Optimization of HOG Algorithm for Computer Vision in Industrial Robots

Precision component displacement, processing, and manipulation in an industrial environment require the high-precision positioning and orientation of industrial robots. However, industrial robots’ positioning includes uncertainties due to assembly and manufacturing tolerances. It is therefore required to use calibration techniques for industrial robot parameters. One of the major sources of uncertainty is the one associated with industrial robot geometrical parameter values. In this paper, using multi-objective meta-heuristic optimization approaches and optical metrology measurements, more accurate Denavit–Hartenberg (DH) geometrical parameters of an industrial robot are estimated. The sensor data used to perform this calibration are the absolute 3D position readings using a highly accurate laser tracker (LT) and industrial robot joint angle readings. Other than position accuracy, the mean absolute deviation of the DH parameters from the manufacturer’s given parameters is considered as the second objective function. Therefore, the optimization problem investigated in this paper is a multi-objective one. The solution to the multi-objective optimization problem is obtained using different evolutionary and swarm optimization approaches. The evolutionary optimization approaches are nondominated sorting genetic algorithms and a multi-objective evolutionary algorithm based on decomposition. The swarm optimization approach considered in this paper is multi-objective particle swarm optimization. It is observed that NSGAII outperforms the other two optimization algorithms in terms of a more diverse Pareto front and the function corresponding to the positional accuracy. It is further observed that through using NSGAII for calibration purposes, the root mean squared for positional error has been improved significantly compared with nominal values.

Robotic automation is consuming the laborious tasks performed by workers all over industry. The increasing demand for trained robotic engineers to implement and maintain industrial robots has led to the development of various courses in academia. Michigan Tech is a FANUC Authorized Certified Education Training Center for industrial robot training. This report discusses the research and development of an integrated robotic workcell consisting of three Fanuc robots, Allen Bradley programmable logic controller (PLC), Mini-Mover belt conveyor and Fanuc iR-vision system. The workcell allows students to explore an environment similar to industry and intended to be used for laboratory hands-on activities in two robotic courses: Real-time Robotic Systems and Industrial Robotic Vision System. To complement hands-on activities and to meet the need of educating robotics to those without access to physical robots, an open source robotic simulation software "RobotRun" has been created in collaboration with a faculty member and students from Computer Science department. The features and a few training examples on the software have also been presented.

Blind-Kriging based natural frequency modeling of industrial Robot

Due to insufficient absolute positioning accuracy, industrial robots frequently face challenges in efficiently performing drilling and riveting operations during the assembly of aircraft and other large-scale workpieces. To enhance the absolute positioning accuracy of industrial robots, this paper proposes a novel kinematic calibration method for industrial robots based on the Improved Grey Wolf Optimization (IGWO) algorithm. Specifically, the method employs an enhanced selection and update strategy to avoid convergence stagnation and local optimum traps. The proposed method features a novel boundary search strategy, which leverages the Dimension-oriented Learning (DL) search strategy to enhance search speed and stability. Through parameter identification and calibration experiments, the effectiveness of the method was validated using an ABB IRB4600 industrial robot and a Leica laser tracker. Additionally, compared with the Levenberg–Marquardt (LM) algorithm, Particle Swarm Optimization (PSO), and Genetic Algorithm (GA), the IGWO algorithm demonstrates faster convergence and superior optimization performance. According to the calibration experimental results, by applying the IGWO algorithm, the absolute positioning accuracy of the industrial robot is ultimately improved from 1.918 mm to 0.475 mm and the absolute positioning accuracy is improved by 75.2%.

Motion and control system with industrial robot in multi-degree of freedom (multi-DOF) is the typical mechatronics system, which combines mechanics, electronics, sensors, computer hardware and software, control, artificial intelligence and modeling technology, and many other advanced technologies. This paper establishes a six-DOF welding robot model, and proposes a complex control method based on improved neural network-PID which uses PSO algorithm's global optimization capability and strong convergence to improve BP network weights. The method is based on backward error propagation of the basic BP algorithm, adjusting the BP network weights and thresholds corresponding to the updating particle position. It takes full advantage of the global optimization of PSO algorithm and maintains the BP algorithm's back-propagation characteristics better. The simulation results show that the method can optimize the dynamic process and reduce the steady-state error of system. It has good value for the control technology.

