• Corpus ID: 239050285

Bootstrapping confidence in future safety based on past safe operation

@article{Bishop2021BootstrappingCI,
  title={Bootstrapping confidence in future safety based on past safe operation},
  author={Peter G. Bishop and Andrey Povyakalo and Lorenzo Strigini},
  journal={ArXiv},
  year={2021},
  volume={abs/2110.10718}
}
With autonomous vehicles (AVs), a major concern is the inability to give meaningful quantitative assurance of safety, to the extent required by society – e.g. that an AV must be at least as safe as a good human driver – before that AV is in extensive use. We demonstrate an approach to achieving more moderate, but useful, confidence, e.g., confidence of low enough probability of causing accidents in the early phases of operation. This formalises mathematically the common approach of operating a… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 15 REFERENCES
Assessing Safety-Critical Systems from Operational Testing: A Study on Autonomous Vehicles
TLDR
The problem of using operational testing to demonstrate high reliability in Autonomous Vehicles is revisited and new theorems extending the Conservative Bayesian Inference approach are applied, which exploit the rigour of Bayesian methods while reducing the risk of involuntary misuse.
Assessing the Safety and Reliability of Autonomous Vehicles from Road Testing
TLDR
The advantages of a new variant of Conservative Bayesian Inference (CBI) are presented, which uses prior knowledge while avoiding optimistic biases, and it is shown that, coupled with accuracy assessment and recalibration techniques, SRGMs could be a valuable test planning aid.
Driving to safety: How many miles of driving would it take to demonstrate autonomous vehicle reliability?
How safe are autonomous vehicles? The answer is critical for determining how autonomous vehicles may shape motor vehicle safety and public health, and for developing sound policies to govern their
Stopping rules for the operational testing of safety-critical software
  • B. Littlewood, D. Wright
  • Engineering, Computer Science
    Twenty-Fifth International Symposium on Fault-Tolerant Computing. Digest of Papers
  • 1995
TLDR
It is argued that the earlier failure information needs to be taken into account in devising the form of the test that the modified software needs to pass, and that after such failure the testing requirement might need to be more stringent (i.e. the number of tests that must be executed failure-free should increase).
Does Software Have to Be Ultra Reliable in Safety Critical Systems?
  • P. Bishop
  • Engineering, Computer Science
    SAFECOMP
  • 2013
TLDR
Higher levels of safety performance can be claimed by taking account of: 1) external mitigation to prevent an accident: 2) the fact that software is corrected once failures are detected in operation.
Validation of ultrahigh dependability for software-based systems
TLDR
It appears that engineering practice must take into account the fact that no solution exists, at present, for the validation of ultra-high dependability in systems relying on complex software.
Conservative Confidence Bounds in Safety, from Generalised Claims of Improvement & Statistical Evidence
TLDR
This work proposes a formal probabilistic (Bayesian) organisation for “Proven-in-use”, “globally-at-least-equivalent” and “stress-tested” arguments, and demonstrates scenarios in which formalising such arguments substantially increases confidence in the target system.
Software Fault-Freeness and Reliability Predictions
TLDR
This work addresses how to combine evidence concerning probability of failure together with evidence pertaining to likelihood of fault-freeness, in a Bayesian framework, and guarantees reliability predictions that are conservative (err on the side of pessimism), despite the difficulty of stating prior probability distributions for reliability parameters.
On reliability assessment when a software-based system is replaced by a thought-to-be-better one
TLDR
This paper presents a conservative, Bayesian approach to software reliability assessment – one that combines reliability evidence from an old system with an assessor’s confidence in a newer system being an improved replacement for the old one.
Reliability assessment of service-based software under operational profile uncertainty
TLDR
A new way of dealing with the uncertainty in the operational profile adopting a two-stage Bayesian inference for reliability assessment is presented, which relies on the availability of information about partitions of the input space.
...
1
2
...