Predicting Vehicles Trajectories in Urban Scenarios with Transformer Networks and Augmented Information
This work addresses trajectory prediction for autonomous vehicles in urban environments, representing an incremental improvement by applying existing methods to new data and contexts.
The paper tackles vehicle trajectory prediction in urban scenarios by adapting Transformer Networks with augmented position and heading data, achieving state-of-the-art results across various scenarios like highways and intersections.
Understanding the behavior of road users is of vital importance for the development of trajectory prediction systems. In this context, the latest advances have focused on recurrent structures, establishing the social interaction between the agents involved in the scene. More recently, simpler structures have also been introduced for predicting pedestrian trajectories, based on Transformer Networks, and using positional information. They allow the individual modelling of each agent's trajectory separately without any complex interaction terms. Our model exploits these simple structures by adding augmented data (position and heading), and adapting their use to the problem of vehicle trajectory prediction in urban scenarios in prediction horizons up to 5 seconds. In addition, a cross-performance analysis is performed between different types of scenarios, including highways, intersections and roundabouts, using recent datasets (inD, rounD, highD and INTERACTION). Our model achieves state-of-the-art results and proves to be flexible and adaptable to different types of urban contexts.