Gantry Robot Research Articles

Using a Yolov8-Based Object Detection Model for an Automatic Garbage Sorting System

This study presents the development of an automatic garbage sorting system based on computer vision techniques and the You Only Look Once version 8 (YOLOv8) algorithm. RGB images of garbage, including cans and plastic bottles, were collected by a camera. The YOLOv8 model, trained on a dataset of both RGB images of cans and plastic bottles, acts as the core for detection and classification. During real-time sorting, the classification results and picking points from the YOLOv8 model are used by a gantry robot. The gantry robot is developed and controlled by a Programmable Logic Controller (PLC) to place each type of garbage into its respective categories. A conveyor tracking algorithm was implemented to pick up garbage moving on the conveyor. The system's performance is evaluated using 20 garbage samples for the can and the plastic bottle category. The accuracy, precision, recall, and F1 score were 92.5%, 90.5%, 95%, and 92.7%, respectively. The system proposed in this study can be modified to sort other garbage types.

Deep learning approach for detecting tomato flowers and buds in greenhouses on 3P2R gantry robot

In recent years, significant advancements have been made in the field of smart greenhouses, particularly in the application of computer vision and robotics for pollinating flowers. Robotic pollination offers several benefits, including reduced labor requirements and preservation of costly pollen through artificial tomato pollination. However, previous studies have primarily focused on the labeling and detection of tomato flowers alone. Therefore, the objective of this study was to develop a comprehensive methodology for simultaneously labeling, training, and detecting tomato flowers specifically tailored for robotic pollination. To achieve this, transfer learning techniques were employed using well-known models, namely YOLOv5 and the recently introduced YOLOv8, for tomato flower detection. The performance of both models was evaluated using the same image dataset, and a comparison was made based on their Average Precision (AP) scores to determine the superior model. The results indicated that YOLOv8 achieved a higher mean AP (mAP) of 92.6% in tomato flower and bud detection, outperforming YOLOv5 with 91.2%. Notably, YOLOv8 also demonstrated an inference speed of 0.7 ms when considering an image size of 1920×1080\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$1920 \ imes 1080$$\\end{document} pixels resized to 640×640\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$640 \ imes 640$$\\end{document} pixels during detection. The image dataset was acquired during both morning and evening periods to minimize the impact of lighting conditions on the detection model. These findings highlight the potential of YOLOv8 for real-time detection of tomato flowers and buds, enabling further estimation of flower blooming peaks and facilitating robotic pollination. In the context of robotic pollination, the study also focuses on the deployment of the proposed detection model on the 3P2R gantry robot. The study introduces a kinematic model and a modified circuit for the gantry robot. The position-based visual servoing method is employed to approach the detected flower during the pollination process. The effectiveness of the proposed visual servoing approach is validated in both un-clustered and clustered plant environments in the laboratory setting. Additionally, this study provides valuable theoretical and practical insights for specialists in the field of greenhouse systems, particularly in the design of flower detection algorithms using computer vision and its deployment in robotic systems used in greenhouses.

Effects of the Human Presence among Robots in the ARIAC 2023 Industrial Automation Competition

ARIAC is a robotic simulation competition promoted by NIST annually since 2017, aiming to present competitors’ with contemporary industry problems to be solved using agile robotics. For the 2023 competition, ARIAC competitors must perform assembly and kitting tasks by controlling four autonomous ground vehicles (AGVs), one floor-based robot, and one ceiling-based (Gantry) robot in an attempt to overcome a range of agility challenges in the supplied simulated environment, itself based on the Robot Operating System (ROS 2) and Gazebo. The 2023 competition also included a “human” agility challenge, comprising a (simulated) human operator working among robots on the factory floor. This development was motivated by the fact that, while robots and automation play an increasingly significant role in modern manufacturing, there still remains a close relationship between machines and humans. They should complement each other’s strengths and cover each other’s limitations while also observing any required safety rules. For example, the ISO standard “Robots and Robotic Devices – Collaborative robots” (ISO 15066:2016) prescribes the distances required between humans and robots. Within the ARIAC simulation environment, each human operator is controlled using autonomous Belief-Desire-Intention (BDI) agents. At the same time, competitors can monitor the position of each human operator at any time by subscribing to the relevant ROS topic. In this article, we analyse the effects of this (simulated) human presence in the 2023 ARIAC competition and perform a detailed analysis of how the three different human personalities that were implemented affect the assembly tasks undertaken at the four different locations of the assembly stations. Given how the system is currently implemented, it appears that the influence of each encoded personality on the competitors is not as predictable as anticipated. We expand on why this may be a problem when addressing real collaborative spaces involving humans and industrial robots and the improvements that can be undertaken to mitigate the ensuing problems.

