Non-driving Related Activities Research Articles

Non-Driving Related Activities Inside an Automated Vehicle Among Malaysia Passengers

The advancement of automotive technology has led to the development of automated vehicles. The trend of passengers performing non-driving-related activities during travel was expected to continue in the future of automated vehicles. It is essential to discover the type of activities that the users prefer to improve the interior design of an automated vehicle. Past studies show that every country has different preferred non-driving related activities. The main objective of this study is to collect data on preferred non-driving related activities, specifically by Malaysians, using online questionnaires. 293 respondents answered the questionnaires in six (6) months. As a result, the top three (3) non-driving related activities in Malaysia are listening to music, calling or texting, and interacting with others. In addition, the most preferred seating position as a passenger, the most suitable travel duration to perform non-driving related activities uninterrupted, and the preferred seating configuration of the automated vehicle were also discovered. The outcome of this study will add knowledge for designing better future automated vehicles suitable for Malaysian users.

Designing for Collaborative Non-Driving Related Activities in Future Cars: Fairness and Team Performance

With the gradual transition towards assisted and automated driving, the car will transform into a more social environment where passengers and drivers engage in Non-Driving-Related Activities (NDRA). To support collaboration among occupants in future vehicles, research suggests interactive systems controlled by several users at once. In this paper, we explore five concepts for the collaborative performance of NDRA with the use-case of music playlist creation. While prior work investigated the effect on social connectedness, we expand insights towards team performance and fairness. Results from a mixed-subject experiment (N=27) show that the concepts have major consequences on team performance and fairness. Certain concepts can promote or hinder coordination effectiveness and, in turn, impact intra-vehicular collaboration. Our observations also indicate that fairness is key to fostering social collaboration in AVs, while it does not naturally define a high team performance. Subsequently, we provide recommendations to guide future designs of collaborative NDRAs in vehicles.

Computer aided derivation of vehicle modules and functions from use cases in order to create user orientated vehicle interior concepts

Trends such as autonomous driving, non-driving related activities and digitalisation are contributing to a revolution in vehicle concept design. An aspect of this is the consideration of future use cases in shaping vehicle architectures. Future user scenarios can help identify relevant use cases, from which the user needs and system requirements can be derived. The derived requirements need to be matched to vehicle functions and architectural modules that can fulfil them. However, the optimal combination of functions and modules can be difficult to identify due to the numerous possibilities. The aim of this paper is to apply a matrix-based methodology that enables the systematic matching of requirements to vehicle functions and/or modules, as well as the identification of an ideal module/function combination for all the considered requirements. An example is presented that considers a requirement specification that has been derived from predetermined user needs. The requirements are matched to suitable functions/modules and the best possible combinations are determined using the proposed matrix-based methodology. Two optimal combinations are selected, one for a vehicle in the entry level segment and the other for a premium vehicle. The results indicate it is possible to determine an optimal combination for both vehicle segments considered, as well as the substantial influence the rating parameters have on the end result. Lastly, it is shown how the results can be applied by concept designers in order to draft tailored, user-orientated interior concepts.

A lightweight temporal attention-based convolution neural network for driver's activity recognition in edge

Low inference latency and accurate response to environment changes play a crucial role in the automated driving system, especially in the current Level 3 automated driving. Achieving the rapid and reliable recognition of driver's non-driving related activities (NDRAs) is important for designing an intelligent takeover strategy that ensures a safe and quick control transition. This paper proposes a novel lightweight temporal attention-based convolutional neural network (LTA-CNN) module dedicated to edge computing platforms, specifically for NDRAs recognition. This module effectively learns spatial and temporal representations at a relatively low computational cost. Its superiority has been demonstrated in an NDRA recognition dataset, achieving 81.01% classification accuracy and an 8.37% increase compared to the best result of the efficient network (MobileNet V3) found in the literature. The inference latency has been evaluated to demonstrate its effectiveness in real applications. The latest NVIDIA Jetson AGX Orin could complete one inference in only 63 ms.

Do males and females prefer different non-driving related activities during automated driving?

We investigated gender differences in the willingness to use travel time for Non-Driving Related Tasks (NDRs) in conditionally automated vehicles (SAE Level 3) using a questionnaire study among 8,412 car-drivers in eight European countries (Germany, Italy, Netherlands, Poland, Romania, Spain, Sweden, and the United Kingdom), as part of the European L3Pilot project. Participants’ responses to what activities they would like to perform while the automated driving is activated were investigated. Results reveal that females were more willing to engage in NDRTs than males for nine out of 12 investigated activities. This study informs about gender differences in engagement with NDRTs which will help in policy development and future interior vehicle design to ensure that all potential users can benefit from AVs.

