Teachless teach-repeat: Toward vision-based programming of industrial robots

Perrollaz, Mathias; Khorbotly, Sami; Cool, Amber; Yoder, John-David; Baumgartner, Eric T.

doi:10.1109/icra.2012.6224639

Cited by 10 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results show good performance. Ideally, the system should be equipped with a smart controlling system such as without programming language for users (Perrollaz et al, 2012); (Yoshitake et al, 2013), but for complex applications this goal seems far away and approaches like Piaget provide a pragmatic solution today.…”

Section: Discussionmentioning

confidence: 99%

Piaget for the Smart Control of Complex Robotized Applications in Industry

Omori

Dessimoz²,

Tomori

et al. 2013

Proceedings of the 10th International Conference on Informatics in Control, Automation and Robotics

View full text Add to dashboard Cite

The control of smart robots, and now similarly smart applications in Factory Automation require programming and control capabilities at the integral level of many heterogeneous resources. Significant proposals exist for this purpose, such as ROS, yet we had to develop an original solution, "Piaget". Piaget can be deployed at a very low level, with very fast capabilities (e.g. 100 nanosecond long time slots in average), but more and more is concentrated on higher hierarchical levels, where it brings the capability to flexibly coordinate multiple, largely smart and otherwise autonomous subsystems. This perfectly reflects fundamental constraints in closed-loop control, which occurs in numerous instances for a smart system. Piaget is especially useful in three important phases of projects: development, programming, and real-time operation. An industrial case is studied, involving multiple, otherwise independent, commercially available subsystems, such as industrial robot arm, PLC, IP camera or joint controller. As always, a special endeffector, here multi-tool, had to be designed for the application. Highlight is given of selected software items, relating to the overall application, to the robot arm, or to the vision part. Experiments are reported, addressing three of the most significant process components. Outcomes are successful.

show abstract

Section: Discussionmentioning

confidence: 99%

Piaget for the Smart Control of Complex Robotized Applications in Industry

Omori

Dessimoz²,

Tomori

et al. 2013

Proceedings of the 10th International Conference on Informatics in Control, Automation and Robotics

View full text Add to dashboard Cite

show abstract

“…In response to a request from a local manufacturer, several of the authors were involved in a project to use computer vision to automate the teaching of a robot task for parts with small lot sizes. The details of that task are found in [12]. While the corporation was pleased with the results of the project, the accuracy obtained was not sufficient for all of their parts.…”

Section: Technical Approachmentioning

confidence: 99%

“…A directly-connected serial connection is used to transfer commands and coordinates to the ABB. More details about the system, and the implementation of a precise manipulation task, can be found in [12].…”

mentioning

confidence: 99%

Experiments Comparing Precision of Stereo-Vision Approaches for Control of an Industrial Manipulator

Yoder

West

Baumgartner

et al. 2013

Experimental Robotics

Self Cite

View full text Add to dashboard Cite

Despite years of research in the area of robotics, the vast majority of industrial robots are still used in "teach-repeat" mode. This requires that the workpiece be in exactly the same position and orientation every time. In many high-volume robotics applications, this is not a problem, since the parts are likely to be fixtured anyway. However, in small to medium lot applications, this can be a significant limitation. The motivation for this project was a corporation who wanted to explore the use of visual control of a manipulator to allow for automated teaching of robot tasks for parts that are run in small lot sizes.

show abstract

“…Choi and Lee (2003) proposed a method which evaluates the performance of a robot manipulator motion based on force/moment direction sensor. Perrollaz et al (2012) utilized a vision-based programming system for industrial robots, which depend on auto-calibration of the system. Skoglund et al (2006) use a range sensor to instruct the robot to follow the trajectory demonstrated by the operator.…”

Section: Introductionmentioning

confidence: 99%

Pick-place of dynamic objects by robot manipulator based on deep learning and easy user interface teaching systems

Hossain

Capi

Jindai

et al. 2017

View full text Add to dashboard Cite

Purpose Development of autonomous robot manipulator for human-robot assembly tasks is a key component to reach high effectiveness. In such tasks, the robot real-time object recognition is crucial. In addition, the need for simple and safe teaching techniques need to be considered, because: small size robot manipulators’ presence in everyday life environments is increasing requiring non-expert operators to teach the robot; and in small size applications, the operator has to teach several different motions in a short time. Design/methodology/approach For object recognition, the authors propose a deep belief neural network (DBNN)-based approach. The captured camera image is used as the input of the DBNN. The DBNN extracts the object features in the intermediate layers. In addition, the authors developed three teaching systems which utilize iPhone; haptic; and Kinect devices. Findings The object recognition by DBNN is robust for real-time applications. The robot picks up the object required by the user and places it in the target location. Three developed teaching systems are easy to use by non-experienced subjects, and they show different performance in terms of time to complete the task and accuracy. Practical implications The proposed method can ease the use of robot manipulators helping non-experienced users completing different assembly tasks. Originality/value This work applies DBNN for object recognition and three intuitive systems for teaching robot manipulators.

show abstract

Teachless teach-repeat: Toward vision-based programming of industrial robots

Cited by 10 publications

References 15 publications

Piaget for the Smart Control of Complex Robotized Applications in Industry

Piaget for the Smart Control of Complex Robotized Applications in Industry

Experiments Comparing Precision of Stereo-Vision Approaches for Control of an Industrial Manipulator

Pick-place of dynamic objects by robot manipulator based on deep learning and easy user interface teaching systems

Contact Info

Product

Resources

About