Multi-Head Attention for Joint Multi-Modal Vehicle Motion Forecasting

Jean Mercat (1, 2) , Thomas Gilles (3, 2) , Nicole El Zoghby (2) , Guillaume Sandou (1) , Dominique Beauvois (1) , Guillermo Pita Gil (2)

1 L2S - Laboratoire des signaux et systèmes
2 Technocentre Renault [Guyancourt]
3 X - École polytechnique

This paper presents a novel vehicle motion forecasting method based on multi-head attention. It produces joint forecasts for all vehicles on a road scene as sequences of multi-modal probability density functions of their positions. Its architecture uses multi-head attention to account for complete interactions between all vehicles, and long short-term memory layers for encoding and forecasting. It relies solely on vehicle position tracks, does not need maneuver definitions, and does not represent the scene with a spatial grid. This allows it to be more versatile than similar model while combining many forecasting capabilities, namely joint forecast with interactions, uncertainty estimation, and multi-modality. The resulting prediction likelihood outperforms state-of-the-art models on the same dataset.

Domains: Engineering Sciences [physics]; Automatic

Jean Mercat, Thomas Gilles, Nicole El Zoghby, Guillaume Sandou, Dominique Beauvois, et al.. Multi-Head Attention for Joint Multi-Modal Vehicle Motion Forecasting. IEEE International Conference on Robotics and Automation, May 2020, Paris, France. ⟨hal-02860895⟩