Huang Renhao, Xue Hao, Pagnucco Maurice, Salim Flora D, Song Yang
IEEE Trans Neural Netw Learn Syst. 2025 Aug;36(8):13691-13708. doi: 10.1109/TNNLS.2025.3550350.
Vision-based trajectory prediction is an important task that supports safe and intelligent behaviors in autonomous systems. Many advanced approaches have been proposed over the years with improved spatial and temporal feature extraction. However, human behavior is naturally diverse and uncertain. Given the past trajectory and surrounding environment information, an agent can have multiple plausible trajectories in the future. To tackle this problem, an essential task named multi-future trajectory prediction (MTP) has recently been studied. This task aims to generate a diverse, acceptable, and explainable distribution of future predictions for each agent. In this article, we present the first survey for MTP with our unique taxonomies and a comprehensive analysis of frameworks, datasets, and evaluation metrics. We also compare models on existing MTP datasets and conduct experiments on the ForkingPath dataset. Finally, we discuss multiple future directions that can help researchers develop novel MTP systems and other diverse learning tasks similar to MTP.
基于视觉的轨迹预测是一项重要任务，它支持自主系统中的安全和智能行为。多年来，人们提出了许多先进方法，改进了空间和时间特征提取。然而，人类行为天然具有多样性和不确定性。给定过去的轨迹和周围环境信息，智能体在未来可能有多个合理的轨迹。为了解决这个问题，最近人们研究了一项名为多未来轨迹预测（MTP）的重要任务。这项任务旨在为每个智能体生成一个多样、可接受且可解释的未来预测分布。在本文中，我们首次对MTP进行了调查，提出了独特的分类法，并对框架、数据集和评估指标进行了全面分析。我们还在现有的MTP数据集上比较了模型，并在ForkingPath数据集上进行了实验。最后，我们讨论了多个未来方向，这些方向可以帮助研究人员开发新颖的MTP系统以及其他类似于MTP的多样学习任务。
