Autonomous vehicles have limited computational resources and thus require efficient control systems. The cost and size of sensors have limited the development of self-driving cars. To overcome these restrictions, this study proposes an efficient framework for the operation of vision-based automatic vehicles; the framework requires only a monocular camera and a few inexpensive radars. The proposed algorithm comprises a multi-task UNet (MTUNet) network for extracting image features and constrained iterative linear quadratic regulator (CILQR) and vision predictive control (VPC) modules for rapid motion planning and control. MTUNet is designed to simultaneously solve lane line segmentation, the ego vehicle's heading angle regression, road type classification, and traffic object detection tasks at approximately 40 FPS for 228 x 228 pixel RGB input images. The CILQR controllers then use the MTUNet outputs and radar data as inputs to produce driving commands for lateral and longitudinal vehicle guidance within only 1 ms. In particular, the VPC algorithm is included to reduce steering command latency to below actuator latency, preventing performance degradation during tight turns. The VPC algorithm uses road curvature data from MTUNet to estimate the appropriate correction for the current steering angle at a look-ahead point to adjust the turning amount. The inclusion of the VPC algorithm in a VPC-CILQR controller leads to higher performance on curvy roads than the use of CILQR alone. Our experiments demonstrate that the proposed autonomous driving system, which does not require high-definition maps, can be applied in current autonomous vehicles.

翻译：自动驾驶车辆的计算资源有限，因此需要高效的控制系统。传感器的成本与尺寸限制了自动驾驶汽车的发展。为克服这些限制，本研究提出一种面向视觉自动车辆运行的高效框架；该框架仅需单目摄像头与少量低成本雷达。所提算法包含用于提取图像特征的多任务UNet（MTUNet）网络，以及用于快速运动规划与控制的约束迭代线性二次调节器（CILQR）和视觉预测控制（VPC）模块。MTUNet设计用于以约40 FPS的速度同步处理228×228像素RGB输入图像的车道线分割、本车航向角回归、道路类型分类与交通目标检测任务。CILQR控制器随后以MTUNet输出和雷达数据作为输入，在仅1毫秒内生成用于车辆横向与纵向引导的驾驶指令。特别地，系统引入VPC算法以将转向指令延迟降低至执行器延迟以下，从而防止急转弯过程中的性能下降。VPC算法利用MTUNet提供的道路曲率数据，在前视点估计对当前转向角的适当修正量以调整转弯幅度。在VPC-CILQR控制器中集成VPC算法，相较于单独使用CILQR，能在弯道路况下实现更高性能。实验表明，所提出的无需高精地图的自动驾驶系统可适用于现有自动驾驶车辆。