Predicting Agent Behaviour and State for Applications in a Roundabout-Scenario Autonomous Driving.

Naveed Muhammad,Björn Åstrand

doi:10.3390/s19194279

Abstract

As human drivers, we instinctively employ our understanding of other road users’ behaviour for enhanced efficiency of our drive and safety of the traffic. In recent years, different aspects of assisted and autonomous driving have gotten a lot of attention from the research and industrial community, including the aspects of behaviour modelling and prediction of future state. In this paper, we address the problem of modelling and predicting agent behaviour and state in a roundabout traffic scenario. We present three ways of modelling traffic in a roundabout based on: (i) the roundabout geometry; (ii) mean path taken by vehicles inside the roundabout; and (iii) a set of reference trajectories traversed by vehicles inside the roundabout. The roundabout models are compared in terms of exit-direction classification and state (i.e., position inside the roundabout) prediction of query vehicles inside the roundabout. The exit-direction classification and state prediction are based on a particle-filter classifier algorithm. The results show that the roundabout model based on set of reference trajectories is better suited for both the exit-direction and state prediction.

Highlights

Autonomous driving has gotten increased attention from the researchers and industrial community alike over the last 10–15 years
The results show that the roundabout model based on set of reference trajectories is better suited for both the exit-direction and state prediction
This paper presents methods for on-road agent behaviour prediction and state estimation in the context of roundabout traffic scenario

Summary

Introduction

Autonomous driving has gotten increased attention from the researchers and industrial community alike over the last 10–15 years. A significant amount of research has been carried out addressing different aspects of autonomous driving such as object detection [6,7], localisation [8], tracking [9], intention estimation [10], as well as end-to-end deep-learning based approaches (e.g., [11]). In addition to the research explicitly addressing autonomous driving, a lot of closely-related research has been carried out in the area of Advanced Driver Assistance Systems (ADAS); for example, Martinez et al [12]. While being in traffic scenarios ranging from residential neighbourhoods to motorways, we as humans continuously use the understanding of other humans’ behaviour, be it other drivers, bicyclists, pedestrians, etc., to keep ourselves and those sharing the roads with us safe. A detailed discussion on how our implicit understanding of behaviour, and subtle cues

Methods

Results

Discussion

Conclusion