Design analysis and development of a gantry robot for multi-layer 3-D concrete printing with simulation and experimental validation

The present study investigates the design analysis and development of a framed gantry robot (FGR) for 3-D concrete printing. Finite element simulations are performed for design validation and parameter estimation to conduct detailed analysis of the concrete printer. The kinematic and dynamic models of FGR are used for workspace analysis, motion control study, and motor sizing for printer development. The motion trajectory of the printer nozzle tip is evaluated using MATLAB simulations. An integrated programmable logic controller (PLC) with an in-built human-machine interface (HMI) through control algorithms has been implemented for interactive, user-friendly, and precise motion control. A separate control system is developed to monitor the pumping power and feed rate of mortar mix during printing. The simulated control scheme is validated experimentally using trajectory tracking for various input printing paths through HMI, with a maximum tracking error of 1 mm. Successful concrete printing trials have been conducted using various mix-design, following extensive evaluation of different printer and material parameters at the laboratory scale. The proposed design concept, mechanisms, interactive control interface, and tracking accuracy have been validated through simulation and experimental results, for ensuring quality concrete prints by the developed printer. Material testing parameters have been evaluated experimentally for modeling various mix-designs. To further evaluate printing performance, simulations of layer deformation in printed structures are conducted using finite element analysis, incorporating non-linear material models and various contact layer interactions. The simulated results of printed layers of different shapes of structures show a close resemblance with the experimental concrete printing trials.

Developing a Gantry Robot with Pre-calculated pure S-curve Motion Profiles for Delicate Egg Handling: Utilizing ESP32, FreeRTOS, and AS5600 Encoders

The poultry industry faces challenges due to egg breakage during transfer. This paper describes a gantry robot specifically designed for delicate egg handling. The robot utilizes pre-calculated pure S-curve motion profiles to achieve smooth and precise movements, minimizing stress on the eggs. This approach leverages the computational efficiency of pre-calculation, making it suitable for low-power microcontrollers like the ESP32. FreeRTOS(Free Real-Time Operating System) ensures real-time task management for profile execution and data collection every 4 milliseconds from the AS5600 encoders. These encoders provide high-resolution angular position feedback, allowing for comparison with the planned S-curve profile after each movement step. This system offers advantages such as reduced egg breakage, improved transfer efficiency, and a simpler design compared to real-time control. However, limitations include limited adaptability to significant environmental changes and disturbances. Future work may investigate incorporating real-time feedback control for enhanced robustness.

Development of a dry mock-up system for verifying pyroprocess automation

This paper presents the design and operation of an autonomous robot for pyroprocess automation, which requires unique approaches beyond those used in industrial applications to achieve the desired performance. Maintaining an extremely dry atmosphere is crucial to handle various materials, including chloride, and an autonomous system ensures this dry environment. The drying room dehumidifier was carefully selected and designed to generate dry air, and different types of dry air conditioning performance were evaluated, including assessing worker accessibility inside the mock-up to determine the system's feasibility. Containers used for process materials were modified to fit the gripper system of the gantry robot for automation. The loading and unloading of process materials in each equipment were automatically performed to connect the process equipment with the robotic system. The gantry robot primarily operated through macro motion to approach waypoints containing process materials, eliminating the need for precise approach motion. The robot's tapered jaw design allowed it to grasp the target object even with imperfect positioning. Robot motions were programmed using a robot simulator for initial positioning and motion planning, and real accuracy was tested in a mock-up facility using the OPC platform.