The purpose of this work is to explore the design principles for a Real-Time Robotic Multi Camera Vision System, in a case study involving a real world competition of autonomous driving. Design practices from vision and real-time research areas are applied into a Real-Time Robotic Vision application, thus exemplifying good algorithm design practices, the advantages of employing the “zero copy one pass” methodology and associated trade-offs leading to the selection of a controller platform. The vision tasks under study are: (i) recognition of a “flat” signal; and (ii) track following, requiring 3D reconstruction. This research firstly improves the used algorithms for the mentioned tasks and finally selects the controller hardware. Optimization for the shown algorithms yielded from 1.5 times to 190 times improvements, always with acceptable quality for the target application, with algorithm optimization being more important on lower computing power platforms. Results also include a 3-cm and five-degree accuracy for lane tracking and 100% accuracy for signalling panel recognition, which are better than most results found in the literature for this application. Clear results comparing different PC platforms for the mentioned Robotic Vision tasks are also shown, demonstrating trade-offs between accuracy and computing power, leading to the proper choice of control platform. The presented design principles are portable to other applications, where Real-Time constraints exist.

In the joint electrical drive system of industrial robots, the optimization and improvement of robot motion control is one of the hotspots of current research, and this paper proposes a method of optimizing the joint electrical drive control of robots using multilevel genetic algorithm.An improved PID control method is used to fuzzify the robot motion, and the robot trajectory fuzzy PID controller is optimized according to the idea of multilevel genetic algorithm.The rise time of each joint of the robot is about 5ms, 55ms, and 75ms, respectively, and the overshooting amount is smaller, and the optimized joint electrical drive system of the industrial robot is more stable in speed control in both the acceleration and deceleration phases, and shows a good dynamic control capability of the motion.It can be seen that the work in this study effectively optimizes the control performance of the industrial robot drive system using multilevel genetic algorithm.

Based on unity3D, an industrial robot application simulation teaching platform is designed to solve the problems of high cost and limited quantity of robot equipment introduction in the current industrial robot teaching. By restoring the real five processes of stacking, grinding, vision, assembly and warehouse storage of industrial robot, not only the teaching efficiency of teachers is improved, but also the robot teaching efficiency of students is improved. Level of understanding and practice.

The rapid growth of robotics and automation, especially during the last few years, its current positive impact and future projections for impact on the United States economy are very promising. This rapid growth of robotic automation in all sectors of industry will require an enormous number of technically sound specialists with the skills in industrial robotics and automation to maintain and monitor existing robots, enhance development of future technologies, and educate users on implementation and applications. It is critical, therefore, that educational institutions adequately respond to this high demand for robotics specialists by developing and offering appropriate courses geared towards professional certification in robotics and automation. In order to effectively teach concepts of industrial robotics, the curriculum needs to be supported by the hands on activities utilizing industrial robots or providing training on robotic simulation software. Nowadays, there is no robotic simulation software available to the academic institution at no cost which limits educational opportunities. As part of the NSF sponsored project, team of faculty members and students from Michigan Tech are developing new, open source RobotRun robotic simulation software which will be available at no cost for adaptation by the other institutions. This will allow current concepts related to industrial robotics to be taught even in locations without access to current robotics hardware. In addition, to teach emerging concepts of robotics, automation, and controls, authors present the design and development the state-of-the-art robotic workcell consisting of 3 FANUC industrial robots equipped with robotic vision system, programmable logic controller, a conveyer and various sensors. The workcell enables the development and programing of various industry-oriented scenerious and therefore provide students with the opportunity of gaining skills that are relevant to current industry needs.

Convolutional Neural Networks (CNNs) have recently been utilized in a wide range of applications, including image and pattern identification, voice recognition, biometric embedded vision, food recognition, and video analysis for surveillance, industrial robots, and autonomous vehicles. Convolutional neural networks (CNNs) are gaining popularity for a variety of reasons. Feature extractors are created by hand in classic image recognition models. The weights of the convolutional layer utilized for feature extraction, as well as the fully connected layer, are used for classification in CNNs, and these weights are set throughout the training phase. The goal of this study is to evaluate a few convolutional neural network (CNN) learning machine approaches for image recognition. Furthermore, machine learning algorithms are used extensively in contemporary approaches to picture recognition. This article focuses on the development trend of convolution neural network (CNNs) model owing to various learning methods in image recognition during the 2000s, which is largely introduced from the angles of capturing, verification, and clustering, based on twenty five journals that have been reviewed. As a result, deep convolutional neural networks (DCNNs) have been very effective in a variety of machine learning and computer vision problems because they provide a large quality gain at a low computational cost. This training approach also enables models with many processing layers to learn different degrees of abstraction for data representation.

Deep learning is the mainstream paradigm in computer vision and machine learning, but performance is usually not as good as expected when used for applications in robot vision. The problem is that robot sensing is inherently active, and often, relevant data is scarce for many application domains. This calls for novel deep learning approaches that can offer a good performance at a lower data consumption cost. We address here monocular depth estimation in warehouse automation with new methods and three different deep architectures. Our results suggest that the incorporation of sensor models and prior knowledge relative to robotic active vision, can consistently improve the results and learning performance from fewer than usual training samples, as compared to standard data-driven deep learning.

The evolution of industrial robotics has advanced from isolated, caged systems through basic human–robot interaction (HRI) to sophisticated human–robot collaboration (HRC). However, conventional vision systems based on red, green, blue (RGB) cameras remain a significant limiting factor in realizing the full potential of collaborative automation. This comprehensive review examines the transformative role of event cameras in advancing HRC capabilities and addressing current limitations in industrial settings. Event cameras, with their microsecond-level temporal resolution and robust performance under challenging lighting conditions, offer substantial advantages over traditional RGB cameras that are constrained by fixed frame rates and ambient lighting dependencies. We present a systematic framework for leveraging event cameras to enhance the human state understanding in collaborative robotics, encompassing real-time detection of poses, gestures, facial expressions, and emotional states. This framework addresses fundamental challenges in workplace safety and collaborative efficiency while enabling more sophisticated and responsive HRC systems. Our review synthesizes recent research developments in event camera applications specific to HRC, providing a detailed comparative analysis of their advantages over conventional vision systems. We identify emerging opportunities and potential research directions for advancing event-based vision in industrial robotics. In addition, we examine integration challenges and propose strategies for implementing event camera technology in existing industrial infrastructure. This work contributes valuable insights into the future trajectory of adaptive and intuitive HRC systems, offering a roadmap for researchers and practitioners in the field of industrial automation.

The load distribution problem for two coordinating industrial robots handling a single object is studied in this paper. When two industrial robots grasp a single object, the total number of applied torques is usually greater than six. Thus the joint torques of two robots for a required motion of the object is not unique. The redundant degrees of freedom may be used to optimize certain kind of performance. We first select the least energy consumption as the optimization criterion. Optimal algorithms without and with a bound on the joint torques are investigated. The results show that the algorithms are computationally complicated which are not suitable for real-time applications. Alternatively, optimal algorithms are then proposed for load distribution with minimum exerted forces on the object. The algorithms are obtained with much less computational time, which makes it attractive for real-time applications. The algorithms are applied to two PUMA 560 type robots as an illustration.

The load distribution problem for two coordinating industrial robots handling a single object is studied. When two industrial robots grasp a single object, the total number of degrees of freedom is usually greater than six. Thus, the joint torques of two robots for a required motion of the object is not unique. The redundant degrees of freedom may be used to optimize certain kind of performance. The least energy consumption is selected as the optimization criterion. Optimal algorithms without and with a bound on the joint torques are investigated. The results show that the algorithms are computationally complicated and not suitable for real-time applications. Alternatively, optimal algorithms are proposed for load distribution with minimum exerted forces on the object. These algorithms require less computational time, which makes them attractive for real-time applications. >

A particle swarm optimization (PSO) algorithm which can dynamically adjust learning factors is proposed to solve the problems of low efficiency and unstable operation of traditional industrial robots. The method uses piecewise polynomial interpolation to fit the trajectory, and uses an improved particle swarm algorithm to optimize the trajectory of industrial robots with time as a fitness function. This method effectively combines the piecewise polynomial interpolation function with PSO, avoids the complex process of particle swarm algorithm to construct the adaptation function, and improves the problem that the traditional PSO is more likely to fall into local extreme value in the early stage and convergence speed is slow in the later stage. Through experiments to obtain the motion pose, velocity and acceleration trajectory of each joint of the manipulator, we can know that this method can effectively realize the trajectory optimization of the industrial robot, and ensure the stability of the overall operation while improving the operating efficiency.