AI Summary & Key Takeaways
AI InsightTest results show that the system improves the drivers' skills and builds trust in them.
📌 3 Key Takeaways
Abstract
In this study, a traffic simulation system (TSS) to provide novice driver candidates with opportunities for training and testing has been developed. Autonomous vehicles that follow the flow of traffic in a microsimulation environment were prepared using a hierarchical concurrent state machine. Autonomous vehicles are skilled and have behavioral aspects such as tracking the lanes, following the vehicles, complying with traffic rules, decelerating, accelerating, and intersection crossings. These driver behaviors are parameterized to allow the autonomous agents to act while disregarding the rules (i.e. aggressive behaviors) or behaving normally. The TSS is operated in 3 different modes, namely the orientation, training, and testing modes. During the orientation phase, the candidate driver's target is to get used to the system and the vehicle, along with traffic rules in city conditions. During training, the driver is warned orally (when necessary) and given written handouts about the mistakes that occurred during the training session. The rules to be obeyed in traffic are kept in an XML file in the system and the data are used to follow the driver's behaviors. During the testing phase, an evaluation mechanism is employed. It observes whether the drivers obey or disregard the rules during the testing time interval. At the end of the test drive, a report showing the driver's mistakes is given. The reports and test results can be recorded in the database with the drivers' names for further analysis and evaluation processes. Driver candidates perform the driving using a steering wheel and pedals, along with a screen platform consisting of 3 monitors. With the TSS user interface, parameterized items such as vehicle selection, the crowdedness of the traffic, the timing of the traffic lights, and the determination of air conditions are possible. The system provides a cheap, affordable, and nonrisky platform for the trainees. Test results show that the system improves the drivers' skills and builds trust in them.
Özet
In this study, a traffic simulation system (TSS) to provide novice driver candidates with opportunities for training and testing has been developed. Autonomous vehicles that follow the flow of traffic in a microsimulation environment were prepared using a hierarchical concurrent state machine. Autonomous vehicles are skilled and have behavioral aspects such as tracking the lanes, following the vehicles, complying with traffic rules, decelerating, accelerating, and intersection crossings. These driver behaviors are parameterized to allow the autonomous agents to act while disregarding the rules (i.e. aggressive behaviors) or behaving normally. The TSS is operated in 3 different modes, namely the orientation, training, and testing modes. During the orientation phase, the candidate driver's target is to get used to the system and the vehicle, along with traffic rules in city conditions. During training, the driver is warned orally (when necessary) and given written handouts about the mistakes that occurred during the training session. The rules to be obeyed in traffic are kept in an XML file in the system and the data are used to follow the driver's behaviors. During the testing phase, an evaluation mechanism is employed. It observes whether the drivers obey or disregard the rules during the testing time interval. At the end of the test drive, a report showing the driver's mistakes is given. The reports and test results can be recorded in the database with the drivers' names for further analysis and evaluation processes. Driver candidates perform the driving using a steering wheel and pedals, along with a screen platform consisting of 3 monitors. With the TSS user interface, parameterized items such as vehicle selection, the crowdedness of the traffic, the timing of the traffic lights, and the determination of air conditions are possible. The system provides a cheap, affordable, and nonrisky platform for the trainees. Test results show that the system improves the drivers' skills and builds trust in them.