The use of infrastructure-to-vehicle communication technologies can enable improved energy efficient autonomous driving. Traditional ecological velocity planning methods have high computational burden, particularly when plug-in hybrid electric vehicles are considered. Consequently, in order to retrieve an optimal velocity profile in real time, it is necessary to rely on significant approximations.In this paper, the aforementioned issue is addressed by exploiting deep reinforcement learning in order to learn an eco-driving velocity planner for a plug-in hybrid electric vehicle within a model-free approach. Moreover, we incorporate a state-of-the-art safety controller based on model predictive control to guarantee traffic light compliance. Statistical analysis of the simulation results demonstrate that the RL controller outperforms two benchmark controllers, and it generalizes well across a variety of intersection configurations.

Pozzi, A., Bae, S., Choi, Y., Borrelli, F., Raimondo, D. M., Moura, S., Ecological Velocity Planning through Signalized Intersections: A Deep Reinforcement Learning Approach, Contributed paper, in Proceedings of the IEEE Conference on Decision and Control, (Korea, 14-18 December 2020), Institute of Electrical and Electronics Engineers Inc., 345 E 47TH ST, NEW YORK, NY 10017 USA Jeju Island 2020:<<PROCEEDINGS OF THE IEEE CONFERENCE ON DECISION & CONTROL>>,2020- 245-252. 10.1109/CDC42340.2020.9304005 [http://hdl.handle.net/10807/193660]

Ecological Velocity Planning through Signalized Intersections: A Deep Reinforcement Learning Approach

Pozzi, Andrea
Primo
;
2020

Abstract

The use of infrastructure-to-vehicle communication technologies can enable improved energy efficient autonomous driving. Traditional ecological velocity planning methods have high computational burden, particularly when plug-in hybrid electric vehicles are considered. Consequently, in order to retrieve an optimal velocity profile in real time, it is necessary to rely on significant approximations.In this paper, the aforementioned issue is addressed by exploiting deep reinforcement learning in order to learn an eco-driving velocity planner for a plug-in hybrid electric vehicle within a model-free approach. Moreover, we incorporate a state-of-the-art safety controller based on model predictive control to guarantee traffic light compliance. Statistical analysis of the simulation results demonstrate that the RL controller outperforms two benchmark controllers, and it generalizes well across a variety of intersection configurations.
2020
Inglese
Proceedings of the IEEE Conference on Decision and Control
59th IEEE Conference on Decision and Control, CDC 2020
Korea
Contributed paper
14-dic-2020
18-dic-2020
978-1-7281-7447-1
Institute of Electrical and Electronics Engineers Inc.
Pozzi, A., Bae, S., Choi, Y., Borrelli, F., Raimondo, D. M., Moura, S., Ecological Velocity Planning through Signalized Intersections: A Deep Reinforcement Learning Approach, Contributed paper, in Proceedings of the IEEE Conference on Decision and Control, (Korea, 14-18 December 2020), Institute of Electrical and Electronics Engineers Inc., 345 E 47TH ST, NEW YORK, NY 10017 USA Jeju Island 2020:<<PROCEEDINGS OF THE IEEE CONFERENCE ON DECISION & CONTROL>>,2020- 245-252. 10.1109/CDC42340.2020.9304005 [http://hdl.handle.net/10807/193660]
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10807/193660
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 20
  • ???jsp.display-item.citation.isi??? 15
social impact