Abstract
The motion of the robot to realize assembly work includes the part where the reuse of the motion adjusted for the real objects is effective and the part where automatic generation in the simulator is suitable. In order to smoothly teach such assembly work, teaching software that enables to combine previously used motions and perform overall adjustment of the workflow and integrated environment representation in the simulator is expected. Some teaching tools focus on the function of making robot motion in detail, and it assumes that the adjustment of the whole workflow including system layout using the real work environment. For this reason, the environmental expression is not sufficient for the above purpose. Although offline teaching tools and motion planning tools are rich in the representation of the environment, there are not many studies on a systematic reuse mechanism of motions adjusted in a real environment, including environment representations. In this paper, we present software design to solve this problem and the implementation of it as a plugin for Choreonoid. By an experiment, we confirmed that we can describe a comparatively complicated assembly work with the proposed software.
Highlights
How to build flexible robot systems that are easy to cope with changes in product design and production volume is an important issue in robot system integration
This paper presented the design of new teaching software based on the reuse of previous teaching data
A combination of parameters adjustable by users, motion pattern, 3D models as an environment expression and meta-data used for search keys and content understanding by users is the unit of data reuse
Summary
How to build flexible robot systems that are easy to cope with changes in product design and production volume is an important issue in robot system integration. There are two approaches for such flexible robot systems. 1. Reduction of manual work by raising an intelligence level of robots. 2. Improvement of engineering work related to robot introduction including teaching. The first approach aims to make computers recognize objects and environment, and generate motions of the robots that enables intended tasks [1, 2]. This results in the reduction of information given by humans explicitly when each system is built.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
