Robot Tracking Research Articles

Intelligent seam tracking in foils joining based on spatial–temporal deep learning from molten pool serial images

Vision-based weld seam tracking has become one of the key technologies to realize intelligent robotic welding, and weld deviation detection is an essential step. However, accurate and robust detection of weld deviations during the microwelding of ultrathin metal foils remains a significant challenge. This challenge can be attributed to the fusion zone at the mesoscopic scale and the complex time-varying interference (pulsed arcs and reflected light from the workpiece surface). In this paper, an intelligent seam tracking approach for foils joining based on spatial–temporal deep learning from molten pool serial images is proposed. More specifically, a microscopic passive vision sensor is designed to capture molten pool and seam trajectory images under pulsed arc lights. A 3D convolutional neural network (3DCNN) and long short-term memory (LSTM)-based welding torch offset prediction network (WTOP-net) is established to implement highly accurate deviation prediction by capturing long-term dependence of spatial–temporal features. Then, expert knowledge is further incorporated into the spatio-temporal features to improve the robustness of the model. In addition, the slime mould algorithm (SMA) is used to prevent local optima and improve accuracy, efficiency of WTOP-net. The experimental results indicate that the maximum error detected by our method fluctuates within ± 0.08 mm and the average error is within ± 0.011 mm when joining two 0.12 mm thickness stainless steel diaphragms. The proposed approach provides a basis for automated robotic seam tracking and intelligent precision manufacturing of ultrathin sheets welded components in aerospace and other fields.

Design and Self-Calibration Method of a Rope-Driven Cleaning Robot for Complex Glass Curtain Walls

Rope-driven robots are increasingly used to safely and efficiently clean complex glass curtain walls. However, continuous global cleaning is difficult for most robots because of their poor performance in overcoming obstacles and adapting to curved surfaces, and an inconvenient winch calibration on complex surfaces further burdens such work. This paper presents a 3-DOF rope-driven robot and a winch self-calibration method for efficient cleaning. The robot, by integrating a 5-rope parallel configuration, a self-adaptive cleaning body, and a self-compensating driving winch, is designed to perform continuous, compliant, and accurate spatial motion on curved walls with obstacles. By deducing the kinematic model, the constraint relationship related to orderly arranged winch positions, maneuverable body positions, and accessible rope lengths is established during the robot tracking 3D trajectory. Combining the established relationship, a series of regulations are formulated for easily acquiring body positions and rope lengths, and then a self-calibration method is proposed by accurately calculating winch positions without using professional instruments. Experimental results show that the robot can perform global and precise movement on complex glass surfaces. Applying the proposed method, the maximum winch calibration error is 6.6 mm, and the maximum body tracking error is controlled within 9.6 mm.

Welding Seam Tracking and Inspection Robot Based on Improved YOLOv8s-Seg Model.

A weld is the main connection form of special equipment, and a weld is also the most vulnerable part of special equipment. Therefore, an effective detection of a weld is of great significance to improve the safety of special equipment. The traditional inspection method is not only time-consuming and labor-intensive, but also expensive. The welding seam tracking and inspection robot can greatly improve the inspection efficiency and save on inspection costs. Therefore, this paper proposes a welding seam tracking and inspection robot based on YOLOv8s-seg. Firstly, the MobileNetV3 lightweight backbone network is used to replace the backbone part of YOLOv8s-seg to reduce the model parameters. Secondly, we reconstruct C2f and prune the number of output channels of the new building module C2fGhost. Finally, in order to make up for the precision loss caused by the lightweight model, we add an EMA attention mechanism after each detection layer in the neck part of the model. The experimental results show that the accuracy of weld recognition reaches 97.8%, and the model size is only 4.88 MB. The improved model is embedded in Jetson nano, a robot control system for seam tracking and detection, and TensorRT is used to accelerate the reasoning of the model. The total reasoning time from image segmentation to path fitting is only 54 ms, which meets the real-time requirements of the robot for seam tracking and detection, and realizes the path planning of the robot for inspecting the seam efficiently and accurately.

Research on robot tracking force control algorithm based on neural networks

Purpose This study aims to propose a force control algorithm based on neural networks, which enables a robot to follow a changing reference force trajectory when in contact with human skin while maintaining a stable tracking force. Design/methodology/approach Aiming at the challenge of robots having difficulty tracking changing force trajectories in skin contact scenarios, a single neuron algorithm adaptive proportional – integral – derivative online compensation is used based on traditional impedance control. At the same time, to better adapt to changes in the skin contact environment, a gated recurrent unit (GRU) network is used to model and predict skin elasticity coefficients, thus adjusting to the uncertainty of skin environments. Findings In two robot–skin interaction experiments, compared with the traditional impedance control and robot force control algorithm based on the radial basis function model and iterative algorithm, the maximum absolute force error, the average absolute force error and the standard deviation of the force error are all decreased. Research limitations/implications As the training process of the GRU network is currently conducted offline, the focus in the subsequent phase is to refine the network to facilitate real-time computation of the algorithm. Practical implications This algorithm can be applied to robot massage, robot B-ultrasound and other robot-assisted treatment scenarios. Originality/value As the proposed approach obtains effective force tracking during robot–skin contact and is verified by the experiment, this approach can be used in robot–skin contact scenarios to enhance the accuracy of force application by a robot.

Gaussian Process-Based Learning Control of Underactuated Balance Robots with an External and Internal Convertible Modeling Structure

Abstract External and internal convertible (EIC) form-based motion control is one of the effective designs of simultaneous trajectory tracking and balance for underactuated balance robots. Under certain conditions, the EIC-based control design is shown to lead to uncontrolled robot motion. To overcome this issue, we present a Gaussian process (GP)-based data-driven learning control for underactuated balance robots with the EIC modeling structure. Two GP-based learning controllers are presented by using the EIC structure property. The partial EIC (PEIC)-based control design partitions the robotic dynamics into a fully actuated subsystem and a reduced-order underactuated system. The null-space EIC (NEIC)-based control compensates for the uncontrolled motion in a subspace, while the other closed-loop dynamics are not affected. Under the PEIC- and NEIC-based, the tracking and balance tasks are guaranteed and convergence rate and bounded errors are achieved without causing any uncontrolled motion by the original EIC-based control. We validate the results and demonstrate the GP-based learning control design using two inverted pendulum platforms.

Design and Operational Assessment of a Railroad Track Robot for Railcar Undercarriage Condition Inspection

Design and Operational Assessment of a Railroad Track Robot for Railcar Undercarriage Condition Inspection

Reynolds Number Independence In An Urban Street Canyon Using 3D Robotic Particle Tracking Velocimetry

The Reynolds number in an Urban Street Canyon is a difficult parameter to match between reduced-scale experiments and full-scale measurements. It is possible to overcome this mismatch in Reynolds numbers by satisfying the Reynolds number independence criterion, which states that above a certain critical Reynolds number, the flow field remains invariant with increasing Reynolds numbers. For an urban canyon with an aspect ratio 1, this critical Reynolds number is often reported to be 12000 for the mean flow quantities. This critical Reynolds number, however, is not applicable for higher-order quantities such as turbulence intensity and Reynolds stresses. In this study, 3D robotic particle tracking velocimetry was used to study the flow in an urban street canyon with an aspect ratio of 1 at several Reynolds numbers to estimate the critical Reynolds number for mean flow quantities and turbulence quantities. It was found that the critical Reynolds number for mean flow quantities was between Re = 13000 and Re = 17000. For the higher-order quantities, it was found that the critical Reynolds number was above 22000.

Large-Scale Measurements Using Robotic Volumetric LPT With Shake-The-Box Inside A Vehicle Cabin: Influence Of Different Fan Speeds On The Flow Topology

In this work, the flow topology inside a passenger car cabin for different fan speeds of the heat, ventilation and air conditioning (HVAC) system is investigated using robotic volumetric Lagrangian Particle Tracking (LPT). The coaxial volumetric velocimeter (CVV), also called MiniShaker, in combination with a robotic arm enables the measurement of the complete passenger's side. In total 37 CVV perspectives (sub-volumes) were measured. At each position 3000 double frame images were recorded. The interior was painted black and the mannequin was wrapped with black aluminum foil in order to keep reflections at a low level. Experimental results for three different fan speeds using helium-filled soap bubbles (HFSB) as tracers and Shake-the-Box (StB) algorithm for the three-dimensional LPT data analyses show that the flow topology changes significantly with increasing fan speeds. At higher fan speeds the flow fields show the highest complexity with four vortices.

Positioning accuracy improvement for target point tracking of robots based on Extended Kalman Filter with an optical tracking system

Although industrial robots have been successfully used in a wide spectrum of applications for production automation, they still face challenges for many high precision tasks especially in low-volume high-mix production due to their low absolute positioning accuracy. To respond to such rapidly changing production tasks, an efficient means is required to determine the pose relationship between the robot and the workpiece without human intervention such as teaching the robot. For this purpose, the paper proposes the use of the Extended Kalman Filter (EKF) with an optical tracking system to improve the robot positioning accuracy with a particular focus on the target point tracking of the end-of-arm tool, which is an essential part for many robotic tasks. To this end, a comprehensive kinematic error model is first derived for the end-of-arm tool that accounts for the errors in the Denavit-Hartenberg (D-H) parameters, the positioning errors of the robot base and the end-of-arm tool installation. Then, by using the optical tracking system, the pose of the end-of-arm tool relative to the workpiece can be determined in an efficient way. Based on the EKF algorithm, the kinematic parameter errors of the system can be estimated online to compensate the positioning error of the target point during the robot movement. Simulation and experimental tests have been performed to demonstrate the effectiveness of the proposed method. The proposed approach utilizes the given trajectory to design a compensation scheme where the kinematic parameter errors of the robot are estimated during the motion and then the positioning error of the end-of-arm tool is compensated at the target point. As a result, this approach can improve the target point accuracy of the robot without continuous feedback to reduce the tracking error along the trajectory in real time. It is easy to implement and suitable for low-volume, high-mix scenarios to determine the pose relationship between the robot and the workpiece without human intervention.

Automated robot and artificial intelligence-powered wastewater surveillance for proactive mpox outbreak prediction

In the wake of the largest-ever recorded outbreak of mpox in terms of magnitude and geographical spread in human history since May 2022, we innovatively developed an automated online sewage virus enrichment and concentration robot for disease tracking. Coupled with an artificial intelligence (AI) model, our research aims to estimate mpox cases based on the concentration of the monkeypox virus (MPXV) in wastewater. Our research has revealed a compelling link between the levels of MPXV in wastewater and the number of clinically confirmed mpox infections, a finding that is reinforced by the ability of our AI prediction model to forecast cases with remarkable precision, capturing 87 % of the data’s variability. However, it is worth noting that this high precision in predictions may be related to the relatively high frequency of data acquisition and the relatively non-mobile isolated environment of the hospital itself. In conclusion, this study represents a significant step forward in our ability to track and respond to mpox outbreaks. It has the potential to revolutionize public health surveillance by utilizing innovative technologies for disease surveillance and prediction.

