polito.it
Politecnico di Torino (logo)

Tele-operated car control using Brain Computer Interface

Filippo Cupolo, Gianluca D'Alleo

Tele-operated car control using Brain Computer Interface.

Rel. Massimo Violante. Politecnico di Torino, Corso di laurea magistrale in Ingegneria Informatica (Computer Engineering), 2020

[img]
Preview
PDF (Tesi_di_laurea) - Tesi
Licenza: Creative Commons Attribution Non-commercial No Derivatives.

Download (11MB) | Preview
Abstract:

In this paper, it is presented an approach to control a car remotely with a Brain Computer Interface (BCI). To achieve this goal it is used a commercial BCI that needed to be connected to a teleoperated car. The accelerator/brake pedals and the steering wheel of the teleoperated car can be remotely controlled through a UDP/IP connection. The BCI is composed by an Emotiv EPOC+ EEG headset that is able to read the brainwaves of the user and train a statistical classifier to classify mental states. Then, these mental states or facial expressions can be translated into commands for the car. Brain-computer interfaces represent a range of acknowledged technologies that translate brain activity into computer commands. The brain is the main processor in giving orders to the human body to perform physical activities. With technological advances, today’s brain signals can be used as commands to control electronic devices. For example, disabled people can use their brain signals to give commands to move a wheelchair or operate a mobile device or even to drive a car. This research aims to develop and evaluate a BCI control application for certain assistive technologies that can be used for remote telepresence or remote driving. It has been implement a scenario to test the usability of the BCI for controlling a tele-operated car. In the scenario the car is completely brain controlled, using different brain patterns for steering and throttle/brake. Main Phases: • Create a dataset of facial expressions/mental commands and train the Brain-Computer Interface in order to get clearer and more significant information. • Use of Cortex API to communicate with the Emotiv SW and get information about facial expressions/mental commands. • Creation of a simulation scenario using ROS and some tools as Autoware or CarDemo. • Translate the mental commands into significant directives to create the possibility to send/receive. • UDP packages for remote driving. • Develop a SW application (C++, Qt framework) that receivs data from the Emotiv SW, convert these data into commands for the teleoperated car and send the commands.

Relatori: Massimo Violante
Anno accademico: 2019/20
Tipo di pubblicazione: Elettronica
Numero di pagine: 107
Soggetti:
Corso di laurea: Corso di laurea magistrale in Ingegneria Informatica (Computer Engineering)
Classe di laurea: Nuovo ordinamento > Laurea magistrale > LM-32 - INGEGNERIA INFORMATICA
Aziende collaboratrici: NON SPECIFICATO
URI: http://webthesis.biblio.polito.it/id/eprint/14528
Modifica (riservato agli operatori) Modifica (riservato agli operatori)