Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Safety-Centered Scenario Generation for Autonomous Vehicles

Kiruthiga Chandra Shekar, Aliasghar Moj Arab

TL;DR

A scenario generation framework that creates diverse, parametrized, and safety-critical driving situations to validate the safety features of autonomous vehicles in simulation to enable the systematic evaluation of evasive maneuvering as a safety feature, while highlighting system limitations and edge-case vulnerabilities.

Abstract

This paper presents a scenario generation framework that creates diverse, parametrized, and safety-critical driving situations to validate the safety features of autonomous vehicles in simulation [15]. By modeling factors such as road geometry, traffic participants, environmental conditions, and perception uncertainties, the framework enables repeatable and scalable testing of safety mechanisms, including emergency braking, evasive maneuvers, and vulnerable road user protection. The framework supports both regulatory and edge case scenarios, mapped to hazards and safety goals derived from Hazard Analysis and Risk Assessment (HARA), ensuring traceability to ISO 26262 functional safety requirements and performance limitations. The output from these simulations provides quantitative safety metrics such as time-to-collision, minimum distance, braking and steering performance, and residual collision severity. These metrics enable the systematic evaluation of evasive maneuvering as a safety feature, while highlighting system limitations and edge-case vulnerabilities. Integration of scenario-based simulation with safety engineering principles offers accelerated validation cycles, improved test coverage at reduced cost, and stronger evidence for regulatory and stakeholder confidence.

Safety-Centered Scenario Generation for Autonomous Vehicles

TL;DR

A scenario generation framework that creates diverse, parametrized, and safety-critical driving situations to validate the safety features of autonomous vehicles in simulation to enable the systematic evaluation of evasive maneuvering as a safety feature, while highlighting system limitations and edge-case vulnerabilities.

Abstract

This paper presents a scenario generation framework that creates diverse, parametrized, and safety-critical driving situations to validate the safety features of autonomous vehicles in simulation [15]. By modeling factors such as road geometry, traffic participants, environmental conditions, and perception uncertainties, the framework enables repeatable and scalable testing of safety mechanisms, including emergency braking, evasive maneuvers, and vulnerable road user protection. The framework supports both regulatory and edge case scenarios, mapped to hazards and safety goals derived from Hazard Analysis and Risk Assessment (HARA), ensuring traceability to ISO 26262 functional safety requirements and performance limitations. The output from these simulations provides quantitative safety metrics such as time-to-collision, minimum distance, braking and steering performance, and residual collision severity. These metrics enable the systematic evaluation of evasive maneuvering as a safety feature, while highlighting system limitations and edge-case vulnerabilities. Integration of scenario-based simulation with safety engineering principles offers accelerated validation cycles, improved test coverage at reduced cost, and stronger evidence for regulatory and stakeholder confidence.
Paper Structure (17 sections, 7 equations, 3 figures, 3 tables)

This paper contains 17 sections, 7 equations, 3 figures, 3 tables.

Table of Contents

  1. Abstract
  2. Introduction
  3. Background
  4. Methodology
  5. AI-Based Code Generation
  6. Coverage
  7. Parameter Space Definition
  8. Scenario Coverage Index Formulation
  9. Coverage Results
  10. Implementation
  11. System Under Test
  12. Simulation Framework
  13. Results
  14. Scenario Performance Summary
  15. Aggregate Statistics
  16. ...and 2 more sections

Figures (3)

  • Figure 1: Scenario generation and safety validation architecture overview
  • Figure 2: High-level schematic of the safety-centered scenario generation and evaluation methodology
  • Figure 3: Scenario generation and simulation pipeline execution. The pipeline consists of three main stages: (1) Scenario Generation Module that samples parameters from defined distributions and generates scenario configurations; (2) Simulation Manager that handles actor synchronization, physics simulation stepping, and real-time data recording; and (3) Data Processing Module that aggregates logs, computes safety metrics, and generates statistical summaries. The modular design enables parallel execution of multiple scenarios in headless mode for scalable testing.