Bootstrapping confidence in future safety based on past safe operation

10/20/2021
by   Peter Bishop, et al.
0

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 system on a limited basis in the hope that mishap-free operation will confirm one's confidence in its safety and allow progressively more extensive operation: a process of "bootstrapping" of confidence. Translating that intuitive approach into theorems shows: (1) that it is substantially sound in the right circumstances, and could be a good method for deciding about the early deployment phase for an AV; (2) how much confidence can be rightly derived from such a "cautious deployment" approach, so that we can avoid over-optimism; (3) under which conditions our sound formulas for future confidence are applicable; (4) thus, which analyses of the concrete situations, and/or constraints on practice, are needed in order to enjoy the advantages of provably correct confidence in adequate future safety.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/26/2020

Safe Model-Based Meta-Reinforcement Learning: A Sequential Exploration-Exploitation Framework

Safe deployment of autonomous robots in diverse environments requires ag...
research
11/20/2015

A Model for Safety Case Confidence Assessment

Building a safety case is a common approach to make expert judgement exp...
research
02/24/2020

Safe reinforcement learning for probabilistic reachability and safety specifications: A Lyapunov-based approach

Emerging applications in robotics and autonomous systems, such as autono...
research
05/31/2018

Probabilistically Safe Robot Planning with Confidence-Based Human Predictions

In order to safely operate around humans, robots can employ predictive m...
research
10/03/2022

Online Update of Safety Assurances Using Confidence-Based Predictions

Robots such as autonomous vehicles and assistive manipulators are increa...
research
09/12/2020

Positive Trust Balance for Self-Driving Car Deployment

The crucial decision about when self-driving cars are ready to deploy is...

Please sign up or login with your details

Forgot password? Click here to reset