Goal-driven Self-Attentive Recurrent Networks for Trajectory Prediction

TL;DR

This paper introduces a lightweight, attention-based recurrent model for human trajectory prediction that, when combined with a scene-aware goal estimation module, achieves competitive accuracy with reduced complexity.

Contribution

The paper presents a novel, simple recurrent architecture enhanced with a scene-aware goal module, improving trajectory prediction accuracy while maintaining low model complexity.

Findings

Performs on par with state-of-the-art methods

Reduces model complexity significantly

Effective scene-aware goal estimation improves accuracy

Abstract

Human trajectory forecasting is a key component of autonomous vehicles, social-aware robots and advanced video-surveillance applications. This challenging task typically requires knowledge about past motion, the environment and likely destination areas. In this context, multi-modality is a fundamental aspect and its effective modeling can be beneficial to any architecture. Inferring accurate trajectories is nevertheless challenging, due to the inherently uncertain nature of the future. To overcome these difficulties, recent models use different inputs and propose to model human intentions using complex fusion mechanisms. In this respect, we propose a lightweight attention-based recurrent backbone that acts solely on past observed positions. Although this backbone already provides promising results, we demonstrate that its prediction accuracy can be improved considerably when combined with a scene-aware goal-estimation module. To this end, we employ a common goal module, based on a U-Net architecture, which additionally extracts semantic information to predict scene-compliant destinations. We conduct extensive experiments on publicly-available datasets (i.e. SDD, inD, ETH/UCY) and show that our approach performs on par with state-of-the-art techniques while reducing model complexity.