Time Efficiency Improvement in Quadruped Walking with Supervised Training Joint Model
To generate stable walking of a quadruped, the complexity of the configuration of the robot involves a significant amount of optimization that decreases to its time efficiency. To address this issue, a machine learning method was used to build a simplified control policy using joint models for the s...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/4/2658 |
| _version_ | 1797622509117374464 |
|---|---|
| author | Chin Ean Yeoh Min Sung Ahn Soomin Choi Hak Yi |
| author_facet | Chin Ean Yeoh Min Sung Ahn Soomin Choi Hak Yi |
| author_sort | Chin Ean Yeoh |
| collection | DOAJ |
| description | To generate stable walking of a quadruped, the complexity of the configuration of the robot involves a significant amount of optimization that decreases to its time efficiency. To address this issue, a machine learning method was used to build a simplified control policy using joint models for the supervised training of quadruped robots. This study considered 12 joints for a four-legged robot, and each joint value was determined based on the conventional method of walking simulation and prepossessed, equaling 2508 sets of data. For data training, the multilayer perceptron model was used, and the optimized number of epochs used to train the model was 5000. The trained models were implemented in robot walking simulations, and they improved performance with an average distance error of 0.0719 m and a computational time as low as 91.98 s. |
| first_indexed | 2024-03-11T09:11:16Z |
| format | Article |
| id | doaj.art-af2d39e00e0242e5857381b6e464fea3 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T09:11:16Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-af2d39e00e0242e5857381b6e464fea32023-11-16T18:58:57ZengMDPI AGApplied Sciences2076-34172023-02-01134265810.3390/app13042658Time Efficiency Improvement in Quadruped Walking with Supervised Training Joint ModelChin Ean Yeoh0Min Sung Ahn1Soomin Choi2Hak Yi3Department of Mechanical Engineering, Graduate School, Kyungpook National University, Daegu 41566, Republic of KoreaDepartment of Mechanical and Aerospace Engineering, University of California, 420 Westwood Plaza, Rm 32-117E, Los Angeles, CA 90095, USADepartment of Mechanical Engineering, Graduate School, Kyungpook National University, Daegu 41566, Republic of KoreaDepartment of Mechanical Engineering, Graduate School, Kyungpook National University, Daegu 41566, Republic of KoreaTo generate stable walking of a quadruped, the complexity of the configuration of the robot involves a significant amount of optimization that decreases to its time efficiency. To address this issue, a machine learning method was used to build a simplified control policy using joint models for the supervised training of quadruped robots. This study considered 12 joints for a four-legged robot, and each joint value was determined based on the conventional method of walking simulation and prepossessed, equaling 2508 sets of data. For data training, the multilayer perceptron model was used, and the optimized number of epochs used to train the model was 5000. The trained models were implemented in robot walking simulations, and they improved performance with an average distance error of 0.0719 m and a computational time as low as 91.98 s.https://www.mdpi.com/2076-3417/13/4/2658supervised learningquadruped robotwalking locomotionmultilayer perceptron |
| spellingShingle | Chin Ean Yeoh Min Sung Ahn Soomin Choi Hak Yi Time Efficiency Improvement in Quadruped Walking with Supervised Training Joint Model Applied Sciences supervised learning quadruped robot walking locomotion multilayer perceptron |
| title | Time Efficiency Improvement in Quadruped Walking with Supervised Training Joint Model |
| title_full | Time Efficiency Improvement in Quadruped Walking with Supervised Training Joint Model |
| title_fullStr | Time Efficiency Improvement in Quadruped Walking with Supervised Training Joint Model |
| title_full_unstemmed | Time Efficiency Improvement in Quadruped Walking with Supervised Training Joint Model |
| title_short | Time Efficiency Improvement in Quadruped Walking with Supervised Training Joint Model |
| title_sort | time efficiency improvement in quadruped walking with supervised training joint model |
| topic | supervised learning quadruped robot walking locomotion multilayer perceptron |
| url | https://www.mdpi.com/2076-3417/13/4/2658 |
| work_keys_str_mv | AT chineanyeoh timeefficiencyimprovementinquadrupedwalkingwithsupervisedtrainingjointmodel AT minsungahn timeefficiencyimprovementinquadrupedwalkingwithsupervisedtrainingjointmodel AT soominchoi timeefficiencyimprovementinquadrupedwalkingwithsupervisedtrainingjointmodel AT hakyi timeefficiencyimprovementinquadrupedwalkingwithsupervisedtrainingjointmodel |