REVIEW 6 cited by
Guidance on the Assurance of Machine Learning in Autonomous Systems (AMLAS)
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Machine Learning (ML) is now used in a range of systems with results that are reported to exceed, under certain conditions, human performance. Many of these systems, in domains such as healthcare , automotive and manufacturing, exhibit high degrees of autonomy and are safety critical. Establishing justified confidence in ML forms a core part of the safety case for these systems. In this document we introduce a methodology for the Assurance of Machine Learning for use in Autonomous Systems (AMLAS). AMLAS comprises a set of safety case patterns and a process for (1) systematically integrating safety assurance into the development of ML components and (2) for generating the evidence base for explicitly justifying the acceptable safety of these components when integrated into autonomous system applications.
Forward citations
Cited by 6 Pith papers
-
Safety Case Patterns for VLA-based driving systems: Insights from SimLingo
RAISE supplies reusable Reject-Instruction and Accept-Adequate-Instructions patterns plus an extended HARA that includes safe events, enabling structured safety cases for VLA driving systems, shown on SimLingo.
-
Beyond Component Testing: Validating Agentic AI Systems
Agentic AI cannot be adequately validated by component tests alone; trajectory-in-context validation is required, and current practice is mature only for behavioral evaluation.
-
Robustness Requirement Coverage using a Situation Coverage Approach for Vision-based AI Systems
A position paper integrating camera noise factor identification with situation coverage to express robustness requirements as performance requirements qualified by bounded operational context subsets (PODs).
-
Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levels
A four-layer systems framework and T0–T5 hierarchy for grading and maintaining bounded trustworthiness claims in embodied AI systems.
-
Assuring the Safety of Reinforcement Learning Components: AMLAS-RL
AMLAS-RL defines six stages for generating RL safety assurance arguments, demonstrated on a wheeled vehicle where verification ultimately showed the need to revisit earlier stages.
-
Enhancing Uncertainty Quantification for Runtime Safety Assurance Using Causal Risk Analysis and Operational Design Domain
A Bayesian network built from fault trees and ODD attributes computes a context-aware safety confidence for an automated valet parking object detector at runtime.
Discussion (0). Continue with ORCID to comment.