Adaptive Stress Testing: Finding Likely Failure Events with Reinforcement Learning
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...
Saved in:
| Published in: | The Journal of artificial intelligence research Vol. 69; pp. 1165 - 1201 |
|---|---|
| Main Authors: | , , , , , , , |
| Format: | Conference Proceeding Journal Article |
| Language: | English |
| Published: |
Ames Research Center
AI Access Foundation, Inc
06.12.2020
AI Access Foundation |
| Subjects: | |
| ISSN: | 1076-9757, 1943-5037, 1076-9757 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | 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. |
|---|---|
| AbstractList | 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. |
| Audience | PUBLIC |
| Author | Genin, Daniel Owen, Michael Lee, Ritchie Silbermann, Joshua Gardner, Ryan W. Kochenderfer, Mykel J. Mengshoel, Ole J. Saksena, Anshu |
| Author_xml | – sequence: 1 givenname: Ritchie surname: Lee fullname: Lee, Ritchie organization: Ames Research Center – sequence: 2 givenname: Ole J. surname: Mengshoel fullname: Mengshoel, Ole J. organization: Norwegian University of Science and Technology – sequence: 3 givenname: Anshu surname: Saksena fullname: Saksena, Anshu organization: Johns Hopkins University Applied Physics Laboratory – sequence: 4 givenname: Ryan W. surname: Gardner fullname: Gardner, Ryan W. organization: Johns Hopkins University Applied Physics Laboratory – sequence: 5 givenname: Daniel surname: Genin fullname: Genin, Daniel organization: Johns Hopkins University Applied Physics Laboratory – sequence: 6 givenname: Joshua surname: Silbermann fullname: Silbermann, Joshua organization: Johns Hopkins University Applied Physics Laboratory – sequence: 7 givenname: Michael surname: Owen fullname: Owen, Michael organization: MIT Lincoln Laboratory – sequence: 8 givenname: Mykel J. surname: Kochenderfer fullname: Kochenderfer, Mykel J. organization: Stanford University |
| BookMark | eNp1kEtPAjEYRRujiYDuXLpo4tbBPmhnxh0hoCaTmCCum04fWoQOtgXDv7eIKxNX_dKe296ePjj1nTcAXGE0xBzTu6V0YYiHmOAanYAerke0YIiWp3lGJS_qkpXnoB_jEqF8SKoemI-13CS3M_AlBRMjXJiYnH-7hzPndR5g4z7Mag9n0q22wcDpzvgU4ZdL73BunLddUGad92BjZPA5cQHOrFxFc_m7DsDrbLqYPBbN88PTZNwUihKSilGrlJLWkloyigjmqtUVKRXRvDW8HmlDcCsZZwzbupTYUqYtp5pXmJctNXQAbo73bkL3uc21xbLbBp-fFIQxShiqKp6p2yOlQhdjMFZsglvLsBcYiYM1cbAmsPixlnHyB1cuyeQ6n0I28F_o-hjyMkqRydwg_yhLrnJ9-g3dg3vz |
| CitedBy_id | crossref_primary_10_1007_s13272_025_00815_4 crossref_primary_10_1016_j_oceaneng_2023_114455 crossref_primary_10_1016_j_cirp_2022_05_002 crossref_primary_10_1016_j_ifacol_2022_10_472 crossref_primary_10_1109_TASE_2023_3297984 crossref_primary_10_1016_j_trc_2025_105106 crossref_primary_10_1109_LRA_2021_3133612 crossref_primary_10_1109_TIFS_2023_3309160 crossref_primary_10_1038_s41598_025_11593_8 crossref_primary_10_1177_1748006X211069277 crossref_primary_10_1145_3680468 crossref_primary_10_1007_s11390_024_2900_7 crossref_primary_10_1016_j_inffus_2025_103729 |
| ContentType | Conference Proceeding Journal Article |
| Copyright | Copyright Determination: PUBLIC_USE_PERMITTED 2020. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the associated terms available at https://www.jair.org/index.php/jair/about |
| Copyright_xml | – notice: Copyright Determination: PUBLIC_USE_PERMITTED – notice: 2020. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the associated terms available at https://www.jair.org/index.php/jair/about |
