is subject to influences such as resistance, speed, and human factors, leading to deviations in its posture. A guiding wheel is employed to rectify its roll angle and ensure the precise spatial positioning of defects both inside and outside the pipeline, as detected by the radar antenna. By analyzing its deflection factors and correction trajectories, the intelligent correction control of the pipeline ground-penetrating radar falls into the realm of nonlinear multi-constraint optimization. Consequently, a time-series-based correction angle prediction algorithm is proposed. The application of the long short-term memory (LSTM) deep learning model facilitates the prediction of correction angles and torque for the guiding wheel. This study compares the performance of LSTM with an autoregressive integrated moving average model under identical dataset conditions. The subsequent findings reveal a reduction of 4.11° and 8.25 N·m in mean absolute error, and a decrease of 10.66% and 7.27% in mean squared error for the predicted correction angles and torques, respectively. These outcomes are achieved utilizing the three-channel drainage pipeline ground-penetrating radar device with top antenna operating at 1.2 GHz and left/right antennas at 750 MHz. The LSTM prediction model intelligently corrects its posture. Experimental results demonstrate an average correction speed of 5 s and an average angular error of ±1°. It is verified that the model can correct its attitude in real-time with small errors, thereby enhancing the accuracy of ground-penetrating radar antennas in locating pipeline defects.

Real-time synchronized monitoring for the overlap accuracy of the combining beam spot in a wavelength beam combination based on confocal planes.

Beam overlap accuracy in a wavelength beam combination system determines the beam quality and efficiency, so systematic monitoring of overlap accuracy is essential. In this work, a method of performing real-time synchronized monitoring and recording overlap accuracy for a combining beam spot is proposed. Firstly, theoretical calculations for monitoring different wavelength sub-beam positions and angular errors are established. Then, an optical design and grayscale centroid algorithm are developed to analyze and simulate the combination spots. A monitoring device was designed and constructed to meet the requirements of combining system applications, which achieved an accuracy of 8.86 µrad. Finally, the method successfully monitored the system spot fluctuation range within ±22 µrad. This study resolves the issue of distinguishing the different wavelength sub-beams and their response delays in traditional combining beams. It offers precise error data for real-time synchronized calibration of the overlap accuracy in laser beam combining technology.

Research on Dental Chairside Scanning and Diagnostic System Based on Artificial Intelligence and Deep Learning

Abstract The scanning technology and diagnosis and treatment system of dental chairs play a better auxiliary role in the level of oral diagnosis and treatment as well as the doctor’s therapeutic effect. In this paper, we design an oral chairside scanning and diagnosis and treatment system, which includes two modules for scanning, acquiring, and managing oral image information. Taking CBCT as the main technology, the steps of image reconstruction, generation, estimation of tooth main axis, and reconstruction of independent tooth contour are carried out sequentially to obtain the three-dimensional network model of teeth. Through the dental clinic information management system, the case base is effectively managed to enhance operational efficiency. The system presented in this paper is tested and applied to analyze its effects during usage. The results show that the maximum difference between the measurement of this system and the manual measurement is not more than 1mm. The mean values of the errors of the system designed in this paper in the angular error and apical error are 3.547±1.556mm and 1.154±0.265mm, respectively. The P-value is less than or equal to 0.05, which is significant, and the system performs very well in these two aspects.

Intelligent electromagnetic navigation system for robot-assisted intraoral osteotomy in mandibular tumor resection: a model experiment.

