Tesi - Addestramento tramite tecniche di Reinforcement Learning di entità virtuali generate al computer all'interno di un simulatore di volo

Questa posizione è in Leonardo Riassunto dell'opportunità da parte della Joinrs AI: Leonardo cerca un Junior per un tirocinio con tesi finale in ingegneria informatica o informatica, focalizzato su Intelligenza Artificiale e Reinforcement Learning applicati al controllo di volo. Il candidato sarà coinvolto nello sviluppo di un agente intelligente per la gestione dinamica di un aeromobile sintetico, con tutor esperti a supporto. L’esperienza si svolge presso la sede di Torino con rimborso spese previsto. Il processo di selezione sarà interamente gestito da Leonardo. -
- #

Job Description
Leonardo is an international industrial group, one of the main global realities in Aerospace, Defense and Security that creates multi-domain technological capabilities in Helicopters, Aircraft, Aerostructures, Electronics, Cyber Security and Space. With over 60,000 employees worldwide, the company has a solid industrial presence in Italy, the United Kingdom, Poland, the United States, and operates in 150 countries also through controlled companies, joint ventures and shareholdings. A protagonist of the main strategic programs at a global level, it is a technological and industrial partner of Governments, Defense Administrations, Institutions and companies. In 2024, Leonardo recorded consolidated revenues of € 17.8 billion, new orders for € 20.9 billion, and invested € 2.5 billion in R&D activities. Innovation, continuous research, digital industry and sustainability are the pillars of its business worldwide. Expert tutors in their sector will follow you, allowing you to deepen the theoretical part and develop your thesis, preparing you best for future professional challenges. The topics proposed for the theses to be carried out in Leonardo embrace a vast spectrum of technological, research and innovation areas: from Artificial Intelligence to High-Performance Computing, from Cyber Security to Materials Engineering, passing through the aerospace sectors. You will be able to explore the most avant-garde areas of your field of study, with creativity and a spirit of innovation. To support you during this experience, which will last a maximum of six months, an expense reimbursement is also provided. We are looking for n. 1 young student to be included in an internship with the aim of developing their degree thesis on the topic concerning "Training through Reinforcement Learning techniques of virtual entities generated by computer within a flight simulator" at the Turin site. The purpose of this thesis is the study, complemented by the development, of a flight control software for a synthetic aircraft based on an artificial intelligence model trained with Reinforcement Learning techniques. Flight control is usually dominated by PID (Proportional-Integral-Derivative) logics, although effective, these systems have limitations that Reinforcement Learning (RL) aims to overcome. An RL model has the ability to learn directly from interaction with the environment and to build an implicit representation of these dynamics, managing to capture complex behaviors. Unlike the fixed parameters of a PID, an RL agent can learn a control policy capable of managing a greater variety of operating conditions. Thanks to training in simulated environments that include variable scenarios, the agent can develop more robust control techniques, improving the stability and performance of the system. While a PID focuses on reducing an error (e.g. maintaining altitude), RL can be trained to maximize a complex reward function that integrates different performance criteria within the same learning process. In this way, the agent can be trained to find the best control policies that simultaneously balance different operational factors, such as precision in following a desired trajectory, fuel saving and structural integrity. The main objective of this thesis is the design and implementation of an intelligent agent capable of managing the dynamic control of a synthetic aircraft. The work will be articulated in the following phases:
- Analysis of commercial products and integration: Study of flight simulators available on the market (e.g. X-Plane 12 or DCS World) as physics engines. The AI agent will interact with the simulator via dedicated APIs or plugins, receiving as input the state of the aircraft (attitude, speed, position) and providing as output the commands on the control surfaces;
- Definition of the Learning Model: Design of the “reward function” to train the agent to perform specific maneuvers (e.g.: maintaining level flight, intercepting waypoints or evasive maneuvers) by maximizing the parameters chosen at the project;
- Validation in a Synthetic Environment: The trained model will be integrated into a complex scenario, typical of military training standards, to evaluate the AI's ability to react to dynamic variables and environmental unforeseen events. Educational qualification: Master's Degree in Computer Engineering or Computer Scie