Behaviour-based approach for skill acquisition during assembly operations, starting from scratch

Robotica ◽  
2006 ◽  
Vol 24 (6) ◽  
pp. 657-671 ◽  
Author(s):  
J. Corona-Castuera ◽  
I. Lopez-Juarez
Keyword(s):  
Neural Network ◽  
Knowledge Base ◽  
Skill Acquisition ◽  
Industrial Robot ◽  
A Priori ◽  
Industrial Robots ◽  
Fuzzy Artmap ◽  
Compliant Motion ◽  
On Line ◽  
Assembly Operations

Industrial robots in poorly structured environments have to interact compliantly with this environment for successful operations. In this paper, we present a behaviour-based approach to learn peg-in-hole operations from scratch. The robot learns autonomously the initial mapping between contact states to motion commands employing fuzzy rules and creating an Acquired-Primitive Knowledge Base (ACQ-PKB), which is later used and refined on-line by a Fuzzy ARTMAP neural network-based controller. The effectiveness of the approach is tested comparing the compliant motion behaviour using the ACQ-PKB and a priori Given-Primitive Knowledge Base (GVN-PKB). Results using a KUKA KR15 industrial robot validate the approach.

Finding Features of Positioning Error for Large Industrial Robots Based on Convolutional Neural Network

2021 ◽  
Author(s):  
Daiki Kato ◽  
Kenya Yoshitugu ◽  
Naoki Maeda ◽  
Toshiki Hirogaki ◽  
Eiichi Aoyama ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Production Systems ◽  
Industrial Robot ◽  
Three Dimensional ◽  
Industrial Robots ◽  
Numerical Control ◽  
Robot Motion ◽  
Positioning Error ◽  
End Effector

Abstract Most industrial robots are taught using the teaching playback method; therefore, they are unsuitable for use in variable production systems. Although offline teaching methods have been developed, they have not been practiced because of the low accuracy of the position and posture of the end-effector. Therefore, many studies have attempted to calibrate the position and posture but have not reached a practical level, as such methods consider the joint angle when the robot is stationary rather than the features during robot motion. Currently, it is easy to obtain servo information under numerical control operations owing to the Internet of Things technologies. In this study, we propose a method for obtaining servo information during robot motion and converting it into images to find features using a convolutional neural network (CNN). Herein, a large industrial robot was used. The three-dimensional coordinates of the end-effector were obtained using a laser tracker. The positioning error of the robot was accurately learned by the CNN. We extracted the features of the points where the positioning error was extremely large. By extracting the features of the X-axis positioning error using the CNN, the joint 1 current is a feature. This indicates that the vibration current in joint 1 is a factor in the X-axis positioning error.

On-line incremental learning for unknown conditions during assembly operations with industrial robots

2015 ◽  
Vol 6 (2) ◽  
pp. 101-114 ◽  
Author(s):  
J. L. Navarro-Gonzalez ◽  
I. Lopez-Juarez ◽  
K. Ordaz-Hernandez ◽  
R. Rios-Cabrera
Keyword(s):  
Incremental Learning ◽  
Industrial Robots ◽  
On Line ◽  
Assembly Operations

scholarly journals Vehicle Trajectory Prediction by Knowledge-Driven LSTM Network in Urban Environments

2020 ◽  
Vol 2020 ◽  
pp. 1-20
Author(s):  
Shaobo Wang ◽  
Pan Zhao ◽  
Biao Yu ◽  
Weixin Huang ◽  
Huawei Liang
Keyword(s):  
Neural Network ◽  
Knowledge Base ◽  
Prior Knowledge ◽  
Prediction Models ◽  
Short Term Memory ◽  
A Priori ◽  
Urban Environments ◽  
Intelligent Vehicles ◽  
Trajectory Prediction ◽  
Reasoning System

An accurate prediction of future trajectories of surrounding vehicles can ensure safe and reasonable interaction between intelligent vehicles and other types of vehicles. Vehicle trajectories are not only constrained by a priori knowledge about road structure, traffic signs, and traffic rules but also affected by posterior knowledge about different driving styles of drivers. The existing prediction models cannot fully combine the prior and posterior knowledge in the driving scene and perform well only in a specific traffic scenario. This paper presents a long short-term memory (LSTM) neural network driven by knowledge. First, a driving knowledge base is constructed to describe the prior knowledge about a driving scenario. Then, the prediction reference baseline (PRB) based on driving knowledge base is determined by using the rule-based online reasoning system. Finally, the future trajectory of the target vehicle is predicted by an LSTM neural network based on the prediction reference baseline, while the predicted trajectory considers both posterior and prior knowledge without increasing the computation complexity. The experimental results show that the proposed trajectory prediction model can adapt to different driving scenarios and predict trajectories with high accuracy due to the unique combination of the prior and posterior knowledge in the driving scene.

NEURAL NETWORK BASED DYNAMIC CONTROLLERS FOR INDUSTRIAL ROBOTS

1995 ◽  
Vol 06 (03) ◽  
pp. 257-271
Author(s):  
SE-YOUNG OH ◽  
WEON-CHANG SHIN ◽  
HYO-GYU KIM
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Network Architecture ◽  
Industrial Robot ◽  
Industrial Robots ◽  
System Stability ◽  
Robot Dynamics ◽  
Time Dynamic ◽  
Dynamic Controller ◽  
And Control

The industrial robot’s dynamic performance is frequently measured by positioning accuracy at high speeds and a good dynamic controller is essential that can accurately compute robot dynamics at a servo rate high enough to ensure system stability. A real-time dynamic controller for an industrial robot is developed here using neural networks. First, an efficient time-selectable hidden layer architecture has been developed based on system dynamics localized in time, which lends itself to real-time learning and control along with enhanced mapping accuracy. Second, the neural network architecture has also been specially tuned to accommodate servo dynamics. This not only facilitates the system design through reduced sensing requirements for the controller but also enhances the control performance over the control architecture neglecting servo dynamics. Experimental results demonstrate the controller’s excellent learning and control performances compared with a conventional controller and thus has good potential for practical use in industrial robots.

scholarly journals Fault Diagnosis of Industrial Robot Bearings Based on Discrete Wavelet Transform and Artificial Neural Network

2020 ◽  
Vol 7 (2) ◽  
Author(s):  
Alaa Abdulhady Jaber ◽  
Robert Bicker
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Wavelet Transform ◽  
Fault Diagnosis ◽  
Discrete Wavelet Transform ◽  
Signal Analysis ◽  
Industrial Robot ◽  
Industrial Robots ◽  
Discrete Wavelet ◽  
Bearing Faults

Industrial robots have long been used in production systems in order to improve productivity, quality and safety in automated manufacturing processes. An unforeseen robot stoppage due to different reasons has the potential to cause an interruption in the entire production line, resulting in economic and production losses. The majority of the previous research on industrial robots health monitoring is focused on monitoring of a limited number of faults, such as backlash in gears, but does not diagnose the other gear and bearing faults. Thus, the main aim of this research is to develop an intelligent condition monitoring system to diagnose the most common faults that could be progressed in the bearings of industrial robot joints, such as inner/outer race bearing faults, using vibration signal analysis. For accurate fault diagnosis, time-frequency signal analysis based on the discrete wavelet transform (DWT) is adopted to extract the most salient features related to faults, and the artificial neural network (ANN) is used for faults classification. A data acquisition system based on National Instruments (NI) software and hardware was developed for robot vibration analysis and feature extraction. An experimental investigation was accomplished using the PUMA 560 robot. Firstly, vibration signals are captured from the robot when it is moving one joint cyclically. Then, by utilising the wavelet transform, signals are decomposed into multi-band frequency levels starting from higher to lower frequencies. For each of these levels the standard deviation feature is computed and used to design, train and test the proposed neural network. The developed system has showed high reliability in diagnosing several seeded faults in the robot.

Position-Force Control for a Six Coordinate Industrial Robot when Performing Complicated Surface Treatment

2019 ◽  
Vol 20 (1) ◽  
pp. 34-43
Author(s):  
V. L. Afonin ◽  
L. V. Gavrilina ◽  
A. N. Smolentsev
Keyword(s):  
Surface Treatment ◽  
Control Method ◽  
Industrial Robot ◽  
Complex Surface ◽  
Industrial Robots ◽  
Complex Surfaces ◽  
Simultaneous Control ◽  
Cutting Surface ◽  
Assembly Operations ◽  
Executive Body

When performing certain technological operations, multi-coordinate industrial robots require simultaneous control of the movement of the executive body and the developed effort. When performing assembly operations (for example, a shaft with a bush), it is necessary to perform a free movement of the shaft along the bore of the bushing and to ensure minimum pressure on the bore walls. When performing operations to handle complex surfaces of parts, it is simultaneously required to move the tool over the surface at a specified speed and to perform a metered pressure on the surface. Since it is impossible to control the force and motion simultaneously at the same coordinate, it is necessary either to switch from one control method to another, or to control various actuators and different controllable coordinates of the actuator. In multi-coordinate robots, this task is complicated by the fact that to control the movement of one of the Cartesian coordinates of the executive body, and by another force, it is simultaneously necessary to control the interrelated generalized coordinates of the robot’s mechanism. In the work presented, the solution of the problem of control of a six-coordinate industrial robot is described, in which the separation of the degrees of mobility into power control and positional control of trajectory motion is carried out. In order to accomplish the task, additional variable parameters are introduced for the treatment of complex surfaces, which determine the position of the cutting edge on the cutting surface, which makes it possible to expand the service area of the robot during selection, for example, one of the coordinates for controlling the pressure force. This task is considered using the example of a six-coordinate industrial robot when performing a complex surface treatment operation, when it is required to program the tool at a specified speed along a path on the surface and at the same time carry out the controlled pressure of the tool on the surface.

scholarly journals Target Recognition of Industrial Robots Using Machine Vision in 5G Environment

2021 ◽  
Vol 15 ◽  
Author(s):  
Zhenkun Jin ◽  
Lei Liu ◽  
Dafeng Gong ◽  
Lei Li
Keyword(s):  
Neural Network ◽  
Visual Recognition ◽  
Simulation Analysis ◽  
Recognition Accuracy ◽  
Target Recognition ◽  
Industrial Robot ◽  
Recognition System ◽  
Industrial Robots ◽  
Network Algorithms ◽  
Positioning Errors

The purpose is to solve the problems of large positioning errors, low recognition speed, and low object recognition accuracy in industrial robot detection in a 5G environment. The convolutional neural network (CNN) model in the deep learning (DL) algorithm is adopted for image convolution, pooling, and target classification, optimizing the industrial robot visual recognition system in the improved method. With the bottled objects as the targets, the improved Fast-RCNN target detection model's algorithm is verified; with the small-size bottled objects in a complex environment as the targets, the improved VGG-16 classification network on the Hyper-Column scheme is verified. Finally, the algorithm constructed by the simulation analysis is compared with other advanced CNN algorithms. The results show that both the Fast RCN algorithm and the improved VGG-16 classification network based on the Hyper-Column scheme can position and recognize the targets with a recognition accuracy rate of 82.34%, significantly better than other advanced neural network algorithms. Therefore, the improved VGG-16 classification network based on the Hyper-Column scheme has good accuracy and effectiveness for target recognition and positioning, providing an experimental reference for industrial robots' application and development.

A comparison of industrial robots interface: force guidance system and teach pendant operation

2016 ◽  
Vol 43 (5) ◽  
pp. 552-562 ◽  
Author(s):  
Guilherme Boulhosa Rodamilans ◽  
Emília Villani ◽  
Luís Gonzaga Trabasso ◽  
Wesley Rodrigues de Oliveira ◽  
Ricardo Suterio
Keyword(s):  
Evaluation Method ◽  
Industrial Robot ◽  
Industrial Applications ◽  
Human Robot Interaction ◽  
Industrial Robots ◽  
Guidance System ◽  
Learning Criterion ◽  
Content Type ◽  
On Line ◽  
Guidance Systems

Purpose This paper aims to propose an evaluation method to compare two different Human–Robot Interaction (HRI) solutions that can be used for on-line programming in an industrial context: a force guidance system and the traditional teach pendant operation. Design/methodology/approach The method defines three evaluation criteria (agility, accuracy and learning) and describes an experimental approach based on the analysis of variance to verify the performance of guidance systems according to these criteria. This method is used in this paper to compare the traditional teach pendant interface with an implementation of a force guidance system based on the use of an external force/torque sensor. Findings The application of the proposed method to an off-the-shelf industrial robot shows that the force guidance system has a better performance according to the agility criterion. Both solutions have a similar performance for the accuracy criterion, with a limit of about 2 mm in the achieved position accuracy. Regarding the learning criterion, the authors cannot affirm that any of the methods has an improved agility when the operator repeats the tasks. Practical implications This work supports the selection of guidance systems to be used in on-line programming of industrial applications. It shows that the force guidance system is an option potentially faster than the teach pendant when the required positioning accuracy is greater than 2 mm. Originality/value The new method proposed in this paper can be applied to a large range of robots, not being limited to commercial available collaborative robots. Furthermore, the method is appropriate to accomplish further investigations in HRI not only to compare programming methods but also to evaluate guidance systems approaches or robot control systems.

Adaptive control of an industrial robot

Robotica ◽  
1986 ◽  
Vol 4 (4) ◽  
pp. 243-246 ◽  
Author(s):  
Ajit M. Karnik ◽  
Naresh K. Sinha
Keyword(s):  
Control Systems ◽  
Industrial Robot ◽  
Industrial Robots ◽  
Superior Performance ◽  
Robot Arm ◽  
Adaptive Controllers ◽  
Self Tuning ◽  
On Line ◽  
Robot Performance ◽  
And Performance

SUMMARYFor the past several years, industrial robots are being used extensively. These robots are generally equipped with relatively simple control systems. Such control systems have proved adequate, but with increased demand on robot performance, there is need for advanced and sophisticated controllers. One of the probelms in the control of robots is that system dynamics change due to several factors such as the orientation of arms and their effective inertia.Adaptive controllers have the advantage that the system is continuously modelled and controller parameters are evaluated on-line, thus resulting in superior performance. Adaptive controllers can be realized in several ways.This paper describes the design and performance of an explicit self tuning regulator for a robot arm.

Sign in / Sign up

Export Citation Format

Share Document