Goal-Driven Self-Attentive Recurrent Networks for Trajectory Prediction

Luigi Filippo Chiara, Pasquale Coscia, Sourav Das, Simone Calderara, Rita Cucchiara, Lamberto Ballan; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 2518-2527

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.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Chiara_2022_CVPR, author = {Chiara, Luigi Filippo and Coscia, Pasquale and Das, Sourav and Calderara, Simone and Cucchiara, Rita and Ballan, Lamberto}, title = {Goal-Driven Self-Attentive Recurrent Networks for Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {2518-2527} }