Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Safety Verification for Evasive Collision Avoidance in Autonomous Vehicles with Enhanced Resolutions

Aliasghar Arab, Milad Khaleghi, Alireza Partovi, Alireza Abbaspour, Chaitanya Shinde, Yashar Mousavi, Vahid Azimi, Ali Karimmoddini

TL;DR

The paper addresses the safety verification of an Evasive Minimum Risk Maneuvering (EMRM) feature for autonomous vehicles operating in high-risk, low-probability scenarios. It extends the traditional Hazard Analysis and Risk Assessment (HARA) framework by incorporating a granular loss-evaluation layer that analyzes how mitigation maneuvers affect loss severity, using definitions of Safeites and Safety Margin Integrity Levels. The approach integrates hazard identification, risk prediction, ASIL determination, and safety-goal extraction, with explicit loss-state definitions and SMIL mappings to guide V&V. The findings demonstrate a pathway for verifying EMRM safety in edge cases, enabling more reliable active safety capabilities and informing future standards and regulatory adoption for AVs.

Abstract

This paper presents a comprehensive hazard analysis, risk assessment, and loss evaluation for an Evasive Minimum Risk Maneuvering (EMRM) system designed for autonomous vehicles. The EMRM system is engineered to enhance collision avoidance and mitigate loss severity by drawing inspiration from professional drivers who perform aggressive maneuvers while maintaining stability for effective risk mitigation. Recent advancements in autonomous vehicle technology demonstrate a growing capability for high-performance maneuvers. This paper discusses a comprehensive safety verification process and establishes a clear safety goal to enhance testing validation. The study systematically identifies potential hazards and assesses their risks to overall safety and the protection of vulnerable road users. A novel loss evaluation approach is introduced, focusing on the impact of mitigation maneuvers on loss severity. Additionally, the proposed mitigation integrity level can be used to verify the minimum-risk maneuver feature. This paper applies a verification method to evasive maneuvering, contributing to the development of more reliable active safety features in autonomous driving systems.

Safety Verification for Evasive Collision Avoidance in Autonomous Vehicles with Enhanced Resolutions

TL;DR

The paper addresses the safety verification of an Evasive Minimum Risk Maneuvering (EMRM) feature for autonomous vehicles operating in high-risk, low-probability scenarios. It extends the traditional Hazard Analysis and Risk Assessment (HARA) framework by incorporating a granular loss-evaluation layer that analyzes how mitigation maneuvers affect loss severity, using definitions of Safeites and Safety Margin Integrity Levels. The approach integrates hazard identification, risk prediction, ASIL determination, and safety-goal extraction, with explicit loss-state definitions and SMIL mappings to guide V&V. The findings demonstrate a pathway for verifying EMRM safety in edge cases, enabling more reliable active safety capabilities and informing future standards and regulatory adoption for AVs.

Abstract

This paper presents a comprehensive hazard analysis, risk assessment, and loss evaluation for an Evasive Minimum Risk Maneuvering (EMRM) system designed for autonomous vehicles. The EMRM system is engineered to enhance collision avoidance and mitigate loss severity by drawing inspiration from professional drivers who perform aggressive maneuvers while maintaining stability for effective risk mitigation. Recent advancements in autonomous vehicle technology demonstrate a growing capability for high-performance maneuvers. This paper discusses a comprehensive safety verification process and establishes a clear safety goal to enhance testing validation. The study systematically identifies potential hazards and assesses their risks to overall safety and the protection of vulnerable road users. A novel loss evaluation approach is introduced, focusing on the impact of mitigation maneuvers on loss severity. Additionally, the proposed mitigation integrity level can be used to verify the minimum-risk maneuver feature. This paper applies a verification method to evasive maneuvering, contributing to the development of more reliable active safety features in autonomous driving systems.

Paper Structure

This paper contains 36 sections, 3 equations, 3 figures, 10 tables.

Table of Contents

  1. Introduction
  2. Evasive Minimum Risk Maneuvering Systems
  3. Identification of Hazard and Real-Time Risk Prediction
  4. Risk of Loss Prediction
  5. Planning and Control of Evasive Maneuvers
  6. System Boundaries
  7. HARA Definitions and Procedure
  8. HARA Taxonomy
  9. Hazard
  10. Exposure
  11. Controllability
  12. System Definitions
  13. Function Extraction
  14. Malfunction Derivation
  15. Hazardous Scenarios
  16. ...and 21 more sections

Figures (3)

  • Figure 1: A schematic depicting a hazardous scenario where a basic MRM might fail to avoid or mitigate the loss in an urban operational designed domain. Advanced EMRM can perform aggressive evasive maneuvers to avoid a catastrophic hazard.
  • Figure 2: Hierarchical flow of EMRM system.
  • Figure 3: AV crosses double solid lanes to mitigate a potential collision with a vulnerable road users (scooter riders) to mitigate a potential loss. a) Images captured from videos posted on social media showing an AV is crossing double solid lanes and not returning. b) A schematic of the AVs evasive maneuver for avoiding potential collisions at the same scenario.

Theorems & Definitions (4)

  • Example 1
  • Definition 1: Loss Severity
  • Definition 2: Loss State
  • Example 2