基于贝叶斯网络的无人驾驶行为决策研究

无人驾驶系统的决策系统是决定无人驾驶汽车安全性、稳定性的关键技术,是无人驾驶汽车智能程度的体现。本文旨在研究一种基于因果推理的无人驾驶行为决策模型,即理性决策,而不是相关推理。建立了基于贝叶斯网络和强化学习的决策模型,结合深度学习,基于规则的专家系统的特性,深入研究决策模型在样本比较少或数据部分缺失的情况下,提高复杂场景下的适应性、提升泛化能力和迁移学习能力。

Research on unmanned driving behavior decision

The decision-making system of an unmanned driving system is a key technology that determines the safety and stability of an unmanned vehicle,which is a manifestation of the degree of intelligence of an unmanned vehicle.This research aims to explore and develop a self-driving car decision model based on causal reasoning,that is,rational decision-making,not related reasoning.The paper establishes a decision model based on Bayesian network and reinforcement learning,combined with the characteristics of deep learning and rule-based expert systems,and deeply studies the decision model to improve the adaptability of complex scenarios when there are fewer samples or partial missing data.Generalization ability and transfer learning ability are improved.