Creating a computing environment in a driving simulator to orchestrate scenarios with autonomous vehicles

A scenario in a driving simulator covers what the human participants experience and what the researchers need: the physical scene, predefined traffic flow, simulated vehicles' interactions with the participants and measurements to be collected.
Current methodologies used to orchestrate scenarios regarding the interactions have the following drawbacks: 1) Action sequences that simulated vehicles should follow in scenarios are specified without the contexts of each Action; 2) programming languages always include
platform-dependent details and are not suitable for context modelling and scenario sharing and 3) there is no mechanism to handle scenarios dynamically and deal with failures to deploy a scenario.
To overcome these problems, a concept named Assignment, which represents the task(s) of Virtual Drivers, was first developed to encode the contextual information of proposed Actions for interaction generation, e.g., potential simulated vehicles involved.
The Ontology for Scenario Orchestration (OSO) was then developed to model concepts and their relationships in the domain of scenario orchestration including the concept Assignment. It can also provide a file for machine processing.
An algorithm named NAUSEA (autoNomous locAl manoeUvre and
Scenario orchEstration based on automated action plAnning) was finally generated to utilise Assignments recorded in OSO. Encoded in the driver model SAIL (Scenario-Aware drIver modeL), NAUSEA can be used by a Virtual Driver to control simulated vehicles dynamically.
Failed interactions, generated by corresponding Assignments, can be regenerated if necessary. A framework SOAV (Scenario Orchestration with Autonomous simulated Vehicles) was formed to support SAIL/- NAUSEA and orchestrate scenarios with autonomous vehicles.
Three verification experiments were carried out and showed that SOAV was working properly by producing corresponding interactions based on SAIL/NAUSEA and Assignments. They also demonstrated that OSO can provide contextual information in a human-readable and machine processable manner.
The OSO evaluation showed that OSO has several advantages such as being readable, flexible etc., but how it can be presented to varieties of audiences needs further examination.