Industrial robot programming by demonstration using stereoscopic vision and inertial sensing

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
João Pedro C. de Souza ◽  
António M. Amorim ◽  
Luís F. Rocha ◽  
Vítor H. Pinto ◽  
António Paulo Moreira
Keyword(s):  
Industrial Robot ◽  
Tracking System ◽  
Low Cost ◽  
Stereoscopic Vision ◽  
Shop Floor ◽  
Programming By Demonstration ◽  
Inertial Sensing ◽  
Software Pipeline ◽  
Content Type ◽  
Pose Tracking

Purpose The purpose of this paper is to present a programming by demonstration (PbD) system based on 3D stereoscopic vision and inertial sensing that provides a cost-effective pose tracking system, even during error-prone situations, such as camera occlusions. Design/methodology/approach The proposed PbD system is based on the 6D Mimic innovative solution, whose six degrees of freedom marker hardware had to be revised and restructured to accommodate an IMU sensor. Additionally, a new software pipeline was designed to include this new sensing device, seeking the improvement of the overall system’s robustness in stereoscopic vision occlusion situations. Findings The IMU component and the new software pipeline allow the 6D Mimic system to successfully maintain the pose tracking when the main tracking tool, i.e. the stereoscopic vision, fails. Therefore, the system improves in terms of reliability, robustness, and accuracy which were verified by real experiments. Practical implications Based on this proposal, the 6D Mimic system reaches a reliable and low-cost PbD methodology. Therefore, the robot can accurately replicate, on an industrial scale, the artisan level performance of highly skilled shop-floor operators. Originality/value To the best of the authors’ knowledge, the sensor fusion between stereoscopic images and IMU applied to robot PbD is a novel approach. The system is entirely designed aiming to reduce costs and taking advantage of an offline processing step for data analysis, filtering and fusion, enhancing the reliability of the PbD system.

Automated de-stacking using compact and low-cost robotized system

2014 ◽  
Vol 41 (2) ◽  
pp. 176-189
Author(s):  
Yufeng Qu ◽  
Guanghua Zong
Keyword(s):  
Industrial Robot ◽  
Low Cost ◽  
Laser Scanner ◽  
Processing Method ◽  
Depth Image ◽  
Content Type ◽  
Video Cameras ◽  
Image Histogram ◽  
Data Processing Method ◽  
Cost Measurement

Purpose – This paper aims to introduce a compact and low-cost robotized system and corresponding processing method for automatically identifying and de-stacking circulation boxes under natural stacking status. Design/methodology/approach – The whole system is composed of an industrial robot, a laser scanner and a computer. Automated de-stacking requires comprehensive and accurate status information of each box. To achieve this goal, the robot carries the laser scanner to perform linear scanning to describe a full depth image for the whole working area. Gaussian filter is applied to the image histogram to suppress the undesired noise. Draining and flooding process derived from classic algorithm identifies each box region from an intensity image. After parameters calculation and calibration, the grasping strategy is estimated and transferred to the robot to finish the de-stacking task. Findings – Currently, without pre-defined stack status, there is still manual operated alignment in stacking process in order to enable automatic de-stacking using robot. Complicated multi-sensor system such as video cameras can recognize the stack status but also brings high-cost and poor adaptability. It is meaningful to research on the efficient and low-cost measurement system as well as corresponding common data processing method. Research limitations/implications – This research presents an efficient solution to automated de-stacking task and only tests for three columns stack depending on the actual working condition. It still needs to be developed and tested for more situations. Originality/value – Utilizing only single laser scanner to measure box status instead of multi-sensor is novel and identification method in research can be suitable for different box types and sizes.

The Pransky interview: Dr Paolo Pirjanian, CTO of iRobot Corporation

2014 ◽  
Vol 41 (1) ◽  
pp. 1-5 ◽  
Author(s):  
Joanne Pransky
Keyword(s):  
Personal Experience ◽  
Industrial Robot ◽  
Low Cost ◽  
Early Career ◽  
Consumer Product ◽  
Content Type ◽  
Technical Leadership ◽  
Cleaning Robot ◽  
Localization And Mapping ◽  
Start Up

Purpose – PhD/inventor builds consumer robot start-up company based on low-cost, groundbreaking visual simultaneous localization and mapping (vSLAM) visual sensors and NorthStar® navigation technologies that sells for nearly $75 million dollars 12 years later. The following article is a “Q&A interview” conducted by Joanne Pransky of Industrial Robot Journal as a method to impart the combined technological, business, and personal experience of a prominent, robotic industry engineer-turned entrepreneur regarding the evolution, commercialization, and challenges of bringing a technological invention to market. The paper aims to discuss these issues. Design/methodology/approach – This interview was with Dr Paolo Pirjanian, CTO of iRobot Corporation. Dr Pirjanian previously served as both CTO and CEO of Evolution Robotics. Dr Pirjanian received his PhD degree from Aalborg University, Denmark. He has received several honors and awards including the IEEE Robotics and Automation Society Early Career Award in 2004 and the Technical Leadership Award from JPL/NASA. Dr Pirjanian holds 67 patents. Findings – The challenges and solutions of transferring technological innovations into an affordable consumer product are presented. The resulting pioneering technologies and approximate 37 patents around vSLAM and NorthStar® were incorporated into Evolution's flagship consumer product, Mint floor cleaning robot. In October 2012, iRobot Corp acquired Evolution for $74 million in an effort to complement their own products and technologies. Originality/value – A robot scientist, in his roles as the CTO and CEO of a robot company, uses a paradigm shift in vision and pattern recognition to build an affordable consumer product and successful company.

Robot programming by demonstration using teleoperation through imitation

2017 ◽  
Vol 44 (2) ◽  
pp. 142-154 ◽  
Author(s):  
Abhishek Jha ◽  
Shital S. Chiddarwar
Keyword(s):  
Real Time ◽  
Degrees Of Freedom ◽  
Industrial Robot ◽  
Learning Ability ◽  
Robot Programming ◽  
Programming Approach ◽  
Programming By Demonstration ◽  
Real Time Control ◽  
Content Type ◽  
Direct Learning

Purpose This paper aims to present a new learning from demonstration-based trajectory planner that generalizes and extracts relevant features of the desired motion for an industrial robot. Design/methodology/approach The proposed trajectory planner is based on the concept of human arm motion imitation by the robot end-effector. The teleoperation-based real-time control architecture is used for direct and effective imitation learning. Using this architecture, a self-sufficient trajectory planner is designed which has inbuilt mapping strategy and direct learning ability. The proposed approach is also compared with the conventional robot programming approach. Findings The developed planner was implemented on the 5 degrees-of-freedom industrial robot SCORBOT ER-4u for an object manipulation task. The experimental results revealed that despite morphological differences, the robot imitated the demonstrated trajectory with more than 90 per cent geometric similarity and 60 per cent of the demonstrations were successfully learned by the robot with good positioning accuracy. The proposed planner shows an upper hand over the existing approach in robustness and operational ease. Research limitations/implications The approach assumes that the human demonstrator has the requisite expertise of the task demonstration and robot teleoperation. Moreover, the kinematic capabilities and the workspace conditions of the robot are known a priori. Practical implications The real-time implementation of the proposed methodology is possible and can be successfully used for industrial automation with very little knowledge of robot programming. The proposed approach reduces the complexities involved in robot programming by direct learning of the task from the demonstration given by the teacher. Originality/value This paper discusses a new framework blended with teleoperation and kinematic considerations of the Cartesian space, as well joint space of human and industrial robot and optimization for the robot programming by demonstration.

Manual guidance for industrial robot programming

2015 ◽  
Vol 42 (5) ◽  
pp. 457-465 ◽  
Author(s):  
Daniele Massa ◽  
Massimo Callegari ◽  
Cristina Cristalli
Keyword(s):  
Industrial Robot ◽  
Robot Programming ◽  
Use Case ◽  
Programming By Demonstration ◽  
Content Type ◽  
Safety Standards ◽  
Novel Approach ◽  
Complete State ◽  
Speed Up ◽  
Practical Implications

Purpose – This paper aims to deal with the problem of programming robots in industrial contexts, where the need of easy programming is increasing, while robustness and safety remain fundamental aspects. Design/methodology/approach – A novel approach of robot programming can be identified with the manual guidance that permits to the operator to freely move the robot through its task; the task can then be taught using Programming by Demonstration methods or simple reproduction. Findings – In this work, the different ways to achieve manual guidance are discussed and an implementation using a force/torque sensor is provided. Experimental results and a use case are also presented. Practical implications – The use case shows how this methodology can be used with an industrial robot. An implementation in industrial contexts should be adjusted accordingly to ISO safety standards as described in the paper. Originality/value – This paper presents a complete state-of-the-art of the problem and shows a real practical use case where the approach presented could be used to speed up the teaching process.

