Towards Certifiable Safety in Learning-Enabled Autonomous Systems: A Perspective

Bansal, Ayoosh; Sha, Lui

Permalink

https://hdl.handle.net/2142/121166 Copy

Description

Title

Towards Certifiable Safety in Learning-Enabled Autonomous Systems: A Perspective

Author(s)

• Bansal, Ayoosh
• Sha, Lui

Issue Date

2025-03-24

Keyword(s)

• software safety
• safety certification
• fault tolerance
• runtime assurance
• safety-critical systems
• autonomous systems
• autonomous vehicles
• autonomous air taxis
• machine learning
• reliability
• robustness

Date of Ingest

2025-03-24T20:31:01-05:00

Abstract

Machine learning has revolutionized the development of autonomous systems by enabling capabilities that would otherwise be infeasible. However, the integration of learning-based components introduces fundamental challenges for safety certification. This paper presents a perspective on achieving the safety certification of learning-enabled autonomous systems without compromising safety standards, with a focus on autonomous vehicles. This perspective explores ongoing research addressing the challenge of safety certification for learning-enabled systems and outlines promising future directions. The key recommendation is the use of certifiable classical software components to ensure that the autonomous system consistently fulfills its safety objectives, regardless of potential faults in learning-based components. However, the lack of certifiable classical alternatives for many safety-critical learning-enabled tasks poses a substantial challenge to the realization of such architectures.

Type of Resource

text

Genre of Resource

working paper

Language

eng

Owning Collections