Positive Trust Balance for Self-Driving Car Deployment
- URL: http://arxiv.org/abs/2009.05801v1
- Date: Sat, 12 Sep 2020 14:23:47 GMT
- Title: Positive Trust Balance for Self-Driving Car Deployment
- Authors: Philip Koopman, Michael Wagner
- Abstract summary: Decision about when self-driving cars are ready to deploy is likely to be made with insufficient lagging metric data.
A Positive Trust Balance approach can help with making a responsible deployment decision.
- Score: 3.106768467227812
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The crucial decision about when self-driving cars are ready to deploy is
likely to be made with insufficient lagging metric data to provide high
confidence in an acceptable safety outcome. A Positive Trust Balance approach
can help with making a responsible deployment decision despite this
uncertainty. With this approach, a reasonable initial expectation of safety is
based on a combination of a practicable amount of testing, engineering rigor,
safety culture, and a strong commitment to use post-deployment operational
feedback to further reduce uncertainty. This can enable faster deployment than
would be required by more traditional safety approaches by reducing the
confidence necessary at time of deployment in exchange for a more stringent
requirement for Safety Performance Indicator (SPI) field feedback in the
context of a strong safety culture.
Related papers
- Safety through Permissibility: Shield Construction for Fast and Safe Reinforcement Learning [57.84059344739159]
"Shielding" is a popular technique to enforce safety inReinforcement Learning (RL)
We propose a new permissibility-based framework to deal with safety and shield construction.
arXiv Detail & Related papers (2024-05-29T18:00:21Z) - Safeguarded Progress in Reinforcement Learning: Safe Bayesian
Exploration for Control Policy Synthesis [63.532413807686524]
This paper addresses the problem of maintaining safety during training in Reinforcement Learning (RL)
We propose a new architecture that handles the trade-off between efficient progress and safety during exploration.
arXiv Detail & Related papers (2023-12-18T16:09:43Z) - Searching for Optimal Runtime Assurance via Reachability and
Reinforcement Learning [2.422636931175853]
runtime assurance system (RTA) for a given plant enables the exercise of an untrusted or experimental controller while assuring safety with a backup controller.
Existing RTA design strategies are well-known to be overly conservative and, in principle, can lead to safety violations.
In this paper, we formulate the optimal RTA design problem and present a new approach for solving it.
arXiv Detail & Related papers (2023-10-06T14:45:57Z) - Safety Margins for Reinforcement Learning [74.13100479426424]
We show how to leverage proxy criticality metrics to generate safety margins.
We evaluate our approach on learned policies from APE-X and A3C within an Atari environment.
arXiv Detail & Related papers (2023-07-25T16:49:54Z) - Did You Mean...? Confidence-based Trade-offs in Semantic Parsing [52.28988386710333]
We show how a calibrated model can help balance common trade-offs in task-oriented parsing.
We then examine how confidence scores can help optimize the trade-off between usability and safety.
arXiv Detail & Related papers (2023-03-29T17:07:26Z) - Optimal Transport Perturbations for Safe Reinforcement Learning with Robustness Guarantees [14.107064796593225]
We introduce a safe reinforcement learning framework that incorporates robustness through the use of an optimal transport cost uncertainty set.
In experiments on continuous control tasks with safety constraints, our approach demonstrates robust performance while significantly improving safety at deployment time.
arXiv Detail & Related papers (2023-01-31T02:39:52Z) - ISAACS: Iterative Soft Adversarial Actor-Critic for Safety [0.9217021281095907]
This work introduces a novel approach enabling scalable synthesis of robust safety-preserving controllers for robotic systems.
A safety-seeking fallback policy is co-trained with an adversarial "disturbance" agent that aims to invoke the worst-case realization of model error.
While the learned control policy does not intrinsically guarantee safety, it is used to construct a real-time safety filter.
arXiv Detail & Related papers (2022-12-06T18:53:34Z) - Safe Reinforcement Learning via Confidence-Based Filters [78.39359694273575]
We develop a control-theoretic approach for certifying state safety constraints for nominal policies learned via standard reinforcement learning techniques.
We provide formal safety guarantees, and empirically demonstrate the effectiveness of our approach.
arXiv Detail & Related papers (2022-07-04T11:43:23Z) - PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures [65.36234499099294]
We propose a new data augmentation strategy utilizing the natural structural complexity of pictures such as fractals.
To meet this challenge, we design a new data augmentation strategy utilizing the natural structural complexity of pictures such as fractals.
arXiv Detail & Related papers (2021-12-09T18:59:31Z) - Bootstrapping confidence in future safety based on past safe operation [0.0]
We show an approach to confidence of low enough probability of causing accidents in the early phases of operation.
This formalises 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.
arXiv Detail & Related papers (2021-10-20T18:36:23Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.