Low cost real-time tracking system prototype using GM862 cellular quad band module

2014 ◽  
Vol 12 (3) ◽  
pp. 389-407 ◽  
Author(s):  
Wael M. El-Medany ◽  
Alauddin Al-Omary ◽  
Riyadh Al-Hakim ◽  
Mustafa Nusaif
Keyword(s):  
Real Time ◽  
Design Methodology ◽  
Tracking System ◽  
Low Cost ◽  
Vehicle Tracking ◽  
Content Type ◽  
Current Location ◽  
Real Time Tracking ◽  
Band Module ◽  
System Prototype

Purpose – The purpose of this paper is to present a development to the hardware and software of a real-time tracking system that provides the position of the tracked vehicle accurately using fairly low-cost equipment and services. Vehicle tracking industries are expanding as businesses are interested to know their fleet vehicles positions minute by minute every day. Many systems were proposed recently that can provide such information. Design/methodology/approach – The system is implemented using GM862 cellular quad band module. A monitoring server and a graphical user interface on a Web site have also been implemented to view the current location of a vehicle on a specific map. Findings – The experiments were conducted and tested in different areas of the Kingdom Of Bahrain using Google maps, and results are discussed. Originality/value – The developed system has been compared to the available and imported tracking systems to some of the telematics companies in Bahrain, and the comparison has been discussed.

A robot assisted assembly system for small components in aircraft assembly

2014 ◽  
Vol 41 (5) ◽  
pp. 413-420 ◽  
Author(s):  
Zhangjun Jin ◽  
Cijun Yu ◽  
Jiangxiong Li ◽  
Yinglin Ke
Keyword(s):  
Industrial Robot ◽  
Tracking System ◽  
Feedback System ◽  
Assembly System ◽  
Robot System ◽  
Small Component ◽  
Content Type ◽  
Laser Tracking ◽  
Aircraft Assembly ◽  
Loop Feedback

Purpose – The purpose of this paper is to propose a robot-assisted assembly system (RAAS) for the installation of a variety of small components in the aircraft assembly system. The RAAS is designed to improve the assembly accuracy and increase the productive efficiency. Design/methodology/approach – The RAAS is a closed-loop feedback system, which is integrated with a laser tracking system and an industrial robot system. The laser tracking system is used to evaluate the deviations of the position and orientation of the small component and the industrial robot system is used to locate and re-align the small component according to the deviations. Findings – The RAAS has exhibited considerable accuracy improvement and acceptable assembly efficiency in aircraft assembly project. With the RAAS, the maximum position deviation of the component is reduced to 0.069 mm and the maximum orientation deviation is reduced to 0.013°. Social implications – The RAAS is applied successfully in one of the aircraft final assembly projects in southwest China. Originality/value – By integrating the laser tracking system, the RAAS is constructed as a closed-loop feedback system of both the position and orientation of the component. With the RAAS, the installation a variety of small components can be dealt with by a single industrial robot.

Lean machine manufacturing at Munjal Showa limited

2014 ◽  
Vol 63 (5) ◽  
pp. 644-664 ◽  
Author(s):  
Shivdasini Singh Amin ◽  
Rakesh Atre ◽  
Ankur Vardia ◽  
Boby Sebastian
Keyword(s):  
Cycle Time ◽  
Lean Manufacturing ◽  
Manufacturing Industry ◽  
Low Cost ◽  
Shop Floor ◽  
New Approach ◽  
Content Type ◽  
Indigenous Development ◽  
Depth Study ◽  
Increase Productivity

Purpose – The global manufacturing industry is becoming more competitive. Munjal Showa, a shock absorber manufacturer in India, is using indigenous development of lean machines by incorporating concepts of lean manufacturing and low-cost automation techniques to increase their competitiveness. This new approach has helped the company to reduce cost of manufacturing and to increase productivity by reducing cycle time and down time. The purpose of this paper is to offer an in depth study of how at Munjal Showa Ltd lean machines are being developed and manufactured. This paper explores how a cumbersome machine was transformed into a lean machine. Design/methodology/approach – This paper explores how a cumbersome machine was transformed into a lean machine. Findings – This new approach has helped the company to reduce cost of manufacturing and to increase productivity by reducing cycle time and down time. Research limitations/implications – The paper discusses the process of converting one cumbersome machine to a lean machine. Practical implications – Creativity before capital. In lean, team brainstorming of ideas and solutions is emphasized instead of spending large sums of money on capital expenditures Social implications – The cockpit model eases pressure of incumbents on the shop floor. Originality/value – The concepts espoused in the paper has increased productivity by 3.45 times and reduced costs.

Sign in / Sign up

Export Citation Format

Share Document