A Temporal–Spatial Deep Learning Approach for Driver Distraction Detection Based on EEG Signals

Distracted driving has been recognized as a major challenge to traffic safety improvement. This article presents a novel driving distraction detection method that is based on a new deep network. Unlike traditional methods, the proposed method uses both temporal information and spatial information of electroencephalography (EEG) signals as model inputs. Convolutional techniques and gated recurrent units were adopted to map the relationship between drivers’ distraction status and EEG signals in the time domain. A driving simulation experiment was conducted to examine the effectiveness of the proposed method. Twenty-four healthy volunteers participated and three types of secondary tasks (i.e., cellphone operation task, clock task, and 2-back task) were used to induce distraction during driving. Drivers’ EEG responses were measured using a 32-channel electrode cap, and the EEG signals were preprocessed to remove artifacts and then split into short EEG sequences. The proposed deep-network-based distraction detection method was trained and tested on the collected EEG data. To evaluate its effectiveness, it was also compared with the networks using temporal or spatial information alone. The results showed that our proposed distraction detection method achieved an overall binary (distraction versus nondistraction) classification accuracy of 0.92. In terms of task-specific distraction detection, its accuracy was 0.88. Further analysis on the individual difference in detection performance showed that drivers’ EEG performance differed across individuals, which suggests that adaptive learning for each individual driver would be needed when developing in-vehicle distraction detection applications. Note to Practitioners—Driver distraction detection is crucial for safety enhancement to avoid crashes caused by nondriving-related activities, such as calling and texting while driving. Related previous studies mainly focus on detection by monitoring head and eye movement using computer vision technologies or by extracting indicators from driving performance measures for driver state inference. However, complex traffic environments (e.g., dynamically changing light distribution on driver’s face and nighttime driving with low illumination) strongly limit the effectiveness of computer vision technologies, and the driving performance characteristics may also be caused by factors other than distraction (e.g., fatigue). To solve these problems, this article seeks to develop a deep learning-based approach to map the unique relationship between driver distraction and the bioelectric electroencephalography (EEG) signals that are not affected by traffic environments. The proposed method can be integrated into the driver assistance systems and autonomous vehicles to deal with emergency situations that need drivers to handle. The timely detection of distraction by our method will significantly facilitate its practical applications in collision avoidance or danger mitigation in the handover process.

How to Display Vehicle Information to Users of Automated Vehicles When Conducting Non-Driving-Related Activities

Automated vehicles (AVs) are expected to enable users to engage in non-driving-related activities (NDRAs). However, users do not easily trust an automated vehicle which poses new challenges for automotive human-machine interfaces (HMIs). Over-presenting vehicle information can distract users from NDRAs, and under-presentation can impact trust and user experience (UX) negatively. To investigate how to best present vehicle information to foster users' trust and UX while performing NDRAs, we designed two in-vehicle HMI concepts: 1) A colored and animated light bar display around the windshield and 2) a windshield display interface presenting pictograms and numbers. Results from a simulator study ($N=18$) indicate that both concepts contribute to a high trust level and UX while not affecting the NDRA performance compared to the baseline of not showing vehicle information. In addition, the light bar provides better UX than the windshield display and is also preferred by users. With our findings, we contribute to the effective design of presenting vehicle information in automated vehicles.

Ghost on the Windshield: Employing a Virtual Human Character to Communicate Pedestrian Acknowledgement and Vehicle Intention

