This work investigates an alternative approach to current control systems for the Automated Driving (AD) of shuttle vehicles on dedicated roads. The proposed solution decouples the problem into two levels: a Deep Deterministic Policy Gradient (DDPG) Reinforcement Learning (RL) agent and a dedicated vehicle logic generating Virtual Lane (VL) data to eliminate redundancy and allow for smooth lane changes on curved roads. The training uses an environment defined through a model-based simulation, exploiting MatLab and Simulink tools, and has been conducted following a Curriculum Learning strategy. The performance of the introduced approach have been evaluated by testing the agent capabilities and exploring its behavior in the presence of external disturbances in the controlled states.
Enhancing Reinforcement Learning for Automated Driving through Virtual Lane Logic / Fasiello, Alessandro; Cerrito, Francesco; Razza, Valentino; Canale, Massimo. - In: IFAC PAPERSONLINE. - ISSN 2405-8971. - ELETTRONICO. - 58, Issue 28:(2024), pp. 55-60. (Intervento presentato al convegno Modeling, Estimation and Control Conference MECC 2024 tenutosi a Chicago, IL (USA) nel Oct 27-30, 2024) [10.1016/j.ifacol.2024.12.010].
Enhancing Reinforcement Learning for Automated Driving through Virtual Lane Logic
Fasiello, Alessandro;Cerrito, Francesco;Razza, Valentino;Canale, Massimo
2024
Abstract
This work investigates an alternative approach to current control systems for the Automated Driving (AD) of shuttle vehicles on dedicated roads. The proposed solution decouples the problem into two levels: a Deep Deterministic Policy Gradient (DDPG) Reinforcement Learning (RL) agent and a dedicated vehicle logic generating Virtual Lane (VL) data to eliminate redundancy and allow for smooth lane changes on curved roads. The training uses an environment defined through a model-based simulation, exploiting MatLab and Simulink tools, and has been conducted following a Curriculum Learning strategy. The performance of the introduced approach have been evaluated by testing the agent capabilities and exploring its behavior in the presence of external disturbances in the controlled states.File | Dimensione | Formato | |
---|---|---|---|
1-s2.0-S2405896324023437-main.pdf
accesso aperto
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Creative commons
Dimensione
944.69 kB
Formato
Adobe PDF
|
944.69 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2992631