SMEMO: Social Memory for Trajectory Forecasting

arXiv:2203.12446v2 Announce Type: replace
Abstract: Effective modeling of human interactions is of utmost importance when forecasting behaviors such as future trajectories. Each individual, with its motion, influences surrounding agents since everyone obeys to social non-written rules such as collision avoidance or group following. In this paper we model such interactions, which constantly evolve through time, by looking at the problem from an algorithmic point of view, i.e. as a data manipulation task. We present a neural network based on an …

abstract agents arxiv collision cs.cv forecasting future human human interactions importance interactions memory modeling paper rules social through trajectory type