AutonomouS and Connected vehiclE Testing using Infrastructure Sensor Measurements

Important results from the project

The objectives of the project were to 1. Identify and deploy roadside sensor-based naturalistic data collection solution to collect a dataset for extraction of critical merging scenarios for AV development. 2. Model the behaviour of human actors in merging situations. 3. Demonstrate the concept of verification and validation toolchain of AVs using extracted merging scenarios and behaviour models. 4. Identify the gaps in the currently available data, such as quality and quantity and required improvements in data collection systems to enable scenario-based verification of AVs.

Expected long term effects

Scenarios and driver behaviour models were derived from recorded data and scrutinised for integration into simulation and test track testing. This project answered the following research questions: - How can naturalistic data from infrastructure sensors be used in scenario-based verification and validation of autonomous vehicles? - How do data properties, such as location, quantity, accuracy, number of recorded interactions, influence quality of simulations?

Approach and implementation

Requirements for data collection have been derived as an outcome from workshops, project meetings and email communication between project members. The following aspects were lifted as the most important: -Relevance for state-of-the-art AD technologies and intended operational design domains for motorway AD. -Technical and economic feasibility of sensor installations and data collection which would maximise the volume of collected data in the budget frame of the project. -Possibility to generalise the collected data on other on-ramp locations.