Consequent pole flux modulated linear actuator under winding chang and field oriented control driving conditions for long track and multi-track agricultural robot

The electromagnetic performance improvement of a double saliency (DS) flux modulated (FM)- permanent magnet linear synchronous motors (PMLSM) for agricultural robots is proposed in this work by minimizing the effect of cross-coupling. To understand the effect of the cross-coupling on the electromagnetic performance, a dq axes model of the DS FM-PMLSM is developed and analyzed under different driving conditions. Based on the result obtained, winding modification schemes are proposed to minimize the thrust ripple and improve the zero torque control. The modified models are studied using finite element analysis (FEA) and the model with the best performance is selected for prototyping. The prototype is then tested and the results are validated against the electromagnetic performance obtained using the FEA. This research targeted the development of a low-cost linear actuator for a sapling grower gantry robot that can be used by farmers around the world.

Gantry Robot System Checkers Player

Technological developments in the field of moving goods are increasing rapidly. Production processes in fields such as the automotive, medical world, and even for household needs use the Pick and Place system for the production process. It has been proven, for a long time, that research has improved the Pick and Place system for many sectors, especially how this process can be combined with AI. Because of this, there has been a lot of research on how to make robots play games with their own brains. For now, most of the game development for AI is board games such as chess, Checkers, Tic Tac Toe, and other board games. Therefore, this paper will explain how to make a robot that can play board games. By implementing the gantry robot system, the robot will be made to play the Checkers game by integrating the robot with the existing AI checker. The concept of this robot is to use Checkers AI and machine integration with a camera where the robot will compete with humans, the camera will detect it from the game board, and then with the learning process from AI, the robot can determine where to move the pieces and it is hoped that the motor will move according to the AI output command of the Checkers Robot. After tha,t the robot will return to its original position and wait for its turn.

Process of Learning from Demonstration with Paraconsistent Artificial Neural Cells for Application in Linear Cartesian Robots

Paraconsistent Annotated Logic (PAL) is a type of non-classical logic based on concepts that allow, under certain conditions, for one to accept contradictions without invalidating conclusions. The Paraconsistent Artificial Neural Cell of Learning (lPANCell) algorithm was created from PAL-based equations. With its procedures for learning discrete patterns being represented by values contained in the closed interval between 0 and 1, the lPANCell algorithm presents responses similar to those of nonlinear dynamical systems. In this work, several tests were carried out to validate the operation of the lPANCell algorithm in a learning from demonstration (LfD) framework applied to a linear Cartesian robot (gantry robot), which was moving rectangular metallic workpieces. For the LfD process used in the teaching of trajectories in the x and y axes of the linear Cartesian robot, a Paraconsistent Artificial Neural Network (lPANnet) was built, which was composed of eight lPANCells. The results showed that lPANnet has dynamic properties with a robustness to disturbances, both in the learning process by demonstration, as well as in the imitation process. Based on this work, paraconsistent artificial neural networks of a greater complexity, which are composed of lPANCells, can be formed. This study will provide a strong contribution to research regarding learning from demonstration frameworks being applied in robotics.

Iterative learning control for piecewise arc path tracking with validation on a gantry robot manufacturing platform

The piecewise arc path tracking problem is a common feature of manufacturing systems operating in a repetitive mode, e.g. assembly production lines. Here, the system end-effector must follow a spatial path without any specific temporal tracking constraints, which makes the temporal profile not fixed a priori. The technique of iterative learning control (ILC) is well-suited to handle this problem, since compared to classical feedback control methods, ILC is capable of learning from previous trial information to minimize the tracking error over repeated trials. This paper extends the ILC task description to address piecewise arc path tracking tasks, and further formulates a more general design framework than existing spatial ILC approaches. A comprehensive ILC algorithm is designed to handle this class of piecewise arc path tracking problems, and practical implementation instructions are provided. Validation is conducted on a gantry robot manufacturing testbed to confirm its feasibility and efficiency in practice with a comparison to existing methods showing its higher path tracking accuracy.

