Tesi etd-07202020-150748 |
Link copiato negli appunti
Tipo di tesi
Tesi di laurea magistrale
Autore
MAUS, PHILIP RUDOLF
URN
etd-07202020-150748
Titolo
Study, Development and Experimentation of Machine Learning Techniques in Grasping Tasks using Tactile Force Sensors in 3-Finger-Gripper
Dipartimento
INGEGNERIA DELL'INFORMAZIONE
Corso di studi
BIONICS ENGINEERING
Relatori
relatore Prof. Cavallo, Filippo
supervisore Dott. Kim, Jaeseok
supervisore Dott. Kim, Jaeseok
Parole chiave
- Tactile Object Recognition
- Neural Network
- Machine Learning
- Tactile Sensing
- Tactile Object Classification
Data inizio appello
09/10/2020
Consultabilità
Non consultabile
Data di rilascio
09/10/2090
Riassunto
This work presents a neural network-based tactile object classification approach using a sensorized
robotic gripper. It explores the classification capabilities of a simple hardware setup by employing various neural network models, including combinative recurrent convolutional models, data set expansion, and feature space expansion via 3 force sensors on the gripper fingertips.
robotic gripper. It explores the classification capabilities of a simple hardware setup by employing various neural network models, including combinative recurrent convolutional models, data set expansion, and feature space expansion via 3 force sensors on the gripper fingertips.
File
| Nome file | Dimensione |
|---|---|
Tesi non consultabile. |
|