Loading…
Comparative safety performance of autonomous- and human drivers: A real-world case study of the Waymo Driver
After several years of public road testing, the commercial deployment of fully autonomous vehicles—or Automated Driving Systems (ADS)—is poised to scale substantially following significant technological advancements and recent regulatory approvals. However, the fundamental question of whether an ADS...
Saved in:
Published in: | Heliyon 2024-07, Vol.10 (14), p.e34379, Article e34379 |
---|---|
Main Authors: | , , , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | |
---|---|
cites | cdi_FETCH-LOGICAL-c445t-20df44ff81ded6787461d665e510dfdd85b8e61490cff979fbabbe16791bb6b23 |
container_end_page | |
container_issue | 14 |
container_start_page | e34379 |
container_title | Heliyon |
container_volume | 10 |
creator | Di Lillo, Luigi Gode, Tilia Zhou, Xilin Atzei, Margherita Chen, Ruoshu Victor, Trent |
description | After several years of public road testing, the commercial deployment of fully autonomous vehicles—or Automated Driving Systems (ADS)—is poised to scale substantially following significant technological advancements and recent regulatory approvals. However, the fundamental question of whether an ADS is safer than its human counterparts remain largely unsolved due to several challenges in establishing an appropriate real-world safety comparison method. As scaling ensues, the lack of an established method can contribute to misinterpretations or uncertainties regarding ADS safety and impede the continuous and consistent assessment of ADS performance. This study introduces three research developments to define a robust and replicable safety comparison method to address this critical methodological gap. First, we introduce the use of liability insurance claims data to measure the comparative safety between ADS and human drivers. Second, we use Swiss Re insurance claims data to establish the first zip code- and responsibility-calibrated human performance benchmark, composed of over 600,000 private passenger vehicle claims and 125 billion miles of driving exposure. Third, we perform a case study by applying the developed baseline to evaluate the safety impact of the Waymo Driver. We find that when benchmarked against zip code-calibrated human baselines, the Waymo Driver significantly improves safety towards other road users. The comparison method established in this study can be replicated for other regions or ADS deployments to aid the decision-making of ADS safety stakeholders such as regulators, and instill trust in the general public. |
doi_str_mv | 10.1016/j.heliyon.2024.e34379 |
format | article |
fullrecord | <record><control><sourceid>proquest_doaj_</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_f30b933b6ca34f30aaf808341e14f9ae</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S2405844024104100</els_id><doaj_id>oai_doaj_org_article_f30b933b6ca34f30aaf808341e14f9ae</doaj_id><sourcerecordid>3090635594</sourcerecordid><originalsourceid>FETCH-LOGICAL-c445t-20df44ff81ded6787461d665e510dfdd85b8e61490cff979fbabbe16791bb6b23</originalsourceid><addsrcrecordid>eNqFkktv3CAUha2qVROl-QmtWHbjKZiHTTdVNH1FitRNqy4RhkuGkW2mgCfyvy-TmabJKise95wPLpyqekvwimAiPmxXGxj8EqZVgxu2AspoK19U5w3DvO4Ywy8fzc-qy5S2GGPCOyFb-ro6o5IQhklzXg3rMO501NnvASXtIC9oB9GFOOrJAAoO6TmHKYxhTjXSk0WbuZSQjcUR00d0hSLoob4LcbDI6FQwebbLwZk3gH7rZQzo8736TfXK6SHB5Wm8qH59_fJz_b2--fHten11UxvGeK4bbB1jznXEghVt1zJBrBAcOCkVazvedyAIk9g4J1vpet33QEQrSd-LvqEX1fWRa4Peql30o46LCtqr-40Qb5WO2ZsBlKO4l5T2wmjKykJr1-GOMgKEOamhsD4dWbu5H8EamHLUwxPo08rkN-o27BUhFHMiZCG8PxFi-DNDymr0ycAw6AnKoypKOO1Iyzr-vBRLLCjnkhUpP0pNDClFcA9XIlgdQqK26hQSdQiJOoak-N497ufB9S8S_xuG8kN7D1El46FkwfoIJpcn9M8c8RdxQtJ3</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3090635594</pqid></control><display><type>article</type><title>Comparative safety performance of autonomous- and human drivers: A real-world case study of the Waymo Driver</title><source>ScienceDirect Journals</source><source>PubMed Central</source><creator>Di Lillo, Luigi ; Gode, Tilia ; Zhou, Xilin ; Atzei, Margherita ; Chen, Ruoshu ; Victor, Trent</creator><creatorcontrib>Di Lillo, Luigi ; Gode, Tilia ; Zhou, Xilin ; Atzei, Margherita ; Chen, Ruoshu ; Victor, Trent</creatorcontrib><description>After several years of public road testing, the commercial deployment of fully autonomous vehicles—or Automated Driving Systems (ADS)—is poised to scale substantially following significant technological advancements and recent regulatory approvals. However, the fundamental question of whether an ADS is safer than its human counterparts remain largely unsolved due to several challenges in establishing an appropriate real-world safety comparison method. As scaling ensues, the lack of an established method can contribute to misinterpretations or uncertainties regarding ADS safety and impede the continuous and consistent assessment of ADS performance. This study introduces three research developments to define a robust and replicable safety comparison method to address this critical methodological gap. First, we introduce the use of liability insurance