Mandibular tumor surgery necessitates precise osteotomies based on tumor boundaries; however, conventional osteotomies often lack accuracy in predicting osteotomy positions and planes, potentially leading to excessive resection of normal bone tissues or residual tumors, thus compromising postoperative quality of life and clinical outcomes. Robotic-assisted surgery (RAS) augmented with artificial intelligence (AI) offers precise localization capabilities, aiding surgeons in achieving accurate osteotomy positioning. This study aimed to evaluate the feasibility and accuracy of a robotic magnetic navigation system for positioning and osteotomy in an intraoral surgical trial of a mandibular tumor model. Patient computed tomography (CT) imaging data of mandibular chin and body tumors were utilized to create 3D printed models, serving as study subjects for mandibular tumor resection. Ten pairs of models were printed for the experimental and control groups. The experimental group (EG) underwent osteotomy using a robot-assisted surgical navigation system, performing osteotomy under robotic navigation following alignment based on preoperative design. The control group (CG) underwent traditional surgery, estimating osteotomy position empirically according to preoperative design. Postoperative CT scans were conducted on both models, and actual postoperative results were compared to preoperative design. Osteotomy accuracy was evaluated by positional and angular errors between preoperatively designed and actual osteotomy planes. For ten randomly selected spots on the left and right sides, respectively, the EG group had mean distance errors of 0.338mm and 0.941mm. These values were obtained from the EG group. In the EG group, on the left side, the mean angular errors were 14.741 degrees, while on the right side, they were 13.021 degrees. For the 10 randomly selected spots on the left and right sides, respectively, the CG had mean distance errors of 1.776mm and 2.320mm. This is in contrast to the results obtained by the EG. It was determined that the left side had a mean angle error of 16.841 degrees, while the right side had an error of 18.416 degrees in the CG group. The above results indicated significantly lower point errors of bilateral osteotomy planes in the experimental group compared to the control group. This study demonstrates the feasibility of electromagnetic navigation robot-assisted intraoral osteotomy for mandibular tumors and suggests that this approach can enhance the precision of clinical surgery.

Comparison of the accuracy of two techniques for three-dimensional digital indirect bonding of orthodontic brackets: A randomized controlled trial.

This study aimed to clinically compare the accuracy of bracket positioning between three-dimensionally (3D) printed indirect bonding trays and vacuum-formed trays made over 3D-printed models. Fourteen patients, planned for fixed orthodontic therapy, were randomly divided into two equal groups. For both groups, both dental arches were scanned, to acquire virtual models, brackets were virtually positioned from central incisors to second premolars, and scans for the final bracket positions were performed. In the first group, transfer trays were 3D-printed. In the second group, virtual models were 3D-printed, and vacuum-formed soft sheets were thermoformed on the printed model. Teeth were indirectly bonded and then scanned. Superimposition of the virtual and the final bracket positioning scans was performed to measure linear and angular deviations in brackets positions. The first group showed significantly less occlusogingival and buccolingual linear errors than the second group. No significant differences in angular deviations were found between both groups. The frequencies of clinically acceptable linear errors within 0.5 mm and angular errors within 2° showed no statistically significant difference between both groups (p> 0.05 for all measurements). The transfer errors in both groups showed linear directional biases toward the mesial, gingival and labial directions. There was no statistically significant difference in the rate of immediate debonding between both groups (10.7% and 7.1% for the first and the second groups, respectively, p=0.295). 3D-printed indirect bonding trays were more accurate than vacuum-formed trays, in terms of linear deviations. Both types of trays showed similar angular control.

Recognition and position estimation method for stacked untextured parts

To address the challenge of recognizing and estimating the position of untextured stacked parts, which are common in industrial environments, this study proposes an integrated approach that incorporates the YOLOv7 target detection algorithm and point cloud alignment techniques. First, the YOLOv7 algorithm is utilized to quickly identify and locate the 2D position of the part, followed by a mapping technique to transform the 2D region of interest (ROI) into the corresponding 3D point cloud region. In the point cloud processing stage, depth threshold segmentation and Euclidean clustering segmentation methods are used to separate the target part from the background and other interfering objects. The pose estimation stage uses the SAC-IA algorithm for coarse alignment, followed by an improved ICP algorithm that introduces an adaptive weighting mechanism and a global optimization strategy for fine alignment to obtain the final 6D pose of the part. The improved strategy significantly optimizes the point-pair selection and alignment process and enhances the robustness and accuracy of the algorithm. Through experimental validation on publicly available part piece datasets, the results show that the part identification and pose estimation method proposed in this study can realize fast and accurate identification and pose estimation of different shapes, non-textured, and scattered stacked parts, where the position error can reach up to 1mm and the angular error within 1°, which meets the requirements of practical applications.

