ETD system

Electronic theses and dissertations repository

 

Tesi etd-03302017-141706


Thesis type
Tesi di laurea magistrale
Author
RESASCO, DANIELA
URN
etd-03302017-141706
Title
Machine Learning for grasp synthesis
Struttura
INGEGNERIA DELL'INFORMAZIONE
Corso di studi
INGEGNERIA ROBOTICA E DELL'AUTOMAZIONE
Supervisors
relatore Prof. Bicchi, Antonio
Parole chiave
  • soft robotics
  • robotics
  • planning
  • object decomposition
  • machine learning
  • grasping
Data inizio appello
04/05/2017;
Consultabilità
Parziale
Data di rilascio
04/05/2087
Riassunto analitico
The goal of this thesis is have a robot that learn how to grasp an unknown object with an underactuated end-effector. We chose to implement regression via deep convolutional neural network in a supervised learning scenario. We present a 3D and 2D deep convolutional neural network with as input, respectively a voxel and images takes from vary point of view of the object.

We create a database that match the image with one feasible pose. The pose is make using Minimum Volume Bounding Box, minimizing the volume of the boxes which fit partial point clouds. In these way we can focus on outermost boxes and we can choose a desired pose that grasping the object in a successful manner.

The simulation is made using Klamp't simulator, and the neural network is implement using Theano library.

We compare the results of our neural network trying different loss function and two structure of network: one with regularization and the other without it.
Note
La tesi in oggetto non è stata inserita correttamente nel data base dall’autore. L’autore stesso ed i relatori sono stati avvertiti di tale omissione.
File