Differential Adaptive Stress Testing of Airborne Collision Avoidance Systems

Lee, Ritchie; Mengshoel, Ole J.; Saksena, Anshu; Gardner, Ryan W.; Genin, Daniel; Brush, Jeffrey S.; Kochenderfer, Mykel J.

doi:10.2514/6.2018-1923

Cited by 14 publications

(12 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The research group of Prof. Kochenderfer uses Reinforcement Learning to find the most likely critical scenarios, and calls it Adaptive Stress Testing [127]- [130]. Koren et al [127] use Monte Carlo Tree Search and Deep Reinforcement Learning.…”

Section: Simulation-based Falsificationmentioning

confidence: 99%

See 1 more Smart Citation

Survey on Scenario-Based Safety Assessment of Automated Vehicles

et al. 2020

View full text Add to dashboard Cite

When will automated vehicles come onto the market? This question has puzzled the automotive industry and society for years. The technology and its implementation have made rapid progress over the last decade, but the challenge of how to prove the safety of these systems has not yet been solved. Since a market launch without proof of safety would neither be accepted by society nor by legislators, much time and many resources have been invested into safety assessment in recent years in order to develop new approaches for an efficient assessment. This paper therefore provides an overview of various approaches, and gives a comprehensive survey of the so-called scenario-based approach. The scenario-based approach is a promising method, in which individual traffic situations are typically tested by means of virtual simulation. Since an infinite number of different scenarios can theoretically occur in real-world traffic, even the scenario-based approach leaves the question unanswered as to how to break these down into a finite set of scenarios, and find those which are representative in order to render testing more manageable. This paper provides a comprehensive literature review of related safety-assessment publications that deal precisely with this question. Therefore, this paper develops a novel taxonomy for the scenario-based approach, and classifies all literature sources. Based on this, the existing methods will be compared with each other and, as one conclusion, the alternative concept of formal verification will be combined with the scenario-based approach. Finally, future research priorities are derived.

show abstract

Section: Simulation-based Falsificationmentioning

confidence: 99%

“…Both papers build on a predecessor paper [129] from the avionic domain. The latter also provides the basis for a paper [130] addressing the differential comparison of two simulators. Instead of minimizing safety, the learner tries to maximize the deviation between both.…”

Section: Simulation-based Falsificationmentioning

confidence: 99%

Survey on Scenario-Based Safety Assessment of Automated Vehicles

et al. 2020

View full text Add to dashboard Cite

show abstract

“…We present a stress testing method, called differential adaptive stress testing (DAST), that extends the AST framework to the differential analysis setting while retaining its desirable properties, including scalability, efficiency, and support for black-box systems. DAST finds the most likely path to a failure event that occurs in the system under test, but not in the baseline system (Lee et al, 2018b). The key idea behind DAST is to drive two simulators in parallel and maximize the difference in their outcomes.…”

Section: Approachmentioning

confidence: 99%

Adaptive Stress Testing: Finding Likely Failure Events with Reinforcement Learning

Lee

Mengshoel

Saksena

et al. 2020

jair

Self Cite

View full text Add to dashboard Cite

Finding the most likely path to a set of failure states is important to the analysis of safety-critical systems that operate over a sequence of time steps, such as aircraft collision avoidance systems and autonomous cars. In many applications such as autonomous driving, failures cannot be completely eliminated due to the complex stochastic environment in which the system operates. As a result, safety validation is not only concerned about whether a failure can occur, but also discovering which failures are most likely to occur. This article presents adaptive stress testing (AST), a framework for finding the most likely path to a failure event in simulation. We consider a general black box setting for partially observable and continuous-valued systems operating in an environment with stochastic disturbances. We formulate the problem as a Markov decision process and use reinforcement learning to optimize it. The approach is simulation-based and does not require internal knowledge of the system, making it suitable for black-box testing of large systems. We present different formulations depending on whether the state is fully observable or partially observable. In the latter case, we present a modified Monte Carlo tree search algorithm that only requires access to the pseudorandom number generator of the simulator to overcome partial observability. We also present an extension of the framework, called differential adaptive stress testing (DAST), that can find failures that occur in one system but not in another. This type of differential analysis is useful in applications such as regression testing, where we are concerned with finding areas of relative weakness compared to a baseline. We demonstrate the effectiveness of the approach on an aircraft collision avoidance application, where a prototype aircraft collision avoidance system is stress tested to find the most likely scenarios of near mid-air collision.

show abstract

“…Various reinforcement learning algorithms can then be applied to find the most probable failure modes of the SUT. AST has successfully been applied to aircraft collision avoidance systems [8], [10] and autonomous driving policies [11]. The AST method is detailed below with an example of an autonomous driving policy being validated for collision avoidance.…”

Section: A Adaptive Stress Testingmentioning

confidence: 99%

Adaptive Stress Testing with Reward Augmentation for Autonomous Vehicle Validatio

Corso

Driggs-Campbell

et al. 2019

2019 IEEE Intelligent Transportation Systems Conference (ITSC)

Self Cite

View full text Add to dashboard Cite

Determining possible failure scenarios is a critical step in the evaluation of autonomous vehicle systems. Real world vehicle testing is commonly employed for autonomous vehicle validation, but the costs and time requirements are high. Consequently, simulation driven methods such as Adaptive Stress Testing (AST) have been proposed to aid in validation. AST formulates the problem of finding the most likely failure scenarios as a Markov decision process, which can be solved using reinforcement learning. In practice, AST tends to find scenarios where failure is unavoidable and tends to repeatedly discover the same types of failures of a system. This work addresses these issues by encoding domain relevant information into the search procedure. With this modification, the AST method discovers a larger and more expressive subset of the failure space when compared to the original AST formulation. We show that our approach is able to identify useful failure scenarios of an autonomous vehicle policy.

show abstract

Differential Adaptive Stress Testing of Airborne Collision Avoidance Systems

Cited by 14 publications

References 7 publications

Survey on Scenario-Based Safety Assessment of Automated Vehicles

Survey on Scenario-Based Safety Assessment of Automated Vehicles

Adaptive Stress Testing: Finding Likely Failure Events with Reinforcement Learning

Adaptive Stress Testing with Reward Augmentation for Autonomous Vehicle Validatio

Contact Info

Product

Resources

About