The invention discloses a hybrid electric vehicle ecological driving method based on multi-target deep reinforcement learning, and belongs to the technical field of deep reinforcement learning. Comprising the following steps: constructing models of an adaptive cruise control (ACC) system and a power system of the hybrid electric vehicle; an MODRL algorithm is utilized, and an MODRL-based energy consumption optimization method under the hybrid electric vehicle following scene is established; and further establishing an input network of a weight corresponding to each optimization target by using a conditional network (CN), so that the MODRL algorithm is applied to multi-system collaborative optimization of the hybrid electric vehicle for the first time, and self-adaptive selection of a multi-target weight is realized in combination with a reward weight sampling mechanism. According to the method provided by the invention, the problem of multi-objective tradeoff related to ecological driving of the hybrid electric vehicle can be solved, so that the development period is shortened while the driving and power performance is improved.
本发明公开了一种基于多目标深度强化学习的混合动力汽车生态驾驶方法,属于深度强化学习技术领域。包括如下步骤:构建混合动力汽车自适应巡航系统(ACC)与动力系统的模型;利用MODRL算法,建立基于MODRL的混合动力汽车跟驰场景下的能耗优化方法;进一步利用条件网络(CN),建立每个优化目标对应权重的输入网络,从而将MODRL算法首次应用于混合动力汽车多系统协同优化,结合奖励权重抽样机制,实现多目标权重的自适应选择。本发明所提出的方法能够解决混合动力汽车生态驾驶涉及的多目标权衡问题,从而在提升驾驶和动力性能的同时缩短开发周期。
Hybrid electric vehicle ecological driving method based on multi-target deep reinforcement learning
基于多目标深度强化学习的混合动力汽车生态驾驶方法
2023-06-13
Patent
Electronic Resource
Chinese
Hybrid electric vehicle ecological driving strategy based on multi-agent reinforcement learning
European Patent Office | 2025
|European Patent Office | 2025
|Fuel cell hybrid electric vehicle energy management method based on deep reinforcement learning
European Patent Office | 2024
|Electric vehicle charging method and device based on multi-agent deep reinforcement learning
European Patent Office | 2025
|