通过自适应高斯混合锚点构建高质量先验，提升行人轨迹预测准确性与多样性。
AGMA: Adaptive Gaussian Mixture Anchors for Prior-Guided Multimodal Human Trajectory Forecasting
- 用两阶段方法从数据中提取行为模式并生成场景自适应先验
- 在ETH-UCY等3个数据集上达到最新性能，显著提升预测精度与多样性
- 适合需要高精度多模态轨迹预测的自动驾驶与机器人导航场景
人类轨迹预测需捕捉行人行为的多模态特性。然而，现有方法常因先验不匹配而受限：学习或固定的先验难以完整表征未来轨迹的合理分布，从而影响预测准确性和多样性。我们理论上证明预测误差下界由先验质量决定，表明先验建模是性能瓶颈。基于此，提出AGMA（自适应高斯混合锚点），通过两阶段构建表达性强的先验：从训练数据中提取多样行为模式，并将其提炼为推理时场景自适应的全局先验。在ETH-UCY、Stanford Drone和JRDB数据集上的大量实验表明，AGMA实现最先进性能，验证了高质量先验在轨迹预测中的关键作用。
原文摘要 · Abstract (English)
Human trajectory forecasting requires capturing the multimodal nature of pedestrian behavior. However, existing approaches suffer from prior misalignment. Their learned or fixed priors often fail to capture the full distribution of plausible futures, limiting both prediction accuracy and diversity. We theoretically establish that prediction error is lower-bounded by prior quality, making prior modeling a key performance bottleneck. Guided by this insight, we propose AGMA (Adaptive Gaussian Mixture Anchors), which constructs expressive priors through two stages: extracting diverse behavioral patterns from training data and distilling them into a scene-adaptive global prior for inference. Extensive experiments on ETH-UCY, Stanford Drone, and JRDB datasets demonstrate that AGMA achieves state-of-the-art performance, confirming the critical role of high-quality priors in trajectory forecasting.
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。