Safety of the Intended Driving Behavior Using Rulebooks
This addresses safety assurance for autonomous vehicles by providing a method to handle complex driving scenarios, though it appears incremental as it connects existing frameworks.
The authors linked the Rulebooks framework to the ISO/PAS 21448 Safety of the Intended Functionality (SOTIF) process for autonomous vehicles, establishing that Rulebooks can describe the path planning function and be used for verification and validation.
Autonomous Vehicles (AVs) are complex systems that drive in uncertain environments and potentially navigate unforeseeable situations. Safety of these systems requires not only an absence of malfunctions but also high performance of functions in many different scenarios. The ISO/PAS 21448 [1] guidance recommends a process to ensure the Safety of the Intended Functionality (SOTIF) for road vehicles. This process starts with a functional specification that fully describes the intended functionality and further includes the verification and validation that the AV meets this specification. For the path planning function, defining the correct sequence of control actions for each vehicle in all potential driving situations is intractable. In this paper, the authors provide a link between the Rulebooks framework, presented by [2], and the SOTIF process. We establish that Rulebooks provide a functional description of the path planning task in an AV and discuss the potential usage of the method for verification and validation.