The traditional social force model (SFM) in crowd simulation experiences difficulty coping with the complexity of the crowd, limited by singular physical formulas and parameters. Recent attempts to combine deep learning with these models focus more on simulating specific states of crowds. This paper introduces an advanced deep social force model, influenced by crowd states. It utilizes deep neural networks to accurately fit crowd trajectory features, enhancing behavior simulation capabilities. Geometrical constraints within the model provide control over varied crowd behaviors, adjustable to simulate different crowd types. Before training, we use the SFM to refine behaviors in real trajectories with excessively small distances, aiming to enhance the general applicability of the model. Comparative experiments affirm the effectiveness of the model, showing comparable performance to both classic physical models and modern learning-based hybrid models in pedestrian simulations, with reduced collisions. In addition, the model has a certain ability to simulate crowds with high density and diverse behaviors.

Achieving crowd formation transformations has wide‐ranging applications in fields such as unmanned aerial vehicle formation control, crowd simulation, and large‐scale performances. However, planning trajectories for hundreds of agents is a challenging and tedious task. When modifying crowd formation change schemes, adjustments are typically required based on the style of formation change. Existing methods often involve manual adjustments at each crucial step, leading to a substantial amount of physical labor. Motivated by these challenges, this study introduces a novel generative adversarial network (GAN) for generating crowd formation transformations. The proposed GAN learns specific styles from a series of crowd formation transformation trajectories and can transform a new crowd with an arbitrary number of individuals into the same styles with minimal manual intervention. The model incorporates a space–time transformer module to aggregate spatiotemporal information for learning distinct styles of formation transformation. Furthermore, this article investigates the relationship between the distribution of training data and the length of trajectory sequences, providing insights into the preprocessing of training data.

The purpose of this paper is to improve the efficiency of performance creative choreography (PCC). Our research work shows that we can realize the model integration and data optimization for PCC in complex environments based on the combined architecture of sensor network (SN) and machine‐learning algorithm (MLA). In order to explain the process and content of this research better, this paper designs a specific problem description framework for PCC, which mainly includes the following content: (1) a twin sensor network (TSN) architecture based on digital twin information interaction is proposed, which defines and describes the acquisition method, classification (creative data, rehearsal data, and live data), and temporal and spatial features of performance data. (2) Proposed a mobile computing method based on director semantic annotation (DSA) as the core computing module of TSN. (3) A spatial dynamic line (SDL) model and a creative activation mechanism (CAM) based on DSA are proposed to realize fast and efficient PCC of dance with the TSN architecture. Experimental results show that the TSN architecture proposed in this article is reasonable and effective. The SDL model achieved significantly better performance with little time increase and improved the computability and aesthetics of PCC. New research ideas are proposed to solve the computational problem of PCC in complex environments.