University of Illinois Urbana-Champaign

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

Bansal, Ayoosh; Sha, Lui

Content Files
Towards_Certifiable_Safety_in_Learning_Enabled_Autonomous_Systems__A_Perspective.pdf

Permalink

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

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

Research and Publications - Electrical and Computer Engineering PRIMARY