Learning the Pedestrian-Vehicle Interaction for Pedestrian Trajectory Prediction

02/10/2022
by   Chi Zhang, et al.
0

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 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 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/16/2021

A context-aware pedestrian trajectory prediction framework for automated vehicles

With the unprecedented shift towards automated urban environments in rec...
research
02/26/2020

Deep Learning and Statistical Models for Time-Critical Pedestrian Behaviour Prediction

The time it takes for a classifier to make an accurate prediction can be...
research
11/06/2021

Prediction of Pedestrian Spatiotemporal Risk Levels for Intelligent Vehicles: A Data-driven Approach

In recent years, road safety has attracted significant attention from re...
research
08/11/2023

Pedestrian Trajectory Prediction in Pedestrian-Vehicle Mixed Environments: A Systematic Review

Planning an autonomous vehicle's (AV) path in a space shared with pedest...
research
12/05/2021

PSI: A Pedestrian Behavior Dataset for Socially Intelligent Autonomous Car

Prediction of pedestrian behavior is critical for fully autonomous vehic...
research
09/24/2021

Deep Social Force

The Social Force model introduced by Helbing and Molnar in 1995 is a cor...

Please sign up or login with your details

Forgot password? Click here to reset