Multi-level crowd simulation using social LSTM.

Due to the complex and subtle behaviors of humans, realistic crowd simulation is difficult. To that end, we propose a novel crowd simulation method that can generate realistic crowd animations with behaviors similar to real crowds and model complex pedestrian behaviors at multiple levels using social long short-term memory (LSTM) neural networks. At the high level, our multi-level simulation model provides global group navigation while at the low level, it can simulate local individual interactions with collision avoidance. We introduce a data-driven method using an improved social LSTM for learning local motion decisions from real pedestrian trajectories in order to capture the subtle movements of the crowd. To achieve scalability, we formulate the low-level and high-level motion control in a force-based scheme. Extensive simulation results demonstrate that our method can produce realistic crowd animations in a variety of scenarios. Evaluations in various metrics show that our method produces better crowd behaviors than previous methods.