Search

消失点检测是基于视觉的无人车辆自主导航的重要组成部分。由于非结构化场景存在缺乏清晰的道路线和复杂的背景干扰等问题, 现有检测方法普遍存在精度低、计算时间长的缺点。因此, 针对非结构化道路特点, 提出了一种结合立体视觉的消失点检测方法。采用双目立体视觉技术获得道路图像的视差图, 使用广度优先算法快速估计出道路图像的背景区域; 设计四方向五尺度的Gabor滤波器组估计像素响应幅值, 并通过幅值校正减少检测误差; 结合背景区域设计一系列投票点选择策略, 来剔除背景区域的干扰, 提高算法精度; 采用动态调整候选点范围策略, 减少消失点的搜索范围, 从而提高算法效率; 设计了一种角度优先投票函数, 将在投票空间中获得最大票数的候选点视为消失点。结果表明, 改进的方法在复杂背景干扰的场景下具有较好的鲁棒性, 在检测速度和检测精度上都有显著提升。

Connected and autonomous vehicles (CAV) employ vehicle-to-vehicle communications to safely drive in a platoon with short inter-vehicle distances, which can improve traffic throughput and reduce fuel consumption. With the development of wireless communication technology, more and more information can be used for vehicle controllers. However, is more information better? In this paper, a fuel economy-based performance evaluation index is established for evaluating the efficiency of CAVs driving in a platoon with different communication topologies. Four typical communication topologies that describe the CAV with different amounts of information are studied by the linear controller. The differential evolution algorithm is used to solve the parameters. Due to the increase in information, more control parameters need to be computed, and it is hard to find an optimal solution. So, the simulation results show that CAV with more information did not obtain a better fuel economy. [ABSTRACT FROM AUTHOR]

Intelligent‐driving technologies play crucial roles in reducing road‐traffic accidents and ensuring more convenience while driving. One of the significant challenges in developing an intelligent vehicle is how to operate it safely without causing fear in other human drivers. This paper presents a new behavioral decision‐making model to achieve both safety and high efficiency and also to reduce the adverse effect of autonomous vehicles on the other road users while driving. Moreover, we attempt to adapt the model for human drivers so that users can understand, adapt, and utilize intelligent‐driving technologies. Furthermore, this paper proposes a combined spring model for assessing driving risk. Thus, we analyze some driving characteristics of drivers and choose "safety" and "high efficiency" as the two main factors that are pursued by drivers while driving. Based on the principle of least action, a multiobjective optimization cost function is established for the decision‐making model. Finally, we design six unprotected left‐turn scenarios at a T‐intersection and three unprotected left‐turn scenarios at a standard two‐lane intersection for applying simulation algorithm and provide a decision‐making map for developing intelligent‐driving technologies. Based on the principle of least action, this paper demonstrates that optimization theory can give insight into drivers' behavior and can also contribute to the development of intelligent‐driving algorithms. The experimental results reveal that the behavioral decision‐making model can always avoid collision accidents on the premise of ensuring certain efficiency, and it can achieve 97.01%, 94.52%, 96.67%, 91.18%, 101.27%, 83.33%, 102.94%, 103.03%, and 105.77% of time to intersection's maximum pass rate in the considered nine scenarios. [ABSTRACT FROM AUTHOR]