Neural Network Based Contact Force Control Algorithm for Walking Robots
Walking algorithms using push-off improve moving efficiency and disturbance rejection performance. However, the algorithm based on classical contact force control requires an exact model or a Force/Torque sensor. This paper proposes a novel contact force control algorithm based on neural networks. T...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/1/287 |
| _version_ | 1827698455926013952 |
|---|---|
| author | Byeongjin Kim Soohyun Kim |
| author_facet | Byeongjin Kim Soohyun Kim |
| author_sort | Byeongjin Kim |
| collection | DOAJ |
| description | Walking algorithms using push-off improve moving efficiency and disturbance rejection performance. However, the algorithm based on classical contact force control requires an exact model or a Force/Torque sensor. This paper proposes a novel contact force control algorithm based on neural networks. The proposed model is adapted to a linear quadratic regulator for position control and balance. The results demonstrate that this neural network-based model can accurately generate force and effectively reduce errors without requiring a sensor. The effectiveness of the algorithm is assessed with the realistic test model. Compared to the Jacobian-based calculation, our algorithm significantly improves the accuracy of the force control. One step simulation was used to analyze the robustness of the algorithm. In summary, this walking control algorithm generates a push-off force with precision and enables it to reject disturbance rapidly. |
| first_indexed | 2024-03-10T13:30:34Z |
| format | Article |
| id | doaj.art-fdfaf45b310448408ab44a4cabe000be |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T13:30:34Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-fdfaf45b310448408ab44a4cabe000be2023-11-21T08:06:31ZengMDPI AGSensors1424-82202021-01-0121128710.3390/s21010287Neural Network Based Contact Force Control Algorithm for Walking RobotsByeongjin Kim0Soohyun Kim1Department of Mechanical Engineering, KAIST, Daejeon 34141, KoreaDepartment of Mechanical Engineering, KAIST, Daejeon 34141, KoreaWalking algorithms using push-off improve moving efficiency and disturbance rejection performance. However, the algorithm based on classical contact force control requires an exact model or a Force/Torque sensor. This paper proposes a novel contact force control algorithm based on neural networks. The proposed model is adapted to a linear quadratic regulator for position control and balance. The results demonstrate that this neural network-based model can accurately generate force and effectively reduce errors without requiring a sensor. The effectiveness of the algorithm is assessed with the realistic test model. Compared to the Jacobian-based calculation, our algorithm significantly improves the accuracy of the force control. One step simulation was used to analyze the robustness of the algorithm. In summary, this walking control algorithm generates a push-off force with precision and enables it to reject disturbance rapidly.https://www.mdpi.com/1424-8220/21/1/287neural networkpush-offwalkingforce controlcontact forceground reaction force |
| spellingShingle | Byeongjin Kim Soohyun Kim Neural Network Based Contact Force Control Algorithm for Walking Robots Sensors neural network push-off walking force control contact force ground reaction force |
| title | Neural Network Based Contact Force Control Algorithm for Walking Robots |
| title_full | Neural Network Based Contact Force Control Algorithm for Walking Robots |
| title_fullStr | Neural Network Based Contact Force Control Algorithm for Walking Robots |
| title_full_unstemmed | Neural Network Based Contact Force Control Algorithm for Walking Robots |
| title_short | Neural Network Based Contact Force Control Algorithm for Walking Robots |
| title_sort | neural network based contact force control algorithm for walking robots |
| topic | neural network push-off walking force control contact force ground reaction force |
| url | https://www.mdpi.com/1424-8220/21/1/287 |
| work_keys_str_mv | AT byeongjinkim neuralnetworkbasedcontactforcecontrolalgorithmforwalkingrobots AT soohyunkim neuralnetworkbasedcontactforcecontrolalgorithmforwalkingrobots |