Take a NAP: Non-Autoregressive Prediction for Pedestrian Trajectories
This work improves trajectory prediction for autonomous systems by replacing autoregressive methods with a non-autoregressive approach, though it is incremental as it builds on existing properties.
The paper tackles pedestrian trajectory prediction by addressing social influence, scene constraints, and multimodality, proposing NAP, a non-autoregressive method that achieves state-of-the-art performance.
Pedestrian trajectory prediction is a challenging task as there are three properties of human movement behaviors which need to be addressed, namely, the social influence from other pedestrians, the scene constraints, and the multimodal (multiroute) nature of predictions. Although existing methods have explored these key properties, the prediction process of these methods is autoregressive. This means they can only predict future locations sequentially. In this paper, we present NAP, a non-autoregressive method for trajectory prediction. Our method comprises specifically designed feature encoders and a latent variable generator to handle the three properties above. It also has a time-agnostic context generator and a time-specific context generator for non-autoregressive prediction. Through extensive experiments that compare NAP against several recent methods, we show that NAP has state-of-the-art trajectory prediction performance.