Scenario Creation
How can I create the millions of scenarios needed to validate an autonomous vehicle?
This many scenarios can't be created by hand.
In the automotive industry, it's widely accepted that validating autonomous vehicles needs a huge number of scenarios that can only be tested in a virtual environment — and that this number can't be created manually.
How can I create the needed millions of scenarios?
Recorded real-world scenarios help, and are even needed as part of the overall validation strategy, but recording every needed scenario on the road is economically infeasible. Many interesting scenarios also involve safety-critical situations that are difficult to safely record in the real world. High-level languages that describe classes of scenarios — such as OpenSCENARIO 2.0 — help, but are usually text-based and therefore hard to use and understand.
Graphical language
BTC Embedded Systems addresses this with an intuitive, graphical language for high-level abstract traffic scenarios. The language describes an abstract scenario in multiple phases, where every parameter — including positions and velocities — can be defined as a parameter range, either absolute or relative to other traffic participants. The graphical environment brings advantages for scenario creation and review, while aiming for compatibility with the ASAM OpenSCENARIO 2.0 standard for flexible tool interoperability.
These abstract scenarios are the basis for all subsequent validation steps, including automatic generation of concrete scenarios and automatic scenario observation.
Before bringing scenarios to a simulation environment, powerful constraint solvers check the defined scenarios for feasibility. This pre-simulation visualizes the dynamic behavior of the scenario and, if no concrete instance can be created, reports potential conflicts between parameter values and ranges — detecting unfeasible scenarios early, before they are ever executed, saving time and cost.
Example
In one example phase, the ego vehicle drives at a speed between 40 and 60 km/h while a fellow vehicle passes on the right lane, starting between 0 and 10 meters behind and ending between 0 and 10 meters in front of the ego vehicle.
Multiple phases, each with its own minimum and maximum duration, are connected into one abstract traffic scenario. Since every parameter can be defined as a value range, each abstract scenario describes an almost infinite set of possible concrete scenarios and simulation runs.
- Ego vehicle speed
- 40 – 60 km/h
- Fellow vehicle, start position
- −10 to 0 m (behind)
- Fellow vehicle, end position
- 0 to +10 m (ahead)
- Lane
- Right lane, passing
Talk to our engineering team.
Tell us where your engineering problem actually is. We'll tell you whether an evaluation license, a workshop, or a conversation is the right next step.