{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T19:04:44Z","timestamp":1773860684315,"version":"3.50.1"},"reference-count":47,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Dutch Research Council (NWO)","award":["403.19.243"],"award-info":[{"award-number":["403.19.243"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Robotics"],"abstract":"<jats:p>This paper proposes a novel approach to measuring human driving performance by using the AI capabilities of automated driving systems, illustrated through three example scenarios. Traditionally, the assessment of human driving has followed a bottom-up methodology, where raw data are compared to fixed thresholds, yielding indicators such as the number of hard braking events. However, acceleration threshold exceedances are often heavily influenced by the driving context. We propose a top-down context-aware approach to driving assessments, in which recordings of human-driven vehicles are analyzed by an automated driving system. By comparing the human driver\u2019s speed to the AI\u2019s recommended speed, we derive a level of disagreement that can be used to distinguish between hard braking caused by aggressive driving and emergency braking in response to a critical event. The proposed method may serve as an alternative to the metrics currently used by some insurance companies and may serve as a template for future AI-based driver assessment.<\/jats:p>","DOI":"10.3390\/robotics13120169","type":"journal-article","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T12:25:42Z","timestamp":1732191942000},"page":"169","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["How AI from Automated Driving Systems Can Contribute to the Assessment of Human Driving Behavior"],"prefix":"10.3390","volume":"13","author":[{"given":"Tom","family":"Driessen","sequence":"first","affiliation":[{"name":"Faculty of Mechanical Engineering, Delft University of Technology, 2628 CD Delft, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5614-1262","authenticated-orcid":false,"given":"Olger","family":"Siebinga","sequence":"additional","affiliation":[{"name":"Faculty of Mechanical Engineering, Delft University of Technology, 2628 CD Delft, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"de Boer","sequence":"additional","affiliation":[{"name":"Faculty of Mechanical Engineering, Delft University of Technology, 2628 CD Delft, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9428-3261","authenticated-orcid":false,"given":"Dimitra","family":"Dodou","sequence":"additional","affiliation":[{"name":"Faculty of Mechanical Engineering, Delft University of Technology, 2628 CD Delft, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dick","family":"de Waard","sequence":"additional","affiliation":[{"name":"Faculty of Behavioural and Social Sciences, University of Groningen, 9712 TS Groningen, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1281-8200","authenticated-orcid":false,"given":"Joost","family":"de Winter","sequence":"additional","affiliation":[{"name":"Faculty of Mechanical Engineering, Delft University of Technology, 2628 CD Delft, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"ref_1","unstructured":"Admiral (2024, November 06). Black Box Insurance. Available online: https:\/\/www.admiral.com\/black-box-insurance."},{"key":"ref_2","unstructured":"Allianz (2024, November 06). BonusDrive. Available online: https:\/\/www.allianz.de\/auto\/kfz-versicherung\/telematik-versicherung."},{"key":"ref_3","unstructured":"Allstate (2024, November 06). Drivewise. Available online: https:\/\/www.allstate.com\/drivewise."},{"key":"ref_4","unstructured":"ANWB (2024, November 06). Veilig Rijden [Safe Driving]. Available online: https:\/\/www.anwb.nl\/verzekeringen\/autoverzekering\/veilig-rijden\/hoe-werkt-het."},{"key":"ref_5","unstructured":"Direct Assurance (2024, November 06). YouDrive. Available online: https:\/\/www.direct-assurance.fr\/nos-assurances\/assurance-auto-connectee."},{"key":"ref_6","unstructured":"Nationwide (2024, November 06). SmartRide. Available online: https:\/\/www.nationwide.com\/personal\/insurance\/auto\/discounts\/smartride."},{"key":"ref_7","unstructured":"Tesla (2024, November 06). Safety Score Beta: Version 2.1. Tesla Support. Available online: https:\/\/www.tesla.com\/support\/insurance\/safety-score#version-2.1."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"103016","DOI":"10.1016\/j.trc.2021.103016","article-title":"The association between crashes and safety-critical events: Synthesized evidence from crash reports and naturalistic driving data among commercial truck drivers","volume":"126","author":"Cai","year":"2021","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1026","DOI":"10.1177\/03611981231211897","article-title":"Predicting damage incidents, fines, and fuel consumption from truck driver data: A study from the Netherlands","volume":"2678","author":"Driessen","year":"2024","journal-title":"Transp. Res. Rec."