Risk Assessment Algorithms Based On Recursive Neural Networks

TL;DR

This paper introduces a novel risk assessment method for road intersections using recursive neural networks that encode scene information with directed acyclic graphs, enabling structure learning of risk.

Contribution

The paper presents a new approach combining graph-based information encoding with recursive neural networks to learn risk structures at intersections, advancing safety system development.

Findings

Effective risk assessment demonstrated on predefined scenarios.

The approach learns the structure of risk, not just risk levels.

Potential for future advanced intersection safety systems.

Abstract

The assessment of highly-risky situations at road intersections have been recently revealed as an important research topic within the context of the automotive industry. In this paper we shall introduce a novel approach to compute risk functions by using a combination of a highly non-linear processing model in conjunction with a powerful information encoding procedure. Specifically, the elements of information either static or dynamic that appear in a road intersection scene are encoded by using directed positional acyclic labeled graphs. The risk assessment problem is then reformulated in terms of an inductive learning task carried out by a recursive neural network. Recursive neural networks are connectionist models capable of solving supervised and non-supervised learning problems represented by directed ordered acyclic graphs. The potential of this novel approach is demonstrated through well predefined scenarios. The major difference of our approach compared to others is expressed by the fact of learning the structure of the risk. Furthermore, the combination of a rich information encoding procedure with a generalized model of dynamical recurrent networks permit us, as we shall demonstrate, a sophisticated processing of information that we believe as being a first step for building future advanced intersection safety systems