A Reliable Context-Aware and Temporal Planning Framework for Autonomous Driving
作者: Argho Dey, Yunfei Yin, Swachha Ray, Md Minhazul Islam, Zheng Yuan, Sijing Xiong, Hongyu Liu, Zhiqiu Huang
分类: cs.RO, cs.CV
发布日期: 2026-07-06
备注: Submitted to IEEE Transactions on Intelligent Transportation Systems. 12 pages, 6 figures
💡 一句话要点
提出可靠的上下文感知与时间规划框架以解决自动驾驶安全问题
🎯 匹配领域: 支柱三：空间感知与语义 (Perception & Semantics) 支柱七：动作重定向 (Motion Retargeting) 支柱八：物理动画 (Physics-based Animation)
关键词: 自动驾驶 上下文感知 时间规划 轨迹规划 感知与规划融合 鲁棒性 多智能体交互
📋 核心要点
- 现有方法在处理传感器性能下降时的观测数据时，往往未能有效评估观测的可靠性，导致轨迹规划不稳定。
- 本文提出的RCT-AD框架通过质量感知模块和时间轨迹规划器，显式建模特征质量与时间一致性，从而提高规划的安全性与一致性。
- 在nuScenes基准测试中，RCT-AD在感知准确性、运动预测和规划鲁棒性上均优于现有的端到端基线，取得了61.5的检测分数。
📝 摘要（中文）
自动驾驶车辆在密集城市交通中的安全运行依赖于在传感器性能下降时仍能保持可靠的感知与规划。实际驾驶中，摄像头观测常因遮挡、运动模糊、光照变化和传感器噪声而受到干扰，导致轨迹规划不稳定，增加碰撞风险。本文提出的可靠上下文感知与时间规划框架（RCT-AD）显式建模特征质量和时间一致性，以支持更安全、更稳定的规划。通过质量门控的先进先出（FILO）记忆机制，RCT-AD对每帧的可靠性进行评分，选择性保留可信特征，并从可靠的历史上下文重构退化观测。实验结果表明，RCT-AD在nuScenes基准测试中显著提高了感知准确性和规划鲁棒性。
🔬 方法详解
问题定义：本文旨在解决自动驾驶中因传感器性能下降导致的感知与规划不稳定问题。现有方法在处理退化观测时未能有效评估其可靠性，增加了碰撞风险。
核心思路：RCT-AD框架通过引入上下文感知模块，评估每帧观测的可靠性，并利用质量门控的FILO记忆机制选择性保留可信特征，从而重构退化的观测数据，增强场景表示的稳定性。
技术框架：RCT-AD整体架构包括三个主要模块：可靠上下文感知模块、时间轨迹规划器和联合检测-分割头。上下文感知模块负责评分和选择特征，轨迹规划器则捕捉长期依赖和多智能体交互。
关键创新：RCT-AD的主要创新在于显式建模特征质量和时间一致性，采用质量门控机制以确保只使用可靠的观测数据进行规划，这与现有方法的无差别融合方式形成鲜明对比。
关键设计：在设计中，使用了质量门控的FILO记忆机制来管理特征的选择与保留，同时在时间轨迹规划器中引入了长时间依赖和多智能体交互的建模，以提高轨迹的平滑性和安全性。具体的损失函数和网络结构细节在论文中进行了详细描述。
🖼️ 关键图片
📊 实验亮点
RCT-AD在nuScenes基准测试中取得了61.5的检测分数、52.9的平均精度和52.3的平均交并比，相较于现有的端到端基线，显著提高了感知准确性、运动预测和规划鲁棒性，同时保持了适合实时部署的计算效率。
🎯 应用场景
该研究的潜在应用领域包括自动驾驶汽车、智能交通系统和机器人导航等。通过提高自动驾驶系统在复杂环境中的安全性和稳定性，RCT-AD有望在未来的智能交通解决方案中发挥重要作用，推动自动驾驶技术的实际应用与普及。
📄 摘要（原文）
Safe operation of autonomous vehicles in dense urban traffic depends on perception and planning that remain reliable when onboard sensing is degraded. In real driving conditions, camera observations are frequently corrupted by occlusion, motion blur, illumination change, and sensor noise, and when such degraded observations are aggregated indiscriminately over time, trajectory planning becomes unstable and collision risk rises for both the ego vehicle and surrounding road users. Recent Bird's-Eye-View (BEV) approaches unify perception and planning through a shared spatial representation, but most fuse temporal information across frames without assessing the reliability of the underlying observations. We present a Reliable Context-Aware and Temporal Planning framework for Autonomous Driving (RCT-AD) that explicitly models feature quality and temporal consistency to support safer, more consistent planning. A Reliable Context Awareness module scores per-frame reliability and selectively retains trustworthy features through a quality-gated First-In-Last-Out (FILO) memory mechanism, reconstructing degraded observations from reliable historical context so that corrupted inputs do not destabilize the scene representation. A Temporal Trajectory Planner captures long-term dependencies and multi-agent interactions to produce smoother, safety-aware trajectories, while a joint detection-and-segmentation head injects semantic and motion cues into the shared BEV space to strengthen scene understanding. Experiments on the nuScenes autonomous driving benchmark show that RCT-AD improves perception accuracy, motion prediction, and planning robustness over recent end-to-end baselines, achieving 61.5 nuScenes Detection Score, 52.9 mean Average Precision, and 52.3 mean Intersection over Union, while maintaining competitive computational efficiency suitable for real-time deployment.