The dataset under consideration is aimed at classifying different driver behaviors and extracting driver patterns. The data was collected using the Carla Simulator platform, and it includes information from a 6-axis virtual IMU (Inertial Measurement Unit) sensor installed on a "Seat Leon" vehicle. The collected data encompasses the driving behaviors of seven distinct drivers on a predefined route with multiple turns.
The primary objective of this dataset is to analyze driver behavior and discern patterns that could have practical applications in areas such as autonomous vehicle development, driver monitoring systems, and road safety.
The data was collected using a customized data collector environment within the Carla Simulator. The simulation environment is based on the "Town03" map, and the data is generated by simulating driving scenarios with a "Seat Leon" car model.
The dataset includes information from a 6-axis virtual IMU sensor, which provides measurements from a 3-axis accelerometer and a 3-axis gyroscope. These sensors capture crucial information about the vehicle's motion and orientation during the simulated drives.
The dataset contains the following features:
- Driver Names: The "class" column, which includes the names of the seven different drivers: [mehdi, apo, gonca, onder, berk, selin, hurcan].
- IMU Data: The dataset includes measurements from the 6-axis IMU sensor, including accelerometer and gyroscope data, which can be further broken down into specific data points, such as acceleration along the x, y, and z axes, and angular velocities around the x, y, and z axes.
- Path Information: The dataset records the path taken by the vehicle, including details about turns and other maneuvers.
The dataset can be used for various applications, including:
- Developing driver monitoring systems for in-vehicle safety.
- Training and evaluating autonomous vehicle algorithms.
- Enhancing driver training programs by tailoring instruction to individual behavior patterns.
- Studying and improving road safety through the identification of risky driving behaviors.
In conclusion, this dataset provides valuable insights into driver behavior and offers opportunities for classification and pattern extraction. The data, collected in a controlled simulation environment, can be used for a variety of applications aimed at improving road safety and advancing autonomous vehicle technology. Further analysis and modeling are required to fully unlock the potential of this dataset.