Mathematical Model to Predict Thrust Ripple in Double Salient Flux-Modulated Linear Permanent for Five-Axis Gantry Robot Under Field Oriented Control

This article proposes a detailed mathematical <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">dqn</i> axes dynamic modeling of a double saliency flux modulated permanent magnet linear synchronous motor used as the linear actuator for the five-axis gantry robot system to study thrust ripple characteristics. To derive the model, the machine double saliency is considered by analyzing the effect of the cross-coupling inductances into the dynamic voltage equation in <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">dqn</i> axes. The electromagnetic performances such as the electromagnetic thrust and the thrust ripple is formulated to check the maximum limit of the thrust ripple at the initial design stage using the derived model. The whole process is validated using 2-D, 3-D finite element analysis, and manufactured prototype under driving conditions.

Emerging robust and data‐driven control methods for uncertain learning systems

Emerging robust and data‐driven control methods for uncertain learning systems

Hybrid Active–Passive Robust Control Framework of a Flexure-Joint Dual-Drive Gantry Robot for High-Precision Contouring Tasks

For high-precision contouring tasks in a typical Cartesian motion system, multiaxis cooperation is a long-standing challenging issue. Inevitably, various factors pose substantial difficulty in the multiaxis cooperation leading to degraded contouring performance, such as the strong coupling effect between different axes, nonlinearity, the unknown dynamics due to the friction, and the difficulties in accurate system identification. To enhance the contouring performance of a flexure-joint dual-drive gantry system against the aforementioned issues, this article presents a hybrid active–passive robust control framework leveraging a model-free architecture. In this control scheme, all the coupling effects, nonlinearity, disturbance, and unknown dynamics are considered as “lumped uncertainty”. Then, a super-twisting sliding mode control method with a signum-type iterative learning law is proposed to passively suppress the lumped uncertainty during iterations; and an extended state observer is deployed to actively compensate the lumped uncertainty and ensure the establishment of sliding motion in the time domain. As supported by theoretical analysis, the proposed controller is shown to exhibit several important properties. First, the establishment of the sliding motion is guaranteed globally, in both the time domain and the iteration domain. Second, the properties of short establishment time of the sliding motion, fast convergence during the iterations, and low chattering are achieved. Moreover, a series of comparative experiments are conducted, and the proposed method is shown to be rather effective in achieving excellent contouring performance in the high-speed and complex-curvature contouring tasks, without relying on the system model.

Investigation of the effect of algorithms of positioning robots on their power and energy consumption

The paper is devoted to the study of motion algorithms that determine the power and energy consumption of process equipment and positioning robots, which are important factors affecting the environment and environmental safety of the technosphere. Based on the study of mathematical models of the degrees of mobility of the gantry robot drives, it is found that under the traditional laws of motion, a fairly significant peak in power consumption occurs at the end of acceleration. The paper shows that by separating in time the moments of the end of acceleration of different drives, it is possible to significantly reduce the maximum power of the robot. A comprehensive approach to the choice of an algorithm and laws of motion that provide an acceptable combination of energy consumption and maximum power consumption has been developed. The authors have shown that there are such laws of motion that ensure the constancy of power for the duration of the acceleration stage and its minimization. The relationship between the minimum instantaneous power and power consumption for such robots has been established. The results obtained can be used to optimize the operation algorithms of both of existing and newly +-robots.

Determination of Design Parameters Considering Working Harmonic and Irreversible Demagnetization for Flux-Modulated Linear Actuator

This article proposes a design process for a flux modulated (FM) permanent-magnet linear actuator for a five-axis gantry robot system by investigating the parameters affecting working harmonics. A detailed design process using the magnetic gearing effect was developed by considering the magnetic equivalent circuit and finite element analysis models of the FM-linear actuator. Considering natural cooling, the design process includes the effect of irreversible demagnetization when selecting the design parameters. Using the design parameters, a final simulation model was created to check the electromagnetic performance under both no-load and full-load conditions. A prototype was built to validate the results obtained using the proposed analytical model.

