arXiv：cs.LG· Arash Raftari, Babak Ebrahimi Soorchaei, Yaser P. Fallah·· 4 小时前AI 评分30
CAA-GMM：面向车辆轨迹预测的上下文感知注意力高斯混合模型
Context-aware Attention-based Gaussian Mixture Models for Vehicular Trajectory Prediction
AI 导读
该论文提出 CAA-GMM，一种上下文感知注意力高斯混合模型，将未来运动建模为以场景上下文和智能体动力学为条件的概率混合，通过轻量注意力机制融合栅格化环境线索与运动历史，实现多模态、不确定性感知的轨迹预测。在 nuScenes 和 Argoverse 2 数据集上，CAA-GMM 精度对标或超越当前最优栅格基线方法，同时保持低计算复杂度；在通信与感知不完美条件下也展现出对不确定性的鲁棒性。
正文
Abstract:Reliable and interpretable trajectory prediction is critical for cooperative and autonomous driving in complex and uncertain environments. This paper introduces a Context-Aware Attention-based Gaussian Mixture Model (CAA-GMM) for multimodal, uncertainty-aware motion forecasting. The proposed approach models future motion as a probabilistic mixture conditioned on both scene context and agent dynamics, capturing diverse behavioral modes with interpretable Gaussian components. A lightweight attention mechanism adaptively encodes inter-agent interactions and contextual salience, enabling efficient fusion of rasterized environment cues and motion history in dense traffic scenes. Comprehensive evaluations on the nuScenes and Argoverse 2 datasets demonstrate that CAA-GMM achieves competitive or superior accuracy compared with state-of-the-art raster-based baselines, while maintaining low computational complexity. Ablation analyses confirm the importance of the attention module for robust contextual reasoning and predictive precision. Furthermore, evaluations under imperfect communication and perception conditions highlight the framework's resilience to uncertainty, establishing CAA-GMM as an efficient and scalable solution for cooperative trajectory prediction in intelligent transportation systems.
| Comments: | 6 pages, 3 figures. Presented at the 2026 IEEE 104th Vehicular Technology Conference (VTC2026-Fall), Boston, MA, USA, 6-9 September 2026 |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.09174 [cs.LG] |
| (or arXiv:2610.09174v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09174 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Arash Raftari [view email]
[v1]
Tue, 6 Oct 2026 22:18:44 UTC (3,251 KB)
来源：arXiv：cs.LG · arxiv.org