Intentions of Vulnerable Road Users - Detection and Forecasting by Means of Machine Learning

TL;DR

This paper presents machine learning models, particularly neural networks, for classifying and predicting the movements of vulnerable road users like pedestrians and cyclists, enhancing early detection and safety in urban traffic.

Contribution

It introduces novel neural network-based movement models for VRUs, combining classification and prediction, and evaluates their performance against traditional methods using a comprehensive urban dataset.

Findings

Higher classification accuracy than IMM Kalman Filtering

Earlier recognition of motion state changes

37-41% reduction in position prediction errors

Abstract

Avoiding collisions with vulnerable road users (VRUs) using sensor-based early recognition of critical situations is one of the manifold opportunities provided by the current development in the field of intelligent vehicles. As especially pedestrians and cyclists are very agile and have a variety of movement options, modeling their behavior in traffic scenes is a challenging task. In this article we propose movement models based on machine learning methods, in particular artificial neural networks, in order to classify the current motion state and to predict the future trajectory of VRUs. Both model types are also combined to enable the application of specifically trained motion predictors based on a continuously updated pseudo probabilistic state classification. Furthermore, the architecture is used to evaluate motion-specific physical models for starting and stopping and video-based pedestrian motion classification. A comprehensive dataset consisting of 1068 pedestrian and 494 cyclist scenes acquired at an urban intersection is used for optimization, training, and evaluation of the different models. The results show substantial higher classification rates and the ability to earlier recognize motion state changes with the machine learning approaches compared to interacting multiple model (IMM) Kalman Filtering. The trajectory prediction quality is also improved for all kinds of test scenes, especially when starting and stopping motions are included. Here, 37\% and 41\% lower position errors were achieved on average, respectively.