Control Through Contact using Mixture of Deep Neural-Net Experts

Home Page
About
Submit A Journal
Submit A Conference
Submit Paper/Book
- Submit a Preprint
- Submit a Book
Contact

Balkan Journal of Electrical and Computer Engineering
Cilt: 13 Sayı: 2
Control Through Contact using Mixture of Deep Neural-Net Experts

Control Through Contact using Mixture of Deep Neural-Net Experts

Pages : 164-173

View : 41 | Download : 67

Publication Date : 2025-06-30

Article Type : Research Paper

Abstract :We provide a data-driven control design framework for hybrid systems, with a special emphasis on contact-rich robotic systems. These systems exhibit continuous state flows and discrete state transitions, which are governed by distinct equations of motion. Hence, it may be impossible to design a single policy that can control the system in all modes. Typically, hybrid systems are controlled by multi-modal policies, each manually triggered based on observed states. However, as the number of potential contacts increase, the number of policies can grow exponentially and the control-switching scheme becomes too complicated to parameterize. To address this issue, we design contact-aware data-driven controllers given by deepnet mixture of experts (MoE). This architecture automatically learns switching-control scheme that can achieve the desired overall performance of the system, and a gating network, which determines the region of validity of each expert, based on the observed states.
Keywords : robotics, nonlinear control, machine learning

ORIGINAL ARTICLE URL

* There may have been changes in the journal, article,conference, book, preprint etc. informations. Therefore, it would be appropriate to follow the information on the official page of the source. The information here is shared for informational purposes. IAD is not responsible for incorrect or missing information.