提升自动驾驶紧急制动的近场监测可靠性
Improving Functional Reliability of Near-Field Monitoring for Emergency Braking in Autonomous Vehicles
- 基于动态空间、物体尺寸和运动预测设计三种监测策略
- 实验显示新策略显著降低误报率，提升系统可靠性
- 适合关注自动驾驶安全与传感器融合的研究者
自动驾驶车辆需要可靠的危险检测能力。然而，主传感器系统可能遗漏近场障碍物，带来安全隐患。尽管专用的快速响应近场监测系统可缓解此问题，但通常存在误报率高的缺陷。本文提出三种基于动态空间特性、相关物体尺寸及运动感知预测的监测策略。在经验证的仿真环境中，对比初始监测策略与所提改进方案，结果表明，新策略能显著提升近场监测系统的功能可靠性。
原文摘要 · Abstract (English)
Autonomous vehicles require reliable hazard detection. However, primary sensor systems may miss near-field obstacles, resulting in safety risks. Although a dedicated fast-reacting near-field monitoring system can mitigate this, it typically suffers from false positives. To mitigate these, in this paper, we introduce three monitoring strategies based on dynamic spatial properties, relevant object sizes, and motion-aware prediction. In experiments in a validated simulation, we compare the initial monitoring strategy against the proposed improvements. The results demonstrate that the proposed strategies can significantly improve the reliability of near-field monitoring systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。