汽车视觉感知与自主导航设计系统设计  

Artificial Intelligence-driven Autonomous Driving System Implementation

作　　者：陆毅 由诚 杨孜萱 简彩仁[1] LU Yi;YOU Cheng;YANG Zixuan;JIAN Cairen(Tan Kah kee College,Xiamen University,Zhangzhou Fujian 363105)

机构地区：[1]厦门大学嘉庚学院,福建漳州363105

出　　处：《长江信息通信》2024年第10期9-12,共4页Changjiang Information & Communications

基　　金：厦门大学嘉庚学院大学生创新创业训练计划项目。

摘　　要：文章提供了一个智能车系统的设计方案,硬件作为基础,软件来实现细节.系统以百度Edgeboard开发板为上位机,英飞凌AURIX TC264为下位机,通过摄像头采集图像,利用FPGA模块实现AI模型部署识别与加速,传输信息之后使用PID算法控制电机速度和PD环节控制舵机打角,实现对车运动速度和方向的闭环控制.整体设计稳定可行,能够模拟真实世界中的交通情况。This article provides a design scheme for an artificial intelligence-driven autonomous driving system,with hardware as the basis and software as the implementation details.The sys-tem uses Baidu Edgeboard development board as the upper computer and Infineon AURIX TC264 as the lower computer.It collects images through the camera and uses the FPGA module to implemcnt AI model deploymcnt.After idcntifying and accelcrating,the PID algorithm is used to control thc motor spced and the PD link to control the stcering angle after transmitting the information to achieve closed-loop control of the vehicle's speed and direction.The ovcrall design is stable and feasible,and can simulate traffic conditions in the real world.

关 键 词：智能车 赛道识别 目标检测 PID控制算法 模块设计 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]