A Novel Flying Robot Swarm Formation Technique Based on Adaptive Wireless Communication using MUSIC Algorithm

This paper presents a novel technique to address the challenge of coordinating swarm flying robots in a leader-follower configuration. A combination of the Multi Signal Classification (MUSIC) estimation algorithm, based on a wireless MIMO array antenna, along with onboard robot control are used for precise route tracking of an individual robot. Employing an array antenna reduces energy consumption for followers in passive mode and reduces computational complexity when measuring the angles of leader angle interferences, which depends on the phase difference of the impinging signal on the antenna elements of the array. Additionally, the angles estimation and beamforming processes, utilizing MUSIC algorithm, form an inner loop that furnishes orientation angles in 3D (Azimuth and elevation angles) for both the leader and potential interference sources. The outer loop, contingent on the onboard controller and the robot's GPS system, enabling fine adjustments in angle and position relative to the leader's location. The simulation results illustrated the efficiency of the proposed technique in estimating the orientation angles of the leader and the interference sources. The technique robustness is confirmed through testing the performance on different trajectories. Where the follower perfectly generates a main radiation beam directed towards the leader, effectively mitigates interference signals from neighboring group leaders, and successfully tracks the leader path.

Dynamic Modeling and Tracking Of 3-Wheels Omni-Directional Mobile Robot with Manual PID Tuning Method

This paper presents the dynamic modelling and tracking control of a holonomic 3-wheel omni-directional mobile robot. A proportional integral derivative (PID) controller is used, and its performance depends on the dynamic model's accuracy. The controller design for the switched non-linear system is based on both a dynamic model and a kinematic design. A proposed dynamic model averages the contact radius of the 3-wheels. The resultant dynamic model, on average, is non-linear and smooth, serving as a potential solution for model-based control design. The closed-loop simulation results clearly illustrate the dynamic characteristics of the 3-wheels omni-directional mobile robot, offering valuable insights into its behaviour for further analysis and optimisation. Comparative simulation results using MATLAB are presented and demonstrate the effectiveness and legitimacy of the control mechanism. Keywords: Holonomic, kinematic, dynamic model, PID controller, non-linear, omni-directional robot

Simultaneous Tracking and Stabilization of Nonholonomic Wheeled Mobile Robots under Constrained Velocity and Torque

Simultaneous Tracking and Stabilization of Nonholonomic Wheeled Mobile Robots under Constrained Velocity and Torque

A robust interpolated model predictive control based on recurrent neural networks for a nonholonomic differential-drive mobile robot with quasi-LPV representation: computational complexity and conservatism

This paper presents an improved Model Predictive Control (MPC) for path tracking of a nonholonomic mobile robot with a differential drive. Nonlinear dynamics and nonholonomic constraints make the optimisation problem of MPC for the robot challenging. Nonlinear dynamics of the robots are expressed by a Linear Parameter Varying (LPV), and a Recurrent Neural Network (RNN) solves the constrained optimisation problem, providing optimal velocities. Moreover, an interpolation-based approach has been introduced to augment the region of attraction. The algorithm ensures stability in the presence of bounded disturbances through the inclusion of free control moves in the control law. The controller efficiency has been evaluated in two scenarios in a hospital setting. The simulation results illustrate that the proposed method performs better than nonlinear MPC and standard LPV-based MPC in terms of computational cost, disturbance rejection, and region of attraction.

A Simple Curvature-Based Backward Path-Tracking Control for a Mobile Robot with N Trailers

This paper introduces a two-tier feedback control law for the path tracking of a mobile robot equipped with N on-axle trailers. Initially, through a recursive design process, the curvature-tracking challenge is converted into stabilizing the joint angles at predefined reference values. This design approach is straightforward and can be easily extended to configurations with multiple trailers. Using input-to-state stability analysis, we demonstrate the asymptotic stability of the closed-loop system, which is structured in cascade form. Furthermore, we reformulate the path-tracking problem as a curvature-planning challenge and propose an algorithm to determine the desired curvature for the tail trailer. The simulation results validate the effectiveness of this novel algorithm in truck-trailer systems.

MOBILE ROBOT TRACKING SYSTEM BASED ON MACHINE VISION AND LASER RADAR

The proposed solution addresses the issue of insufficient real-time performance and accuracy in mobile robot path tracking by introducing a system that combines machine vision and laser radar. In this study, the Broadcom BCM2711 microcontroller chip is connected to the RS232 communication interface for transmitting information to the ARM embedded processor. Users can access position distance, direction, and other robot-related data through the man-machine interface's LCD display in a Windows operating system environment. By initiating an adaptive position tracking algorithm program identified by the robot within the position tracking unit, mobile position tracking of the robot is achieved. Experimental results demonstrate significant improvements in both real-time performance and accuracy of this mobile robot tracking system.

