Developing a parameterized simulation platform with intelligent synthetic agents for training driver candidates

Abstract

This study presents a driver Traffic Training Simulator (TTS) that utilizes intelligent synthetic actors. The movements of intelligent actors are realized using a network flow graph consisting of segment nodes. The intelligent actors in traffic are capable of such objectives as vehicles and lane following. In addition, they are capable of moving according to the traffic signs and lights. The duration of traffic lights can parametrically be determined by the simulator interface. Moreover, parametric values such as weather conditions, seasons, and sunlight can be fed to the simulator as inputs. Similarly, the type of the driver's vehicle and other intelligent vehicles and their numbers can also be parametrically determined. The driver is able to drive in the heavy and light traffic conditions. Currently we are focusing on incorporating the hardware components into the system. Following the tests for the candidates with the system is expected to take place in driver training schools.

Urban traffic modeling with microscopic approach using cellular automata

“…There are several approaches adopted in traffic simulation systems such as macroscopic [25,26], microscopic [23,27], mesoscopic and nanoscopic [28]. The differences between these approaches depend on the level of details.…”

The development of a hardware- and software-based simulation platform for the training of driver candidates

“…As can be seen from Figure 2, a realistic view is produced on 3 screens positioned as in the Figure . For the display, 2 graphics cards (Quadro FX1800, GeForce 9500 GT) and 3 monitors are used. Safe driving skills such as autonomous lane tracking, vehicle tracking of proxy vehicles, and behaviors such as obeying the traffic rules are evaluated by the TSS [23]. Proxy vehicles moving in traffic autonomously may be categorized in terms of their behavior: some vehicles may be set as agents obeying the rules, some as agents disobeying the rules, and some as agents partially obeying the rules.…”

“…City highways are divided into roads, and the roads are divided into segments covering lanes with the starting and ending position information (i.e. the x, y, and z axes), which are then recorded in an XML file [23]. The city roads are connected to each other by junctions.…”

“…If the vehicle moves when the red or yellow lights are on, this is recorded as a mistake. In the system, traffic lights are controlled by a finite state machine, which is responsible for the synchronization of the lights [23]. Traffic lights are the elements that control the traffic at the junctions.…”

“…22 The agents obey the traffic lights. 23 Different types of drivers have increased the realism of the TSS. 24 The display platform has increased the realism of the TSS.…”