Dynamic-Vision-Based Force Measurements Using Convolutional Recurrent Neural Networks
| Autor: | Dongming Gan, Yahya Zweiri, Fariborz Baghaei Naeini, Dimitrios Makris |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Computer science
dynamic vision sensor even-based sensor 02 engineering and technology lcsh:Chemical technology 01 natural sciences Biochemistry Article Analytical Chemistry Contact force 0202 electrical engineering electronic engineering information engineering Computer vision lcsh:TP1-1185 mechanical Electrical and Electronic Engineering Instrumentation computer neuromorphic sensor Artificial neural network business.industry 020208 electrical & electronic engineering 010401 analytical chemistry GRASP Object (computer science) dynamic force estimation Atomic and Molecular Physics and Optics 0104 chemical sciences Variable (computer science) Recurrent neural network Neuromorphic engineering vision-based measurements Artificial intelligence business LSTM |
| Zdroj: | Sensors Volume 20 Issue 16 Sensors, Vol 20, Iss 4469, p 4469 (2020) Sensors (Basel, Switzerland) |
| ISSN: | 1424-8220 |
| DOI: | 10.3390/s20164469 |
| Popis: | In this paper, a novel dynamic Vision-Based Measurement method is proposed to measure contact force independent of the object sizes. A neuromorphic camera (Dynamic Vision Sensor) is utilizused to observe intensity changes within the silicone membrane where the object is in contact. Three deep Long Short-Term Memory neural networks combined with convolutional layers are developed and implemented to estimate the contact force from intensity changes over time. Thirty-five experiments are conducted using three objects with different sizes to validate the proposed approach. We demonstrate that the networks with memory gates are robust against variable contact sizes as the networks learn object sizes in the early stage of a grasp. Moreover, spatial and temporal features enable the sensor to estimate the contact force every 10 ms accurately. The results are promising with Mean Squared Error of less than 0.1 N for grasping and holding contact force using leave-one-out cross-validation method. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
| Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |