用卷积网络预测交通场景中物体未来占据状态，轻量高效且精度领先。
CCLSTM: Coupled Convolutional Long-Short Term Memory Network for Occupancy Flow Forecasting
- 仅用卷积层构建时序-空间联合建模结构，无需向量化输入或注意力机制。
- 在Waymo 2024挑战赛中所有指标排名第一，性能达当前最优水平。
- 适合追求实时部署的自动驾驶系统，尤其适用于低算力场景。
预测动态智能体的未来状态是自动驾驶中的基础任务。一种表达力强的表示方法是占据流场（Occupancy Flow Fields），它能以统一、可扩展的方式建模运动、空间范围及多模态未来分布。尽管近期方法在此表示上取得了优异结果，但通常依赖高质量的向量化输入（实际难以获取），并采用计算开销大的Transformer架构。为此，本文提出耦合卷积长短期记忆网络（CCLSTM），一种仅基于卷积操作的轻量级端到端可训练架构。CCLSTM不依赖向量化输入或自注意力机制，通过紧凑的循环卷积结构有效捕捉时序动态与空间占据流相关性。尽管结构简单，其在占据流指标上达到当前最优表现，截至投稿时，在2024年Waymo占据与流预测挑战赛榜单中所有指标均排名第一。
原文摘要 · Abstract (English)
Predicting future states of dynamic agents is a fundamental task in autonomous driving. An expressive representation for this purpose is Occupancy Flow Fields, which provide a scalable and unified format for modeling motion, spatial extent, and multi-modal future distributions. While recent methods have achieved strong results using this representation, they often depend on high-quality vectorized inputs, which are unavailable or difficult to generate in practice, and the use of transformer-based architectures, which are computationally intensive and costly to deploy. To address these issues, we propose \textbf{Coupled Convolutional LSTM (CCLSTM)}, a lightweight, end-to-end trainable architecture based solely on convolutional operations. Without relying on vectorized inputs or self-attention mechanisms, CCLSTM effectively captures temporal dynamics and spatial occupancy-flow correlations using a compact recurrent convolutional structure. Despite its simplicity, CCLSTM achieves state-of-the-art performance on occupancy flow metrics and, as of this submission, ranks \(1^{\text{st}}\) in all metrics on the 2024 Waymo Occupancy and Flow Prediction Challenge leaderboard.
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。