论文/arXiv 2609.11527·1 个月前

面向 Formula Student Driverless 的基于 Random Forest 的轻量级 LiDAR 锥桶检测框架

提出面向CPU的LiDAR-only轻量感知流水线，并在真实FSD赛事采集的标注簇上验证低延迟锥桶检测。

AI 整理

• 硬件零部件
• 感知与导航
• 数据与采集

原文链接：Lightweight LiDAR-Based Cone Detection Framework Using Random Forest for Formula Student Driverless（arXiv 2609.11527 · 发布日期：2026-09-10）

Lightweight LiDAR-Based Cone Detection Framework Using Random Forest for Formula Student Driverless

提出面向CPU的LiDAR-only轻量感知流水线，并在真实FSD赛事采集的标注簇上验证低延迟锥桶检测。

核心要点

• 面向FSD车辆对可靠、低延迟感知的需求，避免依赖深度学习、多传感器融合和GPU加速。
• 流水线结合地面移除、IMU运动补偿、DBSCAN聚类与几何特征Random Forest分类。
• 特征重要性分析将输入从12项降至7项，同时保持性能。
• 在2,371个真实FSD赛事标注簇上达到98.33% F1，CPU端到端运行3.13 ms，并发布数据集、标注工具和模型。

验证范围与局限：验证范围为真实FSD赛事采集的2,371个标注簇，运行环境为CPU-only硬件。

英文摘要 (Abstract)

Reliable, low-latency perception is crucial for Formula Student Driverless vehicles, yet many existing pipelines rely on deep learning and multi-sensor fusion, often requiring GPU acceleration. This paper presents a lightweight LiDAR-only perception pipeline tailored for CPU execution, combining ground removal, IMU-based motion compensation, DBSCAN clustering, and geometric feature-based Random Forest classification. Feature importance analysis reduced the model input from 12 to 7 features while preserving performance. Evaluated on 2,371 labeled clusters collected from real FSD events, the pipeline achieves an F1-score of 98.33% and an end-to-end runtime of 3.13 ms on CPU-only hardware. The released dataset, labeling tool, and trained models provide a practical and reproducible baseline for other resource-constrained autonomous racing teams.

作者：Márk Mező-Kerekes, Péter Praksz, Chang Liu

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2609.11527：Lightweight LiDAR-Based Cone Detection Framework Using Random Forest for Formula Student Driverless访问 2026-10-21