Show simple item record

dc.contributorBarrado Muxí, Cristina
dc.contributor.authorMuñoz Ferran, Guillem
dc.date.accessioned2018-09-27T12:49:15Z
dc.date.available2018-09-27T12:49:15Z
dc.date.issued2018-09-07
dc.identifier.urihttp://hdl.handle.net/2117/121577
dc.descriptionPremi HEMAV 2018 al millor TFG
dc.description.abstractRecent improvements in computation and algorithmic research, together with the rising era of Big Data, have allowed Artificial Intelligence increase its popularity within masses. The recent publication of the Deep Q-Network (DQN) algorithm, which combines Q-learning with deep neural networks, has been demonstrated as being able to learn how to solve complex task, such as playing Atari games, in an unknown environment solely by gathering experience. These conditions open the door for many other applications, such as autonomous vehicles, doctors or production chains. Moreover, the preceding work of this project was focused on building a baseline architecture for enabling Unmanned Aerial Vehicles (UAVs) learn how to behave autonomously. In this project we provide different architectures for scaling this solution. To evaluate the convergence of the algorithm, we create challenging tasks concerning obstacle avoidance and goal position reaching inside a realistic simulated environment. The provided solution allows UAVs to autonomously move in three dimensions as well as controlling and modifying their velocities. Modifications in the architecture provide different approaches for learning, which are evaluated together with its training efficiency metrics and testing results. The development has been focused on integrating Deep Learning and Reinforcement Learning tools such as Keras and OpenAI Gym in order to build a modular and accessible framework capable of training and testing DRL models for autonomous UAVs within simulated environments. Results of the carried experiments show multiple enhancements compared to previous research and work, along with providing useful insights for potentially identified improvements. In this project, we have been able to successfully beat the existent baseline Double Deep Q-Learning architecture for autonomous UAVs, obtaining a 49% more of average reward and no collisions, on a non-trivial task within a realistic simulated environment.
dc.language.isoeng
dc.publisherUniversitat Politècnica de Catalunya
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/3.0/es/
dc.subjectÀrees temàtiques de la UPC::Enginyeria de la telecomunicació
dc.subject.lcshData mining
dc.subject.lcshInformation technology
dc.subject.otherArtificial Intelligence
dc.subject.otherUAVs
dc.subject.otherDeep Learning
dc.subject.otherReinforcement Learning
dc.subject.otherMachine Learning
dc.subject.otherAutonomous vehicles
dc.subject.otherNeural Networks
dc.subject.otherDeep Reinforcement Learning
dc.subject.otherAlgorithms
dc.titleA new deep reinforcement learning architecture for autonomous UAVs
dc.typeBachelor thesis
dc.subject.lemacMineria de dades
dc.subject.lemacTecnologia de la informació
dc.description.awardwinningAward-winning
dc.rights.accessOpen Access
dc.date.updated2018-09-11T04:29:03Z
dc.audience.educationlevelEstudis de primer/segon cicle
dc.audience.mediatorEscola d'Enginyeria de Telecomunicació i Aeroespacial de Castelldefels
dc.audience.degreeGRAU EN ENGINYERIA TELEMÀTICA (Pla 2009)


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record