Enhancing automated vehicle safety through testing with realistic driver models
| 项目名称： | Enhancing automated vehicle safety through testing with realistic driver models |
| 摘要： | Improving safety during interactions between human drivers and automated vehicles requires an environment where autonomous vehicle software can interact with realistic human driving behavior. Generating this behavior has been challenging due to a lack of driver models that accurately reflect both vehicle kinematics and driver cognition. In this project, the research team proposes to develop an active inference model of car-following behavior that will resolve these limitations. The model will be trained using the UC Berkeley INTERACTION dataset. After training, the team will work with Waymo to validate the model on an internal dataset and, if necessary, implement a set of augmentations that will allow the model to be used to improve the safety of autonomous vehicle interactions with human drivers |
| 状态： | Active |
| 资金： | 150000 |
| 资助组织： | Office of the Assistant Secretary for Research and Technology |
| 管理组织： | Safety through Disruption University Transportation Center (Safe-D) |
| 项目负责人： | Glenn, Eric Zachary |
| 执行机构： | Texas A&M Transportation Institute, College Station |
| 主要研究人员： | McDonald, Tony |
| 开始时间： | 20220115 |
| 预计完成日期： | 20230630 |
| 主题领域： | Highways；Safety and Human Factors；Vehicles and Equipment |
相关文献
- CAV Testing Scenario Design and Implementation using Naturalistic Driving Data and Augmented Reality
- Understanding of advanced vehicle technology: The role of system exposure and perceptions of other road users
- Connected-Vehicle Traffic Signal System Modeling Platform
- Automated Driver's License Test, Computerized Vision Test, and the Real ID Act
- Enhancing the effectiveness of automated vehicle sensory-based alert systems
- Virtual Reality Simulation to Evaluate Drivers’ Mental Models of Advanced Vehicle Technologies
检索历史
应用推荐