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1007\/s42421-021-00039-y","article-title":"A proactive approach to evaluating intersection safety using hard-braking data","volume":"3","author":"Hunter","year":"2021","journal-title":"J. Big Data Anal. Transp."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/j.tra.2018.04.013","article-title":"The use of context-sensitive insurance telematics data in auto insurance rate making","volume":"113","author":"Ma","year":"2018","journal-title":"Transp. Res. Part A Policy Pract."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"e36501","DOI":"10.1016\/j.heliyon.2024.e36501","article-title":"Pricing weekly motor insurance drivers\u2019 with behavioral and contextual telematics data","volume":"10","author":"Guillen","year":"2024","journal-title":"Heliyon"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"102627","DOI":"10.1016\/j.trd.2020.102627","article-title":"Multivariate and location-specific correlates of fuel consumption: A test track study","volume":"92","author":"Melman","year":"2021","journal-title":"Transp. Res. Part D Transp. Environ."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"107269","DOI":"10.1016\/j.aap.2023.107269","article-title":"Context-aware driver risk prediction with telematics data","volume":"192","author":"Moosavi","year":"2023","journal-title":"Accid. Anal. Prev."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"106997","DOI":"10.1016\/j.aap.2023.106997","article-title":"Using contextual data to predict risky driving events: A novel methodology from explainable artificial intelligence","volume":"184","author":"Masello","year":"2023","journal-title":"Accid. Anal. Prev."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Reig Torra, J., Guillen, M., P\u00e9rez-Mar\u00edn, A.M., Rey G\u00e1mez, L., and Aguer, G. (2023). Weather conditions and telematics panel data in monthly motor insurance claim frequency models. Risks, 11.","DOI":"10.3390\/risks11030057"},{"key":"ref_17","unstructured":"Waymo (2024, November 06). Waymo One, Available online: https:\/\/waymo.com."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"6711","DOI":"10.1109\/TITS.2023.3258145","article-title":"Autonomous vehicle\u2019s impact on traffic: Empirical evidence from Waymo open dataset and implications from modelling","volume":"24","author":"Hu","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_19","unstructured":"Lyft (2024, November 06). Lyft, Available online: https:\/\/www.lyft.com."},{"key":"ref_20","first-page":"355","article-title":"Operational safety of automated and human driving in mixed traffic environments: A perspective of car-following behavior","volume":"237","author":"Li","year":"2023","journal-title":"Proc. Inst. Mech. Eng. Part O J. Risk Reliab."},{"key":"ref_21","unstructured":"NVIDIA (2024, November 06). Self-Driving Vehicles. Available online: https:\/\/www.nvidia.com\/en-us\/self-driving-cars."},{"key":"ref_22","unstructured":"comma.ai (2024, November 06). Openpilot. Available online: https:\/\/comma.ai\/openpilot."},{"key":"ref_23","unstructured":"Dorr, B. (2024, November 06). Prius Sets \u2018Autonomous\u2019 Cannonball Run Record with AI Driving Assistant. Available online: https:\/\/www.yahoo.com\/tech\/prius-sets-autonomous-cannonball-run-180347033.html."},{"key":"ref_24","unstructured":"Tesla (2024, November 06). Full Self-Driving (Supervised). Available online: https:\/\/www.tesla.com\/ownersmanual\/modely\/en_us\/GUID-2CB60804-9CEA-4F4B-8B04-09B991368DC5.html."},{"key":"ref_25","unstructured":"Waymo (2024, November 06). Fleet Response: Lending a Helpful Hand to Waymo\u2019s Autonomously Driven Vehicles. Available online: https:\/\/waymo.com\/blog\/2024\/05\/fleet-response."},{"key":"ref_26","unstructured":"Zoox (2024, November 06). How Zoox Uses Teleguidance to Provide Remote Human Assistance to Its Autonomous Vehicles [Video]. YouTube. Available online: https:\/\/www.youtube.com\/watch?v=NKQHuutVx78."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Lu, S., and Shi, W. (2024). Teleoperation in vehicle computing. Vehicle Computing: From Traditional Transportation to Computing on Wheels, Springer.","DOI":"10.1007\/978-3-031-59963-7"},{"key":"ref_28","unstructured":"Michon, J.A. (1993). Generic Intelligent Driver Support, Taylor Francis Ltd."},{"key":"ref_29","unstructured":"Michon, J.A. (2024, November 06). GIDS: Generic Intelligent Driver Support. Available online: https:\/\/www.jamichon.nl\/jam_writings\/1993_car_driver_support.pdf."},{"key":"ref_30","unstructured":"comma.ai (2024, November 06). Openpilot: An Operating System for Robotics. GitHub. Available online: https:\/\/github.com\/commaai\/openpilot."