One of the main evolutions observed in the AV industry over the last couple of years is that many companies have got to the point where they can make the fundamentals of AVs work just fine – sensing, planning routes, controlling the vehicle. The really hard part, though, is making them safe enough in all of the core and edge cases.
In order to achieve production-ready AVs that can deal with all possible situations in a safe and responsible way, sufficient coverage metrics for driving scenarios execution are required. An important part of that is a common language to define test driving scenarios. The language should allow a condensed way to describe the 100Ms of possible scenario variants in which AVs must operate and will be used for the execution of those scenarios, as well as for the collection of data and metrics. It also needs to be portable across the various execution platforms (test tracks, various virtual simulators, X in a loop, and street driving). Other characteristics should be its ability to easily cover the space of infinite tests and parameters, allow for bug hunting, and provide an easy way to get grading metrics for the scenarios that were executed and ultimately measure the safety of the autonomous system.
This one-hour Webinar will discuss how to ensure AV and ADAS safety by using measurable scenario description language for driving scenarios. Topics will include:
- How to achieve measurable safety in AVs and ADAS using Coverage Driven Verification
- What is required from a scenario description language
- Scenario writing and mixing of scenarios
- Scenario coverage: specification, collection, and analysis
- Portability, extensibility, and adaptability considerations
An audience Q&A follows the technical presentations.