Abstract
This paper presents a novel yet simple friction identification method: Support Vector Machines (SVM) for robotic dynamics identification. Compared with previous friction identification method, it can overcome the curse dimensionality, local optimization, and overfit problems. The theoretical analysis and experimental results show that it can lead to high performance and accuracy in limited training data applications.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 4th Asia-Pacific Conference on Control and Measurement |
| Pages | 35-40 |
| Publication status | Published - 2000 |
| Event | Proceedings of the 4th Asia-Pacific Conference on Control and Measurement - Guilin, China Duration: 9 Jul 2000 → 12 Jul 2000 |
Conference
| Conference | Proceedings of the 4th Asia-Pacific Conference on Control and Measurement |
|---|---|
| Place | China |
| City | Guilin |
| Period | 9/07/00 → 12/07/00 |
Research Keywords
- Contact
- Dynamics Identification
- Friction
- Support Vector Machines