TY - JOUR
T1 - VISION-AIDED DEEP REINFORCEMENT LEARNING FOR ENERGY MANAGEMENT OF HYBRID ELECTRIC VEHICLES
AU - Wang, Yong
AU - Wu, Yuankai
AU - Peng, Jiankun
AU - Tan, Huachun
AU - Zeng, Dechong
AU - He, Hongwen
N1 - Publisher Copyright:
© 2019 ICAE.
PY - 2019
Y1 - 2019
N2 - This paper introduces an energy management strategy that combines visual perception and deep reinforcement learning (DRL) algorithms to minimize fuel consumption. The proposed method is capable of autonomously learning the optimal control policy without any prediction efforts. We used a monocular camera in the windshield of a car to catch visual information as inputs. Next, we used state-of-the-art convolutional neural networks based object detection methods to detect and classify traffic light. The traffic light information is used as a state input for a model-free deep reinforcement learning based energy management system with continuous control action. Hence, the traffic light information is incorporated into the energy management system. The experimental results indicate that the fuel economy of the proposed vision-aided strategy achieves 94.5% of dynamic programming-based method’s, and is 6.8% better than that of the original DRL algorithm without traffic light information under a real-world driving cycle.
AB - This paper introduces an energy management strategy that combines visual perception and deep reinforcement learning (DRL) algorithms to minimize fuel consumption. The proposed method is capable of autonomously learning the optimal control policy without any prediction efforts. We used a monocular camera in the windshield of a car to catch visual information as inputs. Next, we used state-of-the-art convolutional neural networks based object detection methods to detect and classify traffic light. The traffic light information is used as a state input for a model-free deep reinforcement learning based energy management system with continuous control action. Hence, the traffic light information is incorporated into the energy management system. The experimental results indicate that the fuel economy of the proposed vision-aided strategy achieves 94.5% of dynamic programming-based method’s, and is 6.8% better than that of the original DRL algorithm without traffic light information under a real-world driving cycle.
KW - deep reinforcement learning
KW - energy management strategy
KW - hybrid electric vehicle
KW - traffic light
KW - visual perception
UR - http://www.scopus.com/inward/record.url?scp=85202598018&partnerID=8YFLogxK
U2 - 10.46855/energy-proceedings-2453
DO - 10.46855/energy-proceedings-2453
M3 - Conference article
AN - SCOPUS:85202598018
SN - 2004-2965
VL - 3
JO - Energy Proceedings
JF - Energy Proceedings
T2 - 11th International Conference on Applied Energy, ICAE 2019
Y2 - 12 August 2019 through 15 August 2019
ER -