polito.it
Politecnico di Torino (logo)

Development and implementation of an obstacle avoidance algorithm for an Unmanned Aerial Vehicle

Davide Graziato

Development and implementation of an obstacle avoidance algorithm for an Unmanned Aerial Vehicle.

Rel. Alessandro Rizzo, Marina Indri, Stefano Primatesta. Politecnico di Torino, Corso di laurea magistrale in Mechatronic Engineering (Ingegneria Meccatronica), 2021

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

Download (16MB) | Preview
Abstract:

The forthcoming of the fourth industrial revolution drives the implementation of autonomous systems and high collaborative robots inside the industrial environments. Flexibility and Adaptivity represent the keys to satisfy the increase of an always faster and low-cost market demands. The FIXIT project main objective is to provide an interactive support for the human operator in the industrial or logistic environment fitting the requirements of the industry 4.0. The scope of the thesis is to develop and implement a collision avoidance system for an Unmanned Aerial Vehicle (UAV) used for maintenance purposes implemented on the FIXIT. The platform of the UAV is composed by a flight controller, the Pixhawk 2.4.8, an onboard computer, the Jetson nano and the Intel realsense D435i depth camera. The designed algorithm uses a path planner based on the implementation of an Informed-RRT* (Informed-Rapid-Exploring-Tree "Star") to produce obstacles-free paths and avoid collision in both known static and unknown dynamics environments. The point clouds generated by the depth-camera are used to extract information from the surroundings of the drone and, then, efficiently define a 3D occupancy map used by the algorithm. In order to validate the obtained results simulation in virtual generated environment using Gazebo and real-life tests are performed. Both the simulation and experimental results convincingly demonstrate how the implementation of this strategy allows the UAV to generate a safe path, prevent collisions and reach the desired target position.

Relatori: Alessandro Rizzo, Marina Indri, Stefano Primatesta
Anno accademico: 2021/22
Tipo di pubblicazione: Elettronica
Numero di pagine: 95
Soggetti:
Corso di laurea: Corso di laurea magistrale in Mechatronic Engineering (Ingegneria Meccatronica)
Classe di laurea: Nuovo ordinamento > Laurea magistrale > LM-25 - INGEGNERIA DELL'AUTOMAZIONE
Aziende collaboratrici: Competence Industry Manufacturing 4.0
URI: http://webthesis.biblio.polito.it/id/eprint/21192
Modifica (riservato agli operatori) Modifica (riservato agli operatori)