CVAIROFeb 10, 2022

Learning the Pedestrian-Vehicle Interaction for Pedestrian Trajectory Prediction

arXiv:2202.05334v217 citations
AI Analysis

This work addresses safety in autonomous driving by improving pedestrian behavior prediction, though it is incremental as it builds on prior models like Social-LSTM and Social-STGCNN.

The paper tackles pedestrian trajectory prediction by learning pedestrian-vehicle interactions, proposing a PVI extractor that reduces average and final displacement errors by up to 7.46% and 5.24% compared to existing methods on the Waymo Open Dataset.

In this paper, we study the interaction between pedestrians and vehicles and propose a novel neural network structure called the Pedestrian-Vehicle Interaction (PVI) extractor for learning the pedestrian-vehicle interaction. We implement the proposed PVI extractor on both sequential approaches (long short-term memory (LSTM) models) and non-sequential approaches (convolutional models). We use the Waymo Open Dataset that contains real-world urban traffic scenes with both pedestrian and vehicle annotations. For the LSTM-based models, our proposed model is compared with Social-LSTM and Social-GAN, and using our proposed PVI extractor reduces the average displacement error (ADE) and the final displacement error (FDE) by 7.46% and 5.24%, respectively. For the convolutional-based models, our proposed model is compared with Social-STGCNN and Social-IWSTCNN, and using our proposed PVI extractor reduces the ADE and FDE by 2.10% and 1.27%, respectively. The results show that the pedestrian-vehicle interaction influences pedestrian behavior, and the models using the proposed PVI extractor can capture the interaction between pedestrians and vehicles, and thereby outperform the compared methods.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes