个人信息
参与实验室科研项目
人机协同柔性智造关键技术与集成验证
人机混合智能系统双层智能测试评估技术研究
机载座舱智能系统人机信任动态演化建模方法研究
学术成果
共撰写/参与撰写专利 1 项，录用/发表论文 1 篇，投出待录用论文1篇。 联培学生可能有其他不在此展示的论文/专利。
patent
-
车辆安全驾驶方法、装置、设备以及存储介质
朱晓俊,
甘毓雯,
张忠政,
潘燕,
and 赵云波
2024
[Abs]
[pdf]
本申请公开了一种车辆安全驾驶方法、装置、设备以及存储介质，涉及人机交互及强化学习技术领域，包括：根据获取到的车辆参数，确定周围车辆的行驶意图，其中，车辆参数包括周围车辆的车辆参数和操控车辆的车辆参数；根据车辆参数和行驶意图，应用训练后的神经网络，生成操控车辆的驾驶决策，并控制操控车辆根据驾驶决策行驶。本申请通过在生成驾驶决策时，考虑周围车辆的驾驶意图，改善无法预测人类驾驶行为的问题，降低了交通事故的发生概率。
Conference Articles
-
A Human-Machine Interaction Approach for Overtaking Scenarios Based on Reinforcement Learning and Intent Inference
Huan Wang,
Yuwen Gan,
and Yun-Bo Zhao
In 2025 44th Chinese Control Conference (CCC)
2025
[Abs]
[doi]
[pdf]
In the context of overtaking maneuvers within hybrid human-machine driving scenarios in autonomous driving, traditional approaches predominantly focus on directly modeling the system’s dynamic behavior and subsequently framing it as an optimal control problem. However, these methods are heavily reliant on the accuracy of the models employed, which often contain inherent errors. Furthermore, given the significant variability among individual human drivers and the influence of their unobservable internal states on their actions, control strategies that are solely based on mathematical models are inadequate for predicting fluctuations in human driving strategies. This limitation can lead to huge fluctuations in control volumes. To solve the above problem, this paper adopts an approach that unites a reinforcement learning module(PPO) with an intent inference module.This approach allows for the acquisition of effective decision-making strategies through interaction with the environment, thereby circumventing the need for modeling unknown entities. Additionally, the application of Bayesian inference for intent inference abstracts the determinants of human behavior as intentions, thereby enhancing the predictive capabilities of machines regarding human decision-making and facilitating more efficient and smoother control. The efficacy of this proposed method is validated through simulation experiments.