用图目标引导和跨上下文注意力预测车辆轨迹，更准更鲁棒。
GC-GAT: Multimodal Vehicular Trajectory Prediction using Graph Goal Conditioning and Cross-context Attention
- 基于车道图生成目标候选，再通过跨注意力融合多源上下文
- 在nuScenes数据集上达到当前最优性能，提升轨迹预测精度
- 适合自动驾驶中复杂交通场景的轨迹预判任务
车辆未来轨迹预测高度依赖模型所接收的上下文信息。上下文可分为静态（如车道线、交通规则）与动态（其他交通参与者）。本文提出一种基于车道图的运动预测模型：先生成图结构的目标提议，再通过跨注意力机制融合多个上下文要素。采用经典的编码器-交互器-解码器架构：编码器使用轻量级门控循环单元编码场景上下文；交互器对编码后的场景特征与图目标提议应用跨注意力；解码器则通过拉普拉斯混合密度网络回归多模态轨迹。利用图目标提议上的跨注意力，模型能聚焦于与目标车辆未来路径相关的场景元素，从而获得更稳健的轨迹估计。在nuScenes运动预测数据集上评估，取得当前最优结果。
原文摘要 · Abstract (English)
Predicting future trajectories of surrounding vehicles heavily relies on what contextual information is given to a motion prediction model. The context itself can be static (lanes, regulatory elements, etc) or dynamic (traffic participants). This paper presents a lane graph-based motion prediction model that first predicts graph-based goal proposals and later fuses them with cross attention over multiple contextual elements. We follow the famous encoder-interactor-decoder architecture where the encoder encodes scene context using lightweight Gated Recurrent Units, the interactor applies cross-context attention over encoded scene features and graph goal proposals, and the decoder regresses multimodal trajectories via Laplacian Mixture Density Network from the aggregated encodings. Using cross-attention over graph-based goal proposals gives robust trajectory estimates since the model learns to attend to future goal-relevant scene elements for the intended agent. We evaluate our work on nuScenes motion prediction dataset, achieving state-of-the-art results.
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。