Research on coupling dynamics modeling and composite control of the multi-flexible space robot

Space robots can assist astronauts in accomplishing a variety of space missions in high-risk environments. As spacecraft become increasingly lightweight, large-scale, and integrated, space robots are a type of large-scale robots with flexible links and flexible joints. However, the flexibility of the components complicates robot modeling and controller design. Therefore, to address the issue of stable trajectory tracking for multi-flexible space robots, a dynamics model of space robots with multiple flexibilities is established, and a composite controller is designed to enhance control stability. In modeling, comprehensively considering the rigid joints, joint flexibility and link flexibility, the kinematics is consistently described by using the component deformation matrix and recursive method. An accurate dynamics model is established by Lagrange’s equations. In control, using fuzzy neural network sliding mode control, a rigid subsystem controller is designed to suppress the system jitter caused by sudden parameter changes. And it implements the robust tracking of the robot trajectory. Meanwhile, the weighted average fuzzy controller is designed to control the link deformation. The regulation of the flexible joint by the fast feedback controller is implemented using the virtual torque feedback control. Finally, the validity of the dynamics and control models is verified using Matlab and Adams. Compared with previous studies, this study considers multiple flexibility factors more fully. The vibration of multiple flexible components is suppressed during the stable trajectory tracking of the robot.

Model-based versus model-free optimal tracking for soft robots: analytical and data-driven Koopman modeling, control design and experimental validation

Model-based versus model-free optimal tracking for soft robots: analytical and data-driven Koopman modeling, control design and experimental validation

Correction: Trajectory Tracking of Differential Wheeled Mobile Robots with Input Saturation and Mismatched Centers

Correction: Trajectory Tracking of Differential Wheeled Mobile Robots with Input Saturation and Mismatched Centers

An Advanced Approach to Object Detection and Tracking in Robotics and Autonomous Vehicles Using YOLOv8 and LiDAR Data Fusion

Accurately and reliably perceiving the environment is a major challenge in autonomous driving and robotics research. Traditional vision-based methods often suffer from varying lighting conditions, occlusions, and complex environments. This paper addresses these challenges by combining a deep learning-based object detection algorithm, YOLOv8, with LiDAR data fusion technology. The principle of this combination is to merge the advantages of these technologies: YOLOv8 excels in real-time object detection and classification through RGB images, while LiDAR provides accurate distance measurement and 3D spatial information, regardless of lighting conditions. The integration aims to apply the high accuracy and robustness of YOLOv8 in identifying and classifying objects, as well as the depth data provided by LiDAR. This combination enhances the overall environmental perception, which is critical for the reliability and safety of autonomous systems. However, this fusion brings some research challenges, including data calibration between different sensors, filtering ground points from LiDAR point clouds, and managing the computational complexity of processing large datasets. This paper presents a comprehensive approach to address these challenges. Firstly, a simple algorithm is introduced to filter out ground points from LiDAR point clouds, which are essential for accurate object detection, by setting different threshold heights based on the terrain. Secondly, YOLOv8, trained on a customized dataset, is utilized for object detection in images, generating 2D bounding boxes around detected objects. Thirdly, a calibration algorithm is developed to transform 3D LiDAR coordinates to image pixel coordinates, which are vital for correlating LiDAR data with image-based object detection results. Fourthly, a method for clustering different objects based on the fused data is proposed, followed by an object tracking algorithm to compute the 3D poses of objects and their relative distances from a robot. The Agilex Scout Mini robot, equipped with Velodyne 16-channel LiDAR and an Intel D435 camera, is employed for data collection and experimentation. Finally, the experimental results validate the effectiveness of the proposed algorithms and methods.