MétaCan
Menu
Back to cohort
Record W4401723277 · doi:10.1109/rew61692.2024.00012

Design of the Safety Case of the Reinforcement Learning-Enabled Component of a Quanser Autonomous Vehicle

2024· article· en· W4401723277 on OpenAlexaff
Mithila Sivakumar, Alvine Boaye Belle, Jinjun Shan, Oluwafemi Odu, Mingfeng Yuan

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldEngineering
TopicSafety Systems Engineering in Autonomy
Canadian institutionsYork University
Fundersnot available
KeywordsComponent (thermodynamics)Reinforcement learningComputer scienceVehicle safetyHuman–computer interactionSystems engineeringEngineeringAutomotive engineeringArtificial intelligence

Abstract

fetched live from OpenAlex

Safety assurance is paramount across industries where mission-critical systems operate, mitigating risks of catas-trophic failures. Safety cases play a pivotal role, particularly in safety critical systems (e.g., autonomous vehicles), in ensuring system reliability and acceptability, providing a structured argument supported by evidence. However, in the safety case literature, it is challenging to get access to a complete safety case, which is crucial for the research community to contribute in this domain. Hence, in this research, we propose an approach to create a safety case for ML-enabled autonomous vehicle, specifically, the Quanser Qcar. We present a complete safety case for a reinforcement learning algorithm applied on the Quanser Qcar to avoid collisions in an unsignalized 4-way intersection. Finally, we report the lessons learned and provide the safety case for the research community to reuse.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.005
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.010
Threshold uncertainty score0.034

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.005
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0010.000
Science and technology studies0.0010.003
Scholarly communication0.0030.002
Open science0.0020.002
Research integrity0.0030.002
Insufficient payload (model declined to judge)0.0100.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.011
GPT teacher head0.201
Teacher spread0.190 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations4
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicSafety Systems Engineering in AutonomyFrench-language works237,207