polito.it
Politecnico di Torino (logo)

A deep reinforcement learning approach to cooperative cruise control for connected cars

Keyu Wang

A deep reinforcement learning approach to cooperative cruise control for connected cars.

Rel. Carla Fabiana Chiasserini, Nicola Amati. Politecnico di Torino, Corso di laurea magistrale in Ict For Smart Societies (Ict Per La Società Del Futuro), 2022

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

Download (13MB) | Preview
[img] Archive (ZIP) (Documenti_allegati) - Other
Licenza: Creative Commons Attribution Non-commercial No Derivatives.

Download (49MB)
Abstract:

In this thesis, we use a deep reinforcement learning algorithm called Deep Deterministic Policy Gradient (DDPG) to achieve vehicle longitudinal control in the CoMoVe framework. And we properly design the reward function, considering some key performance indicators like safety, comfort and stability to guide the model's learning direction. In the meanwhile, we apply multiple methods to reduce overfitting: fine-tuning hyperparameters, diversifying training scenarios and regularization, which improve the performance and robustness of DDPG. In addition, we also test its improved version called Twin Delayed DDPG (TD3) algorithm for comparison as well as providing reference for future research.

Relators: Carla Fabiana Chiasserini, Nicola Amati
Academic year: 2021/22
Publication type: Electronic
Number of Pages: 72
Subjects:
Corso di laurea: Corso di laurea magistrale in Ict For Smart Societies (Ict Per La Società Del Futuro)
Classe di laurea: New organization > Master science > LM-27 - TELECOMMUNICATIONS ENGINEERING
Aziende collaboratrici: UNSPECIFIED
URI: http://webthesis.biblio.polito.it/id/eprint/22672
Modify record (reserved for operators) Modify record (reserved for operators)