Social Attention: Modeling Attention in Human Crowds
This addresses the challenge of safe and predictable robot navigation in human crowds, which is crucial for robotics and autonomous systems, though it is an incremental improvement over existing trajectory prediction methods.
The paper tackles the problem of predicting human trajectories in crowds for robot navigation by introducing Social Attention, a model that captures the relative importance of people based on future collision risk rather than proximity, and demonstrates its performance against a state-of-the-art approach on two public datasets.
Robots that navigate through human crowds need to be able to plan safe, efficient, and human predictable trajectories. This is a particularly challenging problem as it requires the robot to predict future human trajectories within a crowd where everyone implicitly cooperates with each other to avoid collisions. Previous approaches to human trajectory prediction have modeled the interactions between humans as a function of proximity. However, that is not necessarily true as some people in our immediate vicinity moving in the same direction might not be as important as other people that are further away, but that might collide with us in the future. In this work, we propose Social Attention, a novel trajectory prediction model that captures the relative importance of each person when navigating in the crowd, irrespective of their proximity. We demonstrate the performance of our method against a state-of-the-art approach on two publicly available crowd datasets and analyze the trained attention model to gain a better understanding of which surrounding agents humans attend to, when navigating in a crowd.