PREDICTOR - interactive open-source tool - prediction of take-over response timing in semi-automated driving

Sep 18, 2026

This paper presents PREDICTOR (PREDICting Take-Over Response time), an interactive open-source research software tool to predict when key stages occur during transition of control (take-over) in semi-automated driving. While prior research focused on factors affecting minimum take-over time, the tool addresses how factors influence specific stages. Using an interruption-handling stage framework linked to a database of earlier studies, PREDICTOR simulates and visualizes reaction-time distributions, quantifies outliers, and supports scenario exploration and user-defined dependent variables.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages45

Reading Time1 h 53 min

AccessFree to download

Abstract

Keywords

1 Introduction

Background on semi-automated vehicles and transition of control

Take-over request and prior meta-review findings

1 Janssen, C.P., Praetorius, L., Borst, J.P. (in press 2024) . PREDICTOR: a tool to predict the 2 timing of the take-over response process in semi-automated driving. Transportation Research 3 Interdisciplinary Perspectives 4 5 6 Notice: 7 • This article is a pre-print, and is provided for non-commercial use only. Please cite the 8 original source when referring to it. 9 • This article may not exactly replicate the final version published in Transportation Research 10 Interdisciplinary Perspectives. It is not the copy of record. 11 • You can find the journal website here: 12 [https://www.sciencedirect.com/journal/transportation-research-interdisciplinary-perspectives](https://www.sciencedirect.com/journal/transportation-research-interdisciplinary-perspectives)[ ](https://www.sciencedirect.com/journal/transportation-research-interdisciplinary-perspectives)13 14 15 16 PREDICTOR: a tool to predict the timing of the take-over 17 response process in semi-automated driving 18 Christian P. Janssen 1* 19 Leonard Praetorius2 20 Jelmer P. Borst2 21 22 1 : 23 Experimental Psychology & Helmholtz Institute 24 Utrecht University 25 Heidelberglaan 1 , room H0.52 26 3584 CS Utrecht 27 The Netherlands 28 *: Corresponding author: [c.p.janssen@uu.nl](c.p.janssen@uu.nl)[ ](c.p.janssen@uu.nl)29 30 2: 31 Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence 32 University of Groningen 33 Bernoulliborg, room 320 34 Nijenborgh 9 35 9747 AG Groningen 36 The Netherlands 37 38 39 Declarations of interest: none 40 41 Funding acknowledgement: This research did not receive any specific grant from funding 42 agencies in the public, commercial, or not-for-profit sectors. 43 44 Credit statement: 45 Christian Janssen: Conceptualization, Formal analysis, Investigation, Methodology, Project 46 administration, Supervision, Visualization, Writing – original draft, Writing – review and 47 editing. Leonard Praetorius: Data curation, Formal analysis, Investigation, Methodology, 48 Software, Visualization, Writing – original draft, Writing – review and editing. Jelmer 49 Borst: Methodology, Software, Supervision, Writing – review and editing. 50 51 ABSTRACT 52 This paper presents PREDICTOR (PREDICting Take-Over Response time): an interactive 53 open-source research software tool to predict the timing of various stages of a transition of 54 control, or take-over, in semi-automated driving. Although previous work has investigated 55 extensively what factors affect the minimum time needed for a successful take-over by the 56 driver, less is known about how specific stages within the take-over process are affected by 57 those factors. PREDICTOR applies a theoretical framework that describes the take-over 58 process as interruption handling through a series of stages. It then ties this theory to a 59 database that summarizes results from previous take-over studies. PREDICTOR can be used 60 to interactively predict through simulation how specific human factors (e.g., alert modality, 61 alert onset time) impact four distinct stages ofthe take-over response process. The tool 62 simulates and visualizes expected reaction time distributions for each stage of the take-over 63 process. The use of distributions also highlights the likelihood of an accident – as long 64 responses (“outliers”) are quantifiable. Moreover, it can help understand at which stage 65 drivers might take relatively longer or shorter, and which stages are most impacted by a 66 specific factor (e.g., alert modality) . PREDICTOR also allows users to add their own data, 67 and to define their own dependent variables for analysis. As a tool that allows exploration of 68 various scenarios, PREDICTOR can aid in the prediction and analysis of potential future 69 accidents. 70 71 72 Keyword: Transitions of Control; Take-over Request; Cognitive Model; Interruption 73

FAQs

What is PREDICTOR designed to do in semi-automated driving?

PREDICTOR predicts the timing of stages within the transition-of-control (take-over) process and supports interactive simulation of expected reaction-time distributions.

How does PREDICTOR model the take-over process?

It applies a theoretical framework that treats take-over as interruption handling through a series of stages, then links this theory to a database summarizing results from prior take-over studies.

What kinds of factors can PREDICTOR evaluate?

It can model how specific human factors (e.g., alert modality and alert onset time) impact distinct stages of the take-over response process.

Sep 18, 2026

Uploaded by Maya Linwood