UC1.1 – Perception Testing
In Use Case 1.1, the SUNRISE SAF is tested for perception systems in urban environments. The aim here is to test those systems in complex urban intersections/scenarios and adverse weather conditions. There are camera-based, LiDAR-based and radar-based perception systems.
There are six behaviours defined for UC1.1: Car-following, outdoor parking with other vehicles entering or leaving parking spots, obstacle avoidance due to construction work, pedestrian and bicycles, and mainly urban intersections like roundabouts and right/left turn junctions. Some of them with day/night conditions and/or adverse weather conditions like fog, rain and others.
Use case overview
Testing of the different elements of the perception layer when the ADS operational design domain includes complex urban intersections and adverse weather conditions.
Objectives
The scope is to extend the current possibilities of test and validation of CCAM functions in urban environments focusing on intersections where the majority of accidents occur due to distracted pedestrians or traffic lights violations.
SAF blocks demonstrated
Safety case setup
- CCAM system under test: Several perception systems (Camera, LiDAR, Radar) of automated driving systems
- Operational Design Domain: Urban Environment
Test environments
Execution with several simulation frameworks, partially based on the harmonised V&V simulation framework designed in the SUNRISE project. Additionally, proving ground tests.
Safety case building
- Microscopic evaluation (on individual scenarios) of pass/fail results
- Coverage-oriented testing
- SOTIF analysis
- Risk-oriented testing
- High-risk scenarios identification
- Knowledge-based scenarios (EuroNCAP)
- Boundary scenarios identification
- Test scenario allocation / re-allocation
- Modular approach
Test scenarios selected
The main scenarios include:
- right/left turn at junction
- pedestrian crossing
- outdoor parking