CeNTI -

Automotive & Aeronautics

IRoADSim

Industrial Robot based Automobile Driving Simulator

The IRoADSim project aims to develop an advanced in-cabin monitoring system combining strategically positioned cameras and sensors, advanced control methodologies and a cutting-edge cyber-physical simulator to create a comprehensive virtual model of driver behaviour under the influence of alcohol and other risky driving conditions.

By leveraging advanced machine learning (ML) and artificial intelligence (AI) technologies, the project will enable the development of a driver behaviour classification system that can be integrated into vehicle active and passive safety systems, contributing to accident prevention and enhanced road safety.

The project also includes the development of an innovative functional steering wheel based on injection moulding and In-Mould Electronics (IME) technologies, integrating embedded sensing systems capable of detecting user interaction parameters such as hand presence on the steering wheel and grip force. The solution will also incorporate haptic and/or visual feedback mechanisms to provide alerts in situations involving erratic steering wheel interaction or potentially dangerous driving behaviour, as well as RGB and infrared camera systems for monitoring head and eye movements.

IRoADSim

Main Goals/Activities

  • Develop a robot-based driving simulator capable of reproducing representative real-world driving scenarios.

  • Develop an in-cabin monitoring system integrating cameras, biometric sensors and driver data acquisition technologies.

  • Develop a functional steering wheel incorporating user interaction sensors and haptic and/or visual feedback mechanisms through the integration of printed and/or hybrid electronics using In-Mould Electronics (IME) technologies.
  • Develop driver behaviour models based on real and synthetic data, supported by artificial intelligence and machine learning algorithms.

  • Develop an advanced AI-driven driver behaviour classification system capable of identifying risky driving patterns and providing real-time feedback.

With support of: