Predicted-occupancy grids for vehicle safety applications based on autoencoders and the Random Forest algorithm

TL;DR

This paper introduces a machine learning framework combining autoencoders and Random Forests to predict probabilistic occupancy grids for traffic scenarios, aiding vehicle safety and trajectory planning.

Contribution

It presents a novel approach using SDA and RFs to accurately predict future traffic behavior in complex scenarios, enhancing safety applications.

Findings

High accuracy in predicting traffic participant behavior

Effective scenario classification with hierarchical approach

Successful real-vehicle experiments validating the method

Abstract

In this paper, a probabilistic space-time representation of complex traffic scenarios is predicted using machine learning algorithms. Such a representation is significant for all active vehicle safety applications especially when performing dynamic maneuvers in a complex traffic scenario. As a first step, a hierarchical situation classifier is used to distinguish the different types of traffic scenarios. This classifier is responsible for identifying the type of the road infrastructure and the safety-relevant traffic participants of the driving environment. With each class representing similar traffic scenarios, a set of Random Forests (RFs) is individually trained to predict the probabilistic space-time representation, which depicts the future behavior of traffic participants. This representation is termed as a Predicted-Occupancy Grid (POG). The input to the RFs is an Augmented Occupancy Grid (AOG). In order to increase the learning accuracy of the RFs and to perform better predictions, the AOG is reduced to low-dimensional features using a Stacked Denoising Autoencoder (SDA). The excellent performance of the proposed machine learning approach consisting of SDAs and RFs is demonstrated in simulations and in experiments with real vehicles. An application of POGs to estimate the criticality of traffic scenarios and to determine safe trajectories is also presented.