Validating a Traffic Conflict Prediction Technique for Motorways Using a Simulation Approach

Abstract

With the ever-increasing advancements in the technology of driver assistant systems, there is a need for a comprehensive way to identify traffic conflicts to avoid collisions. Although significant research efforts have been devoted to traffic conflict techniques applied for junctions, there is dearth of research on these methods for motorways. This paper presents the validation of a traffic conflict prediction algorithm applied to a motorway scenario in a simulated environment. An automatic video analysis system was developed to identify lane change and rear-end conflicts as ground truth. Using these conflicts, the prediction ability of the traffic conflict technique was validated in an integrated simulation framework. This framework consisted of a sub-microscopic simulator, which provided an appropriate testbed to accurately simulate the components of an intelligent vehicle, and a microscopic traffic simulator able to generate the surrounding traffic. Results from this framework show that for a 10% false alarm rate, approximately 80% and 73% of rear-end and lane change conflicts were accurately predicted, respectively. Despite the fact that the algorithm was not trained using the virtual data, the sensitivity was high. This highlights the transferability of the algorithm to similar road networks, providing a benchmark for the identification of traffic conflict and a relevant step for developing safety management strategies for autonomous vehicles.

Keywords: integrated simulation framework; road safety; traffic conflicts; validation.

Figure 1

Automatic extraction algorithm for lane change and rear-end conflicts from video where EV, PV, and LCV represent the ego-vehicle, preceding vehicle, and lane change vehicle, respectively, while θ, t, s, V, and a represent angle, time, distance, velocity, and acceleration, respectively. Based on these criteria, the timestamps of each identified traffic conflict were recorded and validated. When the threshold was exceeded, the timestamp was highlighted as a traffic conflict by the system.

Figure 2

Visual representation of validating (a) lane change conflict and (b) rear-end conflict.

Figure 3

Ontology and hierarchy for simulation experiments adapted from [30].

Figure 4

The architecture of the integrated simulation platform.

Figure 5

Developing stages of integrated simulation platform.

Figure 6

Section of the motorway for the demonstration experiment showing (i) actual representation and virtual reconstruction in (ii) PreScan and in (iii) PTV VISSIM.

Figure 7

The ego-vehicle used in the simulation framework.

Figure 8

Sensor’s parameters in PreScan GUI converted to module blocks in Simulink interface (bottom right).

Figure 9

Time headway trigger warning in Simulink.

Figure 10

Time headway trigger for preceding vehicle in Simulink.

Figure 11

Estimation of vehicle-related factors in Simulink.

Figure 12

Connection of ego-vehicle to preceding vehicle and harsh braking triggering.

Figure 13

Rear-end conflict in the simulation environment from (a) top-view and (b) from driver’s view.

Figure 14

Time headway of ego-vehicle, velocity, and acceleration of ego-vehicle and opponent vehicle.

Figure 15

Lane change conflict in the simulation environment from (a) top-view and from (b) driver’s view.

Figure 16

Time headway of ego-vehicle, velocity, and acceleration of ego-vehicle and opponent vehicle.

Figure 17

Safe Traffic Dynamic Scenario in the simulation environment from (a) top-view and from (b) driver’s view.

Figure 18

Time headway of ego-vehicle, velocity, and acceleration of ego-vehicle and opponent vehicle.