Abstract

The main aim of this article is to provide an example of reproducible research in robotics. Despite the fact that a large number of researchers agree on the need of reproducibility in robotics and artificial intelligence, the practice of reproducible research is still in an embryonic phase. As a matter of fact, IEEE Robotics and Automation Magazine is, at the date of this article submission, the only top-tier robotics publication accepting "reproducible" articles. To this end, we have chosen a very common and traditional problem and approached it with a "first principles" attitude.

Highlights

  • Many different methods have been proposed in the literature for the control of robotic arms

  • We propose a platform for reproducible research on robotic arm control

  • Work We developed a platform for reproducible research and objective comparisons of different methods for a cheap, low-accuracy, lightweight robotic arm

Read more

Summary

By Fabio Bonsignorio and Enrica Zereik

The main aim of this article is to provide an example of reproducible research in robotics. To validate our reproducible research platform and provide a template methodology for its usage, we have thoroughly compared, in a reproducible way, the performance of simple belief space planning (BSP) and proportional-integral-derivative (PID) controls when applied to a lightweight, low-accuracy, and compliant open source robot arm (i.e., H2Arm). Research Reproducibility Our main goal is to provide a complete software and hardware platform that allows for the statistical replication of our results and experimentation on other, more or less sophisticated control strategies and algorithms We believe this is much needed because real-world comparison of control methods for robot arms is seldom seen in the literature [1], [2]. The system, consisting of an arm and a basic in-hand video camera, was required to Vision Algorithm (C++)

Images From Camera
Test Campaign Category
Other details of
Total Exp
Findings
Conclusions and Future Work

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 call

Disclaimer: 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.