| DBID | CYE CYI AAYXX CITATION 8FE 8FG ABUWG AFKRA ARAPS AZQEC BENPR BGLVJ CCPQU DWQXO GNUQQ HCIFZ JQ2 K7- P62 PHGZM PHGZT PIMPY PKEHL PQEST PQGLB PQQKQ PQUKI PRINS |
| DOI | 10.1613/jair.1.12190 |
| DatabaseName | NASA Scientific and Technical Information NASA Technical Reports Server CrossRef ProQuest SciTech Collection ProQuest Technology Collection ProQuest Central (Alumni) ProQuest Central UK/Ireland Advanced Technologies & Computer Science Collection ProQuest Central Essentials ProQuest Central Technology Collection ProQuest One ProQuest Central ProQuest Central Student SciTech Premium Collection ProQuest Computer Science Collection Computer Science Database ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Premium ProQuest One Academic Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China |
| DatabaseTitle | CrossRef Publicly Available Content Database Advanced Technologies & Aerospace Collection Computer Science Database ProQuest Central Student Technology Collection ProQuest One Academic Middle East (New) ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Essentials ProQuest Computer Science Collection ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest One Applied & Life Sciences ProQuest One Academic UKI Edition ProQuest Central Korea ProQuest Central (New) ProQuest One Academic ProQuest One Academic (New) |
| DatabaseTitleList | CrossRef Publicly Available Content Database |
| Database_xml | – sequence: 1 dbid: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1943-5037 1076-9757 |
| EndPage | 1201 |
| ExternalDocumentID | 10_1613_jair_1_12190 20210018655 |
| GrantInformation | DTRT5715D30011 340428.02.20.01.01 |
| GroupedDBID | .DC 29J 2WC 5GY 5VS AAKMM AAKPC AALFJ AAYFX ACGFO ACM ADBBV ADBSK ADMLS AEFXT AEJOY AENEX AFFHD AFKRA AFWXC AKRVB ALMA_UNASSIGNED_HOLDINGS AMVHM ARAPS BCNDV BENPR BGLVJ CCPQU CYE CYI E3Z EBS EJD F5P FRJ FRP GROUPED_DOAJ GUFHI HCIFZ K7- KQ8 LHSKQ LPJ OK1 OVT P2P PHGZM PHGZT PIMPY PQGLB RNS TR2 XSB AAYXX CITATION 8FE 8FG ABUWG AZQEC DWQXO GNUQQ JQ2 P62 PKEHL PQEST PQQKQ PQUKI PRINS |
| ID | FETCH-LOGICAL-c322t-4bcccaff29a530216cbd827c2d6be694de21ba56551f97a1f35df63d68167b3e3 |
| IEDL.DBID | K7- |
| ISICitedReferencesCount | 38 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000606811900028&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1076-9757 |
| IngestDate | Sun Nov 09 07:25:19 EST 2025 Tue Nov 18 22:23:34 EST 2025 Sat Nov 29 05:27:06 EST 2025 Fri Nov 21 15:49:23 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Adaptive Stress Testing Reinforcement Learning Collision Avoidance Verification And Validation Acas X Safety-Critical Systems |
| Language | English |
| LinkModel | DirectLink |
| MeetingName | 30th International Joint Conference on Artificial Intelligence (IJCAI-21) |
| MergedId | FETCHMERGED-LOGICAL-c322t-4bcccaff29a530216cbd827c2d6be694de21ba56551f97a1f35df63d68167b3e3 |
| Notes | ARC Ames Research Center Virtual ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| OpenAccessLink | https://www.proquest.com/docview/2553250886?pq-origsite=%requestingapplication% |
| PQID | 2553250886 |
| PQPubID | 5160723 |
| PageCount | 37 |
| ParticipantIDs | proquest_journals_2553250886 crossref_primary_10_1613_jair_1_12190 crossref_citationtrail_10_1613_jair_1_12190 nasa_ntrs_20210018655 |
| PublicationCentury | 2000 |
| PublicationDate | 2020-12-06 |
| PublicationDateYYYYMMDD | 2020-12-06 |
