M
"

Directory

High-Level Overview

Glossary

Input

Data Framework

Performance Assurance

Scenario

Create

Format

Store

Environment

Query & Concretise

Allocate

Execute

Safety Argument

Coverage

Test Evaluate

Safety Case

Decide

Audit

Use Cases

SAF Solutions

Submit Feedback

SUNRISE Safety Assurance Framework

UC1.3 – Cooperative Perception Testing

In Use Case 1.3, the SUNRISE SAF is tested for cooperative perception and decision-making in urban intersection scenarios. The SUT is the perception AD subsystem of an urban chauffer ADS which is also capable of sending/receiving and processing (on-board or off-board e.g. employing a remote smart RSU node) rich V2X information data mainly consisting of object-level data perceived from other road users.

There are three functional scenarios defined from T7.1 for assessing the cooperative perception system performance in Use Case 1.3. The first is the “darting-out pedestrian” scenario (1.3 A), the second one is the “urban junction” scenario (1.3 B), and the third one is the “urban roundabout” scenario (1.3 C).

Use case overview

The Use Case demonstrates SUNRISE safety argumentation for urban collective perception (CP) at pedestrian crossings, intersections and roundabouts, focusing on the co-simulation aspects and the safety case building when occlusions and vehicle to vehicle (V2V) connectivity aspects are present.

Objectives

Adapt existing methodologies and combine different test environments to support connected automated driving (CAD) testing and safety argumentation building.

SAF blocks demonstrated

Safety case setup

  • CCAM system under test: Perception layer of an Automated Driving System (ADS) on a real vehicle, enhanced by cooperative perception. The system integrates external object-level data received via V2X communications (CPMs) from nearby vehicles.
  • Operational Design Domain: Urban road with two-lane straight segment, presence of parked vehicles causing occlusion.

Test environments

  • Virtual testing framework

  • Hybrid testing framework

    • Safety case building

    • Safety evidence: Microscopic evaluation (on individual scenarios) of pass/fail results
    • Safety case pass/fail binary result
    • Test scenario allocation and re-allocation if needed in higher fidelity test environment
    • Co-simulation framework execution
    • Risk-oriented testing: Boundary scenarios identification
    • Test scenario prioritization (based on scenario criticality, exposure and complexity as per ISO 34505)
    • Modular approach: Independent subsystems & End-to-end system testing (Open-Loop / Closed-Loop)
    • Verification of simulation results through Hybrid testing

    Test scenarios selected

    UC 1.3-A Darting-out Pedestrian

    Key take aways

  • Co-simulation setup integrating network aspects made possible
  • SUNRISE’s simulation-first approach used to derive test scenario allocation with hybrid components
  • Gaussian process works well for criticality-driven scenario sampling and pass/fail boundary discovery in scenario spaces of small dimensions

    • Demo videos

    Urban ADS validation / Cooperative perception testing / UC 1.3-A – Darting out pedestrian – VEDECOM
    Urban ADS validation / Cooperative perception testing / UC 1.3-A – Darting out pedestrian – ICCS