Iterative Learning Control for Robotic Path Following With Trial-Varying Motion Profiles

Iterative learning control (ILC) aims to maximize the performance of systems performing repeated tracking tasks. However, in most existing applications, the motion profile is inherently specified <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a priori</i> , which has restricted both its application range and scope of performance improvement. For example, the typical repeated path-following task in robotics only requires a spatial path profile rather than a temporal trajectory profile, for which most existing ILC designs are unsuitable. To handle this requirement, this article extends the ILC task description by relaxing this postulate to enable a trial-varying motion profile and formulate an ILC path-following problem with system constraints. Under this extended problem setup, a spatial ILC algorithm is proposed with efficient implementation and robust convergence analysis, which updates the input signal and motion profile at the end of each trial to reduce the tracking error. This algorithm is implemented experimentally on a gantry robot test platform to verify performance, practical feasibility, and reliability. Comparisons with other control methods are also made to clarify its advantages, such as error reduction, control effort reduction, and constraint handling.

Image processing-based realization of servo motor control on a Cartesian Robot with Rexroth PLC

The aim of this study was to separate the objects, whose position was determined using Rexroth PLC on a workbench, and bring them to different locations. Position control of synchronous motors with PLC was done with coordinates obtained by image processing. A real-time Gantry robot was set up for the study. An image taken with the camera connected to Gantry robot is transferred to the Matlab environment. The coordinate data obtained by processing the image are separated for the coordinates used, and the position control of the motors is provided. First, the image was changed to grayscale to apply image processing methods. Then, with the image processing formula, ‘viscircles’ has been applied to mark the detected circles. The obtained coordinates were transferred to IndraWorks PLC to be used in the portal robot. Objects in the determined coordinates were moved to another coordinate with the help of the pneumatic system that integrated to Gantry Robot. The system has been tested for different conditions. As a result of studies, it has been observed that both the image processing method and the system work simultaneously with high accuracy. It is thought that the study can be used in many areas in the literature.

Indirect Method to Measure of Initial Mover Position in Flux-Modulated Linear Actuator for Five-Axis Gantry Robot Using Low-Cost Current Sensors and Considering End Effect

An initial mover position (IMP) detection algorithm for a dual-saliency flux-modulated permanent magnet linear synchronous motor (DS FM-PMLSM) for a five-axis gantry robot has been proposed in this proposed work. The proposed IMP algorithm uses the saliency of the proposed machine, which results in the inductance variation and checks the change in the inductance by providing sequential current profiles. The effect of the end region at the entry and exit are included to check the robustness of the proposed IMP. A design platform using MATLAB and Altair-Flux has been developed to simulate the proposed IMP algorithm for different positions of the mover. Based on the simulation model, a test setup is developed using a low-cost sensor and six-step inverter and tested the validity of the proposed IMP algorithm for the DS FM-PMLSM.

Novel method for welding gantry robot scheduling at shipyards

ABSTRACT Welding is the most critical operation in the shipbuilding process and has a significant influence on the production cost and quality of ships. Therefore, the welding operation must be optimised. This paper presents a real-world welding gantry robot scheduling problem at shipyards, in which three gantry robots function in parallel. Welding gantry robots cannot cross each other and should operate over a certain distance to avoid collisions. To minimise the makespan, the welding tasks given by line segments should be evenly distributed among the three gantry robots. The welding tasks assigned to each robot should be optimally sequenced to minimise the completion time, including the waiting time required to prevent collisions with neighbouring robots. In addition, long welding edges are split, and the split small length edges are assigned to the gantry robots. This paper proposes a mixed-integer linear programming model, three-stage solution approach, and variable neighbourhood search algorithm to solve this problem. Experimental tests conducted on 20 real problem instances revealed that the proposed approach can reduce the makespan by 14% on average when compared with the conventional method.

Influence of Structural and Physical Parameters on Working Harmonic of Flux-Modulated Linear Actuator for Energy Storage System Fire Hazard Detection Robot

This paper proposes the design and analysis of a flux modulated (FM) permanent magnet (PM) linear actuator for the long track gantry robot system used to detect fire hazards in an electric energy storage system (ESS). A detailed design framework for the FM-linear actuator inspired by the magnetic gearing effect is proposed which includes the selection of slot-pole pair numbers and assigning optimal geometric parameters based on working harmonic characteristics. Using the optimal model, the electromagnetic performances both under no-load and full load conditions are performed to check the feasibility of the actuator for the gantry system. A prototype is built to validate the results obtained using the 2D and 3D finite element analysis (FEA).