Long-term human path forecasting in crowds is critical for autonomous moving platforms (like autonomous driving cars and social robots) to avoid collision and make high-quality planning. Although the current research take into account social interactions for prediction, they don't reveal the exact kinds of social interactions happened among people and how the social interactions affect the decision-making process of pedestrians, which further limits its robustness. Social interactions in pedestrian walking are intuitively massive and hard to label and quantify. In this paper, we explore creatively to quantify and interpret how pedestrians interact with others by proposing Learn to Cluster. Our clustering social interactions is probabilistic latent variable generative, learning directly from sequential trajectory observations, scalable to arbitrary number of pedestrians. Learn to cluster is label-free and can be naturally integrated into the training process of the prediction model. The latent variables will then serve as 'labels' to categorize social interactions. Extensive experiments over several trajectory prediction benchmarks demonstrate that our method is able to learn the patterns of social interactions and effectively integrate the patterns to pedestrian trajectory prediction.

翻译：人群中的长期人体路径预测对于自主移动平台（如自动驾驶汽车和社交机器人）避免碰撞并制定高质量规划至关重要。尽管当前研究在预测中考虑了社会交互，但并未揭示人群中发生的具体社会交互类型及其对行人决策过程的影响，这进一步限制了预测的鲁棒性。行人行走中的社会交互本质上数量庞大且难以标注和量化。本文创新性地提出"学习聚类"（Learn to Cluster）方法，以量化和解释行人如何与他人互动。我们的社会交互聚类采用概率潜变量生成模型，可直接从序列轨迹观测中学习，并可扩展至任意数量的行人。该方法是免标注的，能自然融入预测模型的训练过程。潜变量将作为"标签"对社会交互进行分类。在多个轨迹预测基准上的大量实验表明，我们的方法能够学习社会交互模式，并将这些模式有效集成到行人轨迹预测中。