Human motion trajectory prediction using the Social Force Model for real-time and low computational cost applications

Abstract

Human motion trajectory prediction is a very important functionality for human-robot collaboration, specifically in accompany- ing, guiding, or approaching tasks, but also in social robotics, self-driving vehicles, or security systems. In this paper, a novel trajectory prediction model, Social Force Generative Adversarial Network (SoFGAN), is pro- posed. SoFGAN uses a Generative Adversarial Network (GAN) and So- cial Force Model (SFM) to generate different plausible people trajectories reducing collisions in a scene. Furthermore, a Conditional Variational Au- toencoder (CVAE) module is added to emphasize the destination learn- ing. We show that our method is more accurate in making predictions in UCY or BIWI datasets than most of the current state-of-the-art models and also reduces collisions in comparison to other approaches. Through real-life experiments, we demonstrate that the model can be used in real-time without GPU¿s to perform good quality predictions with a low computational cost.