Lin Haowen, Shaham Sina, Chiang Yao-Yi, Shahabi Cyrus
University of Southern California, Department of Computer Science, Los Angeles, United States.
University of Minnesota, Department of Computer Science and Engineering, Twin Cities, United States.
Proc ACM SIGSPATIAL Int Conf Adv Inf. 2023 Nov;2023. doi: 10.1145/3589132.3625657. Epub 2023 Dec 22.
Accessing realistic human movements (aka trajectories) is essential for many application domains, such as urban planning, transportation, and public health. However, due to privacy and commercial concerns, real-world trajectories are not readily available, giving rise to an important research area of generating synthetic but realistic trajectories. Inspired by the success of deep neural networks (DNN), data-driven methods learn the underlying human decision-making mechanisms and generate synthetic trajectories by directly fitting real-world data. However, these DNN-based approaches do not exploit people's moving behaviors (e.g., work commute, shopping purpose), significantly influencing human decisions during the generation process. This paper proposes MBP-GAIL, a novel framework based on generative adversarial imitation learning that synthesizes realistic trajectories that preserve moving behavior patterns in real data. MBP-GAIL models temporal dependencies by Recurrent Neural Networks (RNN) and combines the stochastic constraints from moving behavior patterns and spatial constraints in the learning process. Through comprehensive experiments, we demonstrate that MBP-GAIL outperforms state-of-the-art methods and can better support decision making in trajectory simulations.
获取真实的人类运动（即轨迹）对于许多应用领域至关重要，如城市规划、交通和公共卫生。然而，由于隐私和商业方面的考虑，现实世界的轨迹不易获取，这催生了一个重要的研究领域，即生成合成但逼真的轨迹。受深度神经网络（DNN）成功的启发，数据驱动的方法学习潜在的人类决策机制，并通过直接拟合现实世界的数据来生成合成轨迹。然而，这些基于DNN的方法没有利用人们的移动行为（如通勤上班、购物目的），在生成过程中对人类决策有显著影响。本文提出了MBP-GAIL，这是一个基于生成对抗模仿学习的新颖框架，它能合成保留真实数据中移动行为模式的逼真轨迹。MBP-GAIL通过递归神经网络（RNN）对时间依赖性进行建模，并在学习过程中结合来自移动行为模式的随机约束和空间约束。通过全面的实验，我们证明MBP-GAIL优于现有方法，并且能在轨迹模拟中更好地支持决策。