},{"key":"ref_31","unstructured":"Chen, L., Tang, T., Cai, Z., Li, Y., Wu, P., Li, H., Shi, J., Yan, J., and Qiao, Y. (2022). Level 2 autonomous driving on a single device: Diving into the devils of Openpilot. arXiv."},{"key":"ref_32","unstructured":"comma (2024, November 06). A Drive to Taco Bell [Video]. YouTube. Available online: https:\/\/www.youtube.com\/watch?v=SUIZYzxtMQs."},{"key":"ref_33","unstructured":"Greer Viau (2024, November 06). I Turned My Toyota Corolla into a Self Driving Car [Video]. YouTube. Available online: https:\/\/www.youtube.com\/watch?v=NmBfgOanCyk."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"4250","DOI":"10.21105\/joss.04250","article-title":"JOAN: A framework for human-automated vehicle interaction experiments in a virtual reality driving simulator","volume":"8","author":"Beckers","year":"2023","journal-title":"J. Open Source Softw."},{"key":"ref_35","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., and Koltun, V. (2017, January 13\u201315). CARLA: An open urban driving simulator. Proceedings of the 1st Annual Conference on Robot Learning, Mountain View, CA, USA. Available online: https:\/\/proceedings.mlr.press\/v78\/dosovitskiy17a.html."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.trf.2021.09.021","article-title":"Driving examiners\u2019 views on data-driven assessment of test candidates: An interview study","volume":"83","author":"Driessen","year":"2021","journal-title":"Transp. Res. Part F Traffic Psychol. Behav."},{"key":"ref_37","unstructured":"Hennessey, M.P., Shankwitz, C., and Donath, M. (1995, January 22\u201326). Sensor-based virtual bumpers for collision avoidance: Configuration issues. Proceedings of the PHOTONICS EAST \u201995, Philadelphia, PA, USA."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1109\/TITS.2020.3008284","article-title":"Dynamic driving risk potential field model under the connected and automated vehicles environment and its application in car-following modeling","volume":"23","author":"Li","year":"2020","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"103428","DOI":"10.1016\/j.trc.2021.103428","article-title":"A risk field-based metric correlates with driver\u2019s perceived risk in manual and automated driving: A test-track study","volume":"133","author":"Kolekar","year":"2021","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_40","unstructured":"comma.ai (2024, November 06). Development Speed Over Everything [Blog]. 11 October 2022. Available online: https:\/\/blog.comma.ai\/dev-speed."},{"key":"ref_41","unstructured":"Allen, R.W., Rosenthal, T.J., and Aponso, B.L. (December, January 30). Measurement of behavior and performance in driving simulation. Proceedings of the Driving Simulation Conference North America, 2005, Orlando, FL, USA. Available online: https:\/\/www.nads-sc.uiowa.edu\/dscna\/2005\/papers\/Measurement_Behavior_Performance_Driving_Simulation.pdf."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Evans, L., and Schwing, R.C. (1985). A critical view of driver behavior models: What do we know, what should we do?. Human Behavior and Traffic Safety, Springer.","DOI":"10.1007\/978-1-4613-2173-6"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Fridman, L., Ding, L., Jenik, B., and Reimer, B. (2019, January 16\u201317). Arguing machines: Human supervision of black box AI systems that make life-critical decisions. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, Long Beach, CA, USA.","DOI":"10.1109\/CVPRW.2019.00173"},{"key":"ref_44","unstructured":"Waymo-Research (2024, November 06). Waymo-Open-Dataset. GitHub. Available online: https:\/\/github.com\/waymo-research\/waymo-open-dataset."},{"key":"ref_45","unstructured":"Tesla (2024, November 06). Teslamotors. GitHub. Available online: https:\/\/github.com\/teslamotors."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Sivakumar, P., Neeraja Lakshmi, A., Angamuthu, A., Sandhya Devi, R.S., Vinoth Kumar, B., and Studener, S. (2022). Automotive Grade Linux. An open-source architecture for connected cars. Software Engineering for Automotive Systems, CRC Press.","DOI":"10.1201\/9781003269908-6"},{"key":"ref_47","unstructured":"comma.ai (2024, November 06). Openpilot in Simulator. GitHub. Available online: https:\/\/github.com\/commaai\/openpilot\/tree\/master\/tools\/sim."}],"container-title":["Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2218-6581\/13\/12\/169\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:37:02Z","timestamp":1760114222000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2218-6581\/13\/12\/169"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"references-count":47,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["robotics13120169"],"URL":"https:\/\/doi.org\/10.3390\/robotics13120169","relation":{},"ISSN":["2218-6581"],"issn-type":[{"value":"2218-6581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,21]]}}}