| DOI | Resolve DOI: https://doi.org/10.1007/s10846-023-01867-6 |
|---|
| Author | Search for: Maghami, Ali1ORCID identifier: https://orcid.org/0000-0003-0807-0495; Search for: Imbert, Alaïs1; Search for: Côté, Gabriel1; Search for: Monsarrat, Bruno1; Search for: Birglen, Lionel; Search for: Khoshdarregi, MattORCID identifier: https://orcid.org/0000-0003-2987-3000 |
|---|
| Affiliation | - National Research Council of Canada. Aerospace
|
|---|
| Funder | Search for: Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Search for: National Research Council of Canada; Search for: Mitacs |
|---|
| Format | Text, Article |
|---|
| Subject | robot calibration; multi-robot cooperative system; artifcial neural networks; deep learning |
|---|
| Abstract | Robot calibration is crucial in multi-robot cooperative systems where the inaccuracy of robots can add up and cause large errors in the fnal trajectory of handled parts or process tools. In this work, a two-step calibration approach is proposed based on artifcial neural networks (ANNs) and defnition of compensated pose for a master–slave cooperative robot system. Measuring the pose of master and slave robots at diferent locations in their shared workspace is required to create pairs of joint angles and output pose errors as training data. The generated data is used to train two ANN models for compensating the master–slave relative error and the master robot errors. The master–slave relative error is corrected by introducing a compensated pose for the slave robot with respect to the master robot. A neural network is then trained to predict the error parameters of the compensated pose for the joint angles of both robots as the input. The master robot is then corrected individually using another ANN model to address the absolute accuracy of the cooperative system. Measurements and simulations have been performed on a dual-robot cooperative system before and after geometric calibration. The process of cross validation is carried out to fnd the best network architecture for the optimal performance in correcting the robots’ errors. It has been shown that even after pre-existing model-based calibration of each robot, both the absolute accuracy of the master robot and the relative tracking accuracy can be further improved by the proposed implementation of ANN calibration. |
|---|
| Publication date | 2023-04-18 |
|---|
| Publisher | Springer |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | fbb2c793-5c71-4169-8811-652652aaea67 |
|---|
| Record created | 2023-09-05 |
|---|
| Record modified | 2023-09-05 |
|---|
