一种用于受控环境自动驾驶赛车的模块化架构设计
A Modular Architecture Design for Autonomous Driving Racing in Controlled Environments
AI总结：
本文提出一种模块化自动驾驶架构，用于Formula Student无人驾驶竞赛车辆在封闭赛道环境中的应用，通过YOLOv11实现交通锥检测，结合神经立体深度估计实现3D定位，提升厘米级定位精度，并通过三次样条插值路径规划与纯追求控制器实现高效控制。
摘要：
本文提出了一种模块化自动驾驶架构，用于Formula Student无人驾驶竞赛车辆在封闭赛道环境中的应用。感知模块采用YOLOv11进行实时交通锥检测，在FSOCO数据集上达到0.93 mAP@0.5的检测精度，结合ZED 2i相机的神经立体深度估计实现3D交通锥定位，最大距离7米时中位误差小于0.5米。状态估计通过基于运动自行车模型的扩展卡尔曼滤波融合RTK-GNSS定位和惯性测量单元测量，实现厘米级定位精度，比原始GNSS提升了12厘米。路径规划通过三次样条插值计算赛道路径，并根据曲率和车辆动力学分配速度曲线。受控纯追求控制器通过动态前瞻参数化由速度误差参数化跟踪规划轨迹。整个流程作为模块化ROS 2架构在NVIDIA Jetson Orin NX平台上实现，每个子系统作为独立节点通过双计算机配置通信。实验验证结合现实传感器评估与基于仿真的端到端测试，其中注入现实传感器误差分布以评估系统在代表性条件下的整体性能。
英文摘要：
This paper presents a modular autonomous driving architecture for Formula Student Driverless competition vehicles operating in closed-circuit environments. The perception module employs YOLOv11 for real-time traffic cone detection, achieving 0.93 mAP@0.5 on the FSOCO dataset, combined with neural stereo depth estimation from a ZED 2i camera for 3D cone localization with sub-0.5 m median error at distances up to 7 m. State estimation fuses RTK-GNSS positioning and IMU measurements through an Extended Kalman Filter (EKF) based on a kinematic bicycle model, achieving centimeter-level localization accuracy with a 12 cm improvement over raw GNSS. Path planning computes the racing line via cubic spline interpolation on ordered track boundaries and assigns speed profiles constrained by curvature and vehicle dynamics. A regulated pure pursuit controller tracks the planned trajectory with a dynamic lookahead parameterized by speed error. The complete pipeline is implemented as a modular ROS 2 architecture on an NVIDIA Jetson Orin NX platform, with each subsystem deployed as independent nodes communicating through a dual-computer configuration. Experimental validation combines real-world sensor evaluation with simulation-based end-to-end testing, where realistic sensor error distributions are injected to assess system-level performance under representative conditions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