claims data to measure the comparative safety between ADS and human drivers. Second, we use Swiss Re insurance claims data to establish the first zip code- and responsibility-calibrated human performance benchmark, composed of over 600,000 private passenger vehicle claims and 125 billion miles of driving exposure. Third, we perform a case study by applying the developed baseline to evaluate the safety impact of the Waymo Driver. We find that when benchmarked against zip code-calibrated human baselines, the Waymo Driver significantly improves safety towards other road users. The comparison method established in this study can be replicated for other regions or ADS deployments to aid the decision-making of ADS safety stakeholders such as regulators, and instill trust in the general public.</description><identifier>ISSN: 2405-8440</identifier><identifier>EISSN: 2405-8440</identifier><identifier>DOI: 10.1016/j.heliyon.2024.e34379</identifier><identifier>PMID: 39114012</identifier><language>eng</language><publisher>England: Elsevier Ltd</publisher><subject>case studies ; decision making ; humans ; insurance ; stakeholders</subject><ispartof>Heliyon, 2024-07, Vol.10 (14), p.e34379, Article e34379</ispartof><rights>2024</rights><rights>2024 Published by Elsevier Ltd.</rights><rights>2024 Published by Elsevier Ltd. 2024</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c445t-20df44ff81ded6787461d665e510dfdd85b8e61490cff979fbabbe16791bb6b23</cites><orcidid>0000-0001-8308-9941</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC11305169/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.sciencedirect.com/science/article/pii/S2405844024104100$$EHTML$$P50$$Gelsevier$$Hfree_for_read</linktohtml><link.rule.ids>230,314,724,777,781,882,3536,27905,27906,45761,53772,53774</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/39114012$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Di Lillo, Luigi</creatorcontrib><creatorcontrib>Gode, Tilia</creatorcontrib><creatorcontrib>Zhou, Xilin</creatorcontrib><creatorcontrib>Atzei, Margherita</creatorcontrib><creatorcontrib>Chen, Ruoshu</creatorcontrib><creatorcontrib>Victor, Trent</creatorcontrib><title>Comparative safety performance of autonomous- and human drivers: A real-world case study of the Waymo Driver</title><title>Heliyon</title><addtitle>Heliyon</addtitle><description>After several years of public road testing, the commercial deployment of fully autonomous vehicles—or Automated Driving Systems (ADS)—is poised to scale substantially following significant technological advancements and recent regulatory approvals. However, the fundamental question of whether an ADS is safer than its human counterparts remain largely unsolved due to several challenges in establishing an appropriate real-world safety comparison method. As scaling ensues, the lack of an established method can contribute to misinterpretations or uncertainties regarding ADS safety and impede the continuous and consistent assessment of ADS performance. This study introduces three research developments to define a robust and replicable safety comparison method to address this critical methodological gap. First, we introduce the use of liability insurance claims data to measure the comparative safety between ADS and human drivers. Second, we use Swiss Re insurance claims data to establish the first zip code- and responsibility-calibrated human performance benchmark, composed of over 600,000 private passenger vehicle claims and 125 billion miles of driving exposure. Third, we perform a case study by applying the developed baseline to evaluate the safety impact of the Waymo Driver. We find that when benchmarked against zip code-calibrated human baselines, the Waymo Driver significantly improves safety towards other road users. The comparison method established in this study can be replicated for other regions or ADS deployments to aid the decision-making of ADS safety stakeholders such as regulators, and instill trust in the general public.</description><subject>case studies</subject><subject>decision making</subject><subject>humans</subject><subject>insurance</subject><subject>stakeholders</subject><issn>2405-8440</issn><issn>2405-8440</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>DOA</sourceid><recordid>eNqFkktv3CAUha2qVROl-QmtWHbjKZiHTTdVNH1FitRNqy4RhkuGkW2mgCfyvy-TmabJKise95wPLpyqekvwimAiPmxXGxj8EqZVgxu2AspoK19U5w3DvO4Ywy8fzc-qy5S2GGPCOyFb-ro6o5IQhklzXg3rMO501NnvASXtIC9oB9GFOOrJAAoO6TmHKYxhTjXSk0WbuZSQjcUR00d0hSLoob4LcbDI6FQwebbLwZk3gH7rZQzo8736TfXK6SHB5Wm8qH59_fJz_b2--fHten11UxvGeK4bbB1jznXEghVt1zJBrBAcOCkVazvedyAIk9g4J1vpet33QEQrSd-LvqEX1fWRa4Peql30o46LCtqr-40Qb5WO2ZsBlKO4l5T2wmjKykJr1-GOMgKEOamhsD4dWbu5H8EamHLUwxPo08rkN-o27BUhFHMiZCG8PxFi-DNDymr0ycAw6AnKoypKOO1Iyzr-vBRLLCjnkhUpP0pNDClFcA9XIlgdQqK26hQSdQiJOoak-N497ufB9S8S_xuG8kN7D1El46FkwfoIJpcn9M8c8RdxQtJ3</recordid><startdate>20240730</startdate><enddate>20240730</enddate><creator>Di Lillo, Luigi</creator><creator>Gode, Tilia</creator><creator>Zhou, Xilin</creator><creator>Atzei, Margherita</creator><creator>Chen, Ruoshu</creator><creator>Victor, Trent</creator><general>Elsevier Ltd</general><general>Elsevier</general><scope>6I.