Influence of Shape, Installation and Rotation Motion Errors on Tin Bronze Clearance Seal of Rotary Joint

The rotary joint is the key device of the marine clutch. Once the seal fails, the power cannot be transmitted. In view of the above problems, this research studies the influence of shape, installation and rotation motion errors on clearance seal. The results show that compared with the absence of roundness error, the roundness error of the shaft will increase the leakage by about 2.5-4.9 %. The cylindrical error of the bushing will reduce the leakage, but it will bring more serious friction, wear and life problems. The existence of radial installation error will increase the leakage, and the larger the radial installation error, the more obvious the flow field extrusion, the higher the unevenness of the pressure field in the whole flow field. The existence of angular installation error will reduce the leakage, but it will cause more serious friction and wear, resulting in a sharp increase in temperature. The leakage increases by about 0.68 % when the radial installation error is 0.1 mm, and the rotary motion error further increases the leakage by about 0.15 %. The above research can provide theoretical support for the structural design and optimization of the rotary joint tin bronze clearance seal.

Simulation analysis and collaborative optimization of key components of the precision detection platform for high precision encoder

To realize the error detection of the high-precision photoelectric encoder, the optical small-angle precision measurement principle of the photoelectric autocollimator and single-sided mirror, and the 360° full circle measurement principle of angle inversion of the compound biaxis turntable are used to establish the precision detection platform of the encoder. The error model of the biaxial structure in the photoelectric coding error detection platform is established by introducing the error sources of the biaxial structure, such as the coaxiality error, angular position error, and installation error. At the same time, the biaxis structure and error models are used to optimize the compound biaxis structure system. By analyzing the natural frequency and vibration characteristics of the structure, the rationality and reliability of the compound biaxis system of the high-precision encoder precision detection platform are verified.

3D Position Tracking Using On-Chip Magnetic Sensing in Image-Guided Navigation Bronchoscopy.

This paper presents a compact and low-cost on-chip sensor and readout circuit. The sensor achieves high-resolution 5-degrees-of-freedom (DoF) tracking (x, y, z, yaw, and pitch). With the help of an external wire wound sensor, it can also achieve high-resolution 6-degrees-of-freedom (DoF) tracking (x, y, z, yaw, pitch, and roll angles). The sensor uses low-frequency magnetic fields to detect the position and orientation of instruments, providing a viable alternative to using X-rays in image-guided surgery. To measure the local magnetic field, a highly miniaturised on-chip magnetic sensor capable of sensing the magnetic field has been developed incorporating an on-chip magnetic sensor coil, analog-front end, continuous-time ∆Σ analog-to-digital converter (ADC), LVDS transmitter, bandgap reference, and voltage regulator. The microchip is fabricated using 65 nm CMOS technology and occupies an area of 1.06 mm 2, the smallest reported among similar designs to the best of our knowledge. The 5-DoF system accurately navigates with a precision of 1.1 mm within the volume-of-interest (VOI) of 15 ×15 ×15 cm 3. The 6-DoF system achieves a navigation accuracy of 0.8 mm and an angular error of 1.1 degrees in the same VOI. These results were obtained at a 20 Hz update rate in benchtop characterisation. The prototype sensor demonstrates accurate position tracking in real-life pre-clinical in-vivo settings within the porcine lung of a live swine, achieving a reported worst-case registration accuracy of 5.8 mm.

Pose2Gaze: Eye-Body Coordination During Daily Activities for Gaze Prediction From Full-Body Poses.

Human eye gaze plays a significant role in many virtual and augmented reality (VR/AR) applications, such as gaze-contingent rendering, gaze-based interaction, or eye-based activity recognition. However, prior works on gaze analysis and prediction have only explored eye-head coordination and were limited to human-object interactions. We first report a comprehensive analysis of eye-body coordination in various human-object and human-human interaction activities based on four public datasets collected in real-world (MoGaze), VR (ADT), as well as AR (GIMO and EgoBody) environments. We show that in human-object interactions, e.g. pick and place, eye gaze exhibits strong correlations with full-body motion while in human-human interactions, e.g. chat and teach, a person's gaze direction is correlated with the body orientation towards the interaction partner. Informed by these analyses we then present Pose2Gaze- a novel eye-body coordination model that uses a convolutional neural network and a spatio-temporal graph convolutional neural network to extract features from head direction and full-body poses, respectively, and then uses a convolutional neural network to predict eye gaze. We compare our method with state-of-the-art methods that predict eye gaze only from head movements and show that Pose2Gaze outperforms these baselines with an average improvement of 24.0% on MoGaze, 10.1% on ADT, 21.3% on GIMO, and 28.6% on EgoBody in mean angular error, respectively. We also show that our method significantly outperforms prior methods in the sample downstream task of eye-based activity recognition. These results underline the significant information content available in eye-body coordination during daily activities and open up a new direction for gaze prediction.