| PublicationDate_xml | – month: 12 year: 2020 text: 2020-12-06 day: 06 |
| PublicationDecade | 2020 |
| PublicationPlace | Ames Research Center |
| PublicationPlace_xml | – name: Ames Research Center – name: San Francisco |
| PublicationTitle | The Journal of artificial intelligence research |
| PublicationYear | 2020 |
| Publisher | AI Access Foundation, Inc AI Access Foundation |
| Publisher_xml | – name: AI Access Foundation, Inc – name: AI Access Foundation |
| SSID | ssj0019428 |
| Score | 2.5402966 |
| Snippet | 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,... |
| SourceID | proquest crossref nasa |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 1165 |
| SubjectTerms | Aircraft Aircraft accidents Artificial intelligence Autonomous cars Collision avoidance Collisions Computer simulation Cybernetics, Artificial Intelligence And Robotics Failure Failure analysis Flight data recorders Learning Markov processes Midair collisions Pseudorandom Safety critical Search algorithms Statistics And Probability Systems Analysis And Operations Research |
| Title | Adaptive Stress Testing: Finding Likely Failure Events with Reinforcement Learning |
| URI | https://ntrs.nasa.gov/citations/20210018655 https://www.proquest.com/docview/2553250886 |
| Volume | 69 |
| WOSCitedRecordID | wos000606811900028&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3fT9swELYY7GEvMLZO68YqP2xPk0ftJHbMCwLUCgSroo5N3VPkX0EZKHRNh7T_fj7XqZAmeOE1tqzI3_l8d777DqGPUvPcVNwRIZkmaZoJorjlRFgtpPJuCws82z8uxGSSz2ayiAG3NqZVdjoxKGp7ayBGvu9N34SBNcEP578JdI2C19XYQuMZ2qKMUZDzc0HWrwgyZatSOMGJFJmIie_-Btv_perFFwrcCqCN711Jm41q1X-KOdw2452n_udLtB3tTHy0EoxdtOGaV2in6-GA45F-jaZHVs1B5eFvoWoEXwLtRnN1gMd1KHjBF_W1u_mLx6qGDHY8ggTJFkP8Fk9d4F01IcSII1XrVQ99H48uT05J7LNAjD_OS5Jq43GsKiYV9BCi3GibM2GY5dpxmVrHqFbe8stoJYWiVZLZiieW55QLnbjkjd-128a9RdhWYqgps1TZYSq095eMdlludJIz7STvo8_dVpcmkpBDL4ybEpwRD0wJwJS0DMD00af17PmKfOOBeT1ArfRLtSUDL3ZIoeC2j_Y6jMp4NP34GqB3jw-_Ry8YONeQu8L30OZy8cd9QM_N3bJuFwO0dTyaFNNBcOIHQe78t-Lsa_HzH0lW36g |
| linkProvider | ProQuest |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1LbxMxEB6VgkQvlEdRAwV8oCdkGnt37TVShSpo1CohQiWg3oxfWy1UacgGUP9UfyMeZzdCQnDrgbMty7vzaV6e-QbgubKidJUIVCpuaZ4XkhrhBZXeSmVi2MITz_ankRyPy9NT9X4NrrpeGCyr7HRiUtT-wmGOfC-6vhlHb0K8nn2jODUKX1e7ERpLWAzD5c8YsjX7x2-jfHc5HxxO3hzRdqoAdRG8C5pbF29dVVwZnJjDhLO-5NJxL2wQKveBM2uin1OwSknDqqzwlci8KJmQNgtZPPcG3MyzUiJX_1DS1auFyvmy9U4KqmQh20L7aDH3vph6_pIhlwNq_99M4PrUNOYPQ5Cs22Dzf_svd-FO60eTgyXw78FamN6HzW5GBWlV1gM4OfBmhiqdfEhdMWSCtCLTs1dkUKeGHjKqv4bzSzIwNVbok0MsAG0I5qfJSUi8si6lUElLRXu2BR-v5cseRildTMM2EF_JvmXcM-P7ubQxHnQ2FKWzWcltUKIHLzrRateSrOOsj3ONwVYEgkYgaKYTEHqwu9o9W5KL_GXfFqJEx6MazTFK7zNsKO7BTocJ3aqeuL4CxKN_Lz-D20eTdyM9Oh4PH8MGx0QC1umIHVhfzL-HJ3DL_VjUzfxpQjmBz9cNn19CMzm- |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=proceeding&rft.title=The+Journal+of+artificial+intelligence+research&rft.atitle=Adaptive+Stress+Testing%3A+Finding+Likely+Failure+Events+with+Reinforcement+Learning&rft.au=Lee%2C+Ritchie&rft.au=Mengshoel%2C+Ole+J.&rft.au=Saksena%2C+Anshu&rft.au=Gardner%2C+Ryan+W.&rft.date=2020-12-06&rft.pub=AI+Access+Foundation%2C+Inc&rft.issn=1076-9757&rft.eissn=1943-5037&rft.volume=69&rft_id=info:doi/10.1613%2Fjair.1.12190&rft.externalDBID=CYI&rft.externalDocID=20210018655 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1076-9757&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1076-9757&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1076-9757&client=summon |