</scope><scope>AAFTH</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>7S9</scope><scope>L.6</scope><scope>5PM</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0001-8308-9941</orcidid></search><sort><creationdate>20240730</creationdate><title>Comparative safety performance of autonomous- and human drivers: A real-world case study of the Waymo Driver</title><author>Di Lillo, Luigi ; Gode, Tilia ; Zhou, Xilin ; Atzei, Margherita ; Chen, Ruoshu ; Victor, Trent</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c445t-20df44ff81ded6787461d665e510dfdd85b8e61490cff979fbabbe16791bb6b23</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>case studies</topic><topic>decision making</topic><topic>humans</topic><topic>insurance</topic><topic>stakeholders</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Di Lillo, Luigi</creatorcontrib><creatorcontrib>Gode, Tilia</creatorcontrib><creatorcontrib>Zhou, Xilin</creatorcontrib><creatorcontrib>Atzei, Margherita</creatorcontrib><creatorcontrib>Chen, Ruoshu</creatorcontrib><creatorcontrib>Victor, Trent</creatorcontrib><collection>ScienceDirect Open Access Titles</collection><collection>Elsevier:ScienceDirect:Open Access</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>AGRICOLA</collection><collection>AGRICOLA - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>Heliyon</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Di Lillo, Luigi</au><au>Gode, Tilia</au><au>Zhou, Xilin</au><au>Atzei, Margherita</au><au>Chen, Ruoshu</au><au>Victor, Trent</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Comparative safety performance of autonomous- and human drivers: A real-world case study of the Waymo Driver</atitle><jtitle>Heliyon</jtitle><addtitle>Heliyon</addtitle><date>2024-07-30</date><risdate>2024</risdate><volume>10</volume><issue>14</issue><spage>e34379</spage><pages>e34379-</pages><artnum>e34379</artnum><issn>2405-8440</issn><eissn>2405-8440</eissn><abstract>After several years of public road testing, the commercial deployment of fully autonomous vehicles—or Automated Driving Systems (ADS)—is poised to scale substantially following significant technological advancements and recent regulatory approvals. However, the fundamental question of whether an ADS is safer than its human counterparts remain largely unsolved due to several challenges in establishing an appropriate real-world safety comparison method. As scaling ensues, the lack of an established method can contribute to misinterpretations or uncertainties regarding ADS safety and impede the continuous and consistent assessment of ADS performance. This study introduces three research developments to define a robust and replicable safety comparison method to address this critical methodological gap. First, we introduce the use of liability insurance claims data to measure the comparative safety between ADS and human drivers. Second, we use Swiss Re insurance claims data to establish the first zip code- and responsibility-calibrated human performance benchmark, composed of over 600,000 private passenger vehicle claims and 125 billion miles of driving exposure. Third, we perform a case study by applying the developed baseline to evaluate the safety impact of the Waymo Driver. We find that when benchmarked against zip code-calibrated human baselines, the Waymo Driver significantly improves safety towards other road users. The comparison method established in this study can be replicated for other regions or ADS deployments to aid the decision-making of ADS safety stakeholders such as regulators, and instill trust in the general public.</abstract><cop>England</cop><pub>Elsevier Ltd</pub><pmid>39114012</pmid><doi>10.1016/j.heliyon.2024.e34379</doi><orcidid>https://orcid.org/0000-0001-8308-9941</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 2405-8440 |
ispartof | Heliyon, 2024-07, Vol.10 (14), p.e34379, Article e34379 |
issn | 2405-8440 2405-8440 |
language | eng |
recordid | cdi_doaj_primary_oai_doaj_org_article_f30b933b6ca34f30aaf808341e14f9ae |
source | ScienceDirect Journals; PubMed Central |
subjects | case studies decision making humans insurance stakeholders |
title | Comparative safety performance of autonomous- and human drivers: A real-world case study of the Waymo Driver |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-19T19%3A14%3A38IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Comparative%20safety%20performance%20of%20autonomous-%20and%20human%20drivers:%20A%20real-world%20case%20study%20of%20the%20Waymo%20Driver&rft.jtitle=Heliyon&rft.au=Di%20Lillo,%20Luigi&rft.date=2024-07-30&rft.volume=10&rft.issue=14&rft.spage=e34379&rft.pages=e34379-&rft.artnum=e34379&rft.issn=2405-8440&rft.eissn=2405-8440&rft_id=info:doi/10.1016/j.heliyon.2024.e34379&rft_dat=%3Cproquest_doaj_%3E3090635594%3C/proquest_doaj_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c445t-20df44ff81ded6787461d665e510dfdd85b8e61490cff979fbabbe16791bb6b23%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=3090635594&rft_id=info:pmid/39114012&rfr_iscdi=true |