Analysis of Gaze, Head Orientation, and Joint Attention in Autism With Triadic VR Interviews.

Effective use of gaze and head orientation can strengthen the sense of inclusion in multi-party interactions, including job interviews. Not making significant eye contact with the interlocutors, or not turning towards them, may be interpreted as disinterest, which could worsen job interview outcomes. This study aims to support the situational solo practice of gaze behavior and head orientation using a triadic (three-way) virtual reality (VR) job interview simulation. The system lets users encounter common interview questions and see how they share attention among the interviewers based on their conversational role (speaking or listening). Given the yaw and position readings of the VR headset, we use a machine learning-based approach to analyze head orientations relative to the interviewers in the virtual environment, and achieve low angular error in a low complexity way. We examine the degree to which interviewer backchannels trigger attention shifts or behavioral mirroring and investigate the social modulation of gaze and head orientation for autistic and non-autistic individuals. In both speaking and listening roles, the autistic participants gazed at, and oriented towards the two virtual interviewers less often, and they displayed less behavioral mirroring (mirroring the head turn of one avatar towards another) compared to the non-autistic participants.

Modeling and compensation of enhanced volumetric error of machine tools containing crosstalk errors

The error compensation method is an economical and effective method to improve the machining accuracy of machine tools. Conventional volumetric error modeling of machine tools is based on the rigid body kinematics model using 21 terms of geometric errors and assumes the geometric error of one axis is independent of other axes. However, if the error motion does not satisfy this assumption in serial machine tools, it may significantly influence the overall machine tool accuracy. This paper reveals the existence of mutual crosstalk of angular errors in coupling axes by experiments with equipping the five-degree-of-freedom (5-DOF) embedded sensor module in each axis. A new on-machine measurement method is proposed for detecting crosstalk errors of the coupling axes covering the whole coupling area. It is confirmed that the position-dependent geometric errors (PDGEs) of each axis should be modified by two-dimensional dependence. Therefore, extended from the normal volumetric error model (NVEM) that is commonly used nowadays, a novel enhanced volumetric error model (EVEM) that contains crosstalk's PDGEs is proposed. The real-time error compensation controller (RECC) embedded in CNC system kernel has been developed in collaboration with the vender by writing in the application function. The effectiveness and feasibility of the EVEM and RECC are verified by non-cutting and cutting experiments. Through comparison tests with laser interferometer on body diagonals, the accuracy improving rate of EVEM is about 10 % higher than NVEM. The real-cutting tests on the ISO10791 sample are verified by a CMM and the results show the accuracy improvement of EVEM is better than NVEM by about 20 %.

An Efficient Guiding Manager for Ground Mobile Robots in Agriculture

Mobile robots have become increasingly important across various sectors and are now essential in agriculture due to their ability to navigate effectively and precisely in crop fields. Navigation involves the integration of several technologies, including robotics, control theory, computer vision, and artificial intelligence, among others. Challenges in robot navigation, particularly in agriculture, include mapping, localization, path planning, obstacle detection, and guiding control. Accurate mapping, localization, and obstacle detection are crucial for efficient navigation, while guiding the robotic system is essential to execute tasks accurately and for the safety of crops and the robot itself. Therefore, this study introduces a Guiding Manager for autonomous mobile robots specialized for laser-based weeding tools in agriculture. The focus is on the robot’s tracking, which combines a lateral controller, a spiral controller, and a linear speed controller to adjust to the different types of trajectories that are commonly followed in agricultural environments, such as straight lines and curves. The controllers have demonstrated their usefulness in different real work environments at different nominal speeds, validated on a tracked mobile platform with a width of about 1.48 m, in complex and varying field conditions including loose soil, stones, and humidity. The lateral controller presented an average absolute lateral error of approximately 0.076 m and an angular error of about 0.0418 rad, while the spiral controller presented an average absolute lateral error of about 0.12 m and an angular error of about 0.0103 rad, with a horizontal accuracy of about ±0.015 m and an angular accuracy of about ±0.009 rad, demonstrating its effectiveness in real farm tests.