Pedestrians base their street-crossing decisions on vehicle-centric as well as driver-centric cues. In the future, however, drivers of autonomous vehicles will be preoccupied with non-driving related activities and will thus be unable to provide pedestrians with relevant communicative cues. External human–machine interfaces (eHMIs) hold promise for filling the expected communication gap by providing information about a vehicle’s situational awareness and intention. In this paper, we present an eHMI concept that employs a virtual human character (VHC) to communicate pedestrian acknowledgement and vehicle intention (non-yielding; cruising; yielding). Pedestrian acknowledgement is communicated via gaze direction while vehicle intention is communicated via facial expression. The effectiveness of the proposed anthropomorphic eHMI concept was evaluated in the context of a monitor-based laboratory experiment where the participants performed a crossing intention task (self-paced, two-alternative forced choice) and their accuracy in making appropriate street-crossing decisions was measured. In each trial, they were first presented with a 3D animated sequence of a VHC (male; female) that either looked directly at them or clearly to their right while producing either an emotional (smile; angry expression; surprised expression), a conversational (nod; head shake), or a neutral (neutral expression; cheek puff) facial expression. Then, the participants were asked to imagine they were pedestrians intending to cross a one-way street at a random uncontrolled location when they saw an autonomous vehicle equipped with the eHMI approaching from the right and indicate via mouse click whether they would cross the street in front of the oncoming vehicle or not. An implementation of the proposed concept where non-yielding intention is communicated via the VHC producing either an angry expression, a surprised expression, or a head shake; cruising intention is communicated via the VHC puffing its cheeks; and yielding intention is communicated via the VHC nodding, was shown to be highly effective in ensuring the safety of a single pedestrian or even two co-located pedestrians without compromising traffic flow in either case. The implications for the development of intuitive, culture-transcending eHMIs that can support multiple pedestrians in parallel are discussed.

Caught in the blind spot of a truck: A choice model on driver glance behavior towards cyclists at intersections

Vulnerable road users (VRUs) constitute an increasing proportion of the annual road fatalities across Europe. One of the crash types involved in these fatalities are blind spot crashes between trucks and bicyclists. Despite the presence of mandatory blind spot mirrors, truck drivers are often reported to have overlooked the presence of a bicyclist. This raises the question if and when truck drivers check their blind spot mirrors for the presence of bicyclists, and which factors contribute to such glance behavior. The current study presents the results of an analysis of naturalistic glance behavior by 39 truck drivers in 1,903 right-turning maneuvers at urban intersections, where in each maneuver there was a chance of crossing the path of a bicyclist. The descriptive analysis revealed that most often truck drivers did not cast a glance upon their blind spot mirrors as recommended by the examination guidelines. Furthermore, a choice model was developed with the main factors that have an impact on glance behavior. Drivers were more likely to glance with a priority regulation that allowed conflicts, with lower speed limits, with zebra crossings, without cyclist facilities, without a lead vehicle making the same maneuver, in presence of VRUs, without adverse sight conditions, in lower age groups, without certain non-driving related activities, when driving a truck with more direct vision on VRUs, and without a camera providing a view on the blind spot, and with less time between a standstill and starting the maneuver. Three factors did not significantly improve the choice model and were therefore left out, despite showing significant effects in bivariate tests: intersection layout (e.g., three vs. four legs), presence of advanced stopping lanes, and visual obstruction. Implications of the choice model are discussed for driver education (in terms of timely glances, reducing inattention, and hazard anticipation) and vehicle design (in terms of direct vision).

How to Keep Drivers Attentive during Level 2 Automation? Development and Evaluation of an HMI Concept Using Affective Elements and Message Framing

With Level 3 and 4 automated driving activated, users will be allowed to engage in a wide range of non-driving related activities (NDRAs). Although Level 2 automation can appear very similar to L3 and L4, drivers are required to always monitor the system. However, past research has found drivers neglect this obligation at least partly and instead engage in NDRAs. Since this behavior can have negative impacts on traffic safety, the goal of this work was to develop a human–machine interface (HMI) concept to motivate users to continue their supervision task. This work’s concept used message framing in connection with affective elements. Every three minutes, messages were displayed on the head-up display. To evaluate the affective message concept’s (AMC) effectiveness, we conducted a between-subject driving simulator study (baseline vs. advanced HMI) with 32 participants and 45 min of driving time with both L2 and L4 phases and a silent system malfunction. Results show the road attention ratio decreases and the NDRA engagement ratio increases over time only for baseline participants. Participants supported by the AMC did not show a change over time in monitoring behavior and NDRA engagement. However, no effect on the drivers’ reaction to the system failure became apparent. No effects on subjective workload and user experience were found. Additional research is needed to further investigate the safety implications and long-term effectiveness of the concept, as well as a driver-state-dependent design.

Why would people want to travel more with automated cars?

The use of automated vehicles (AVs) may enable drivers to focus on non-driving related activities while travelling and reduce the unwanted efforts of the driving task. This is expected to make using a car more attractive, or at least less unpleasant compared to manually driven vehicles. Consequently, the number and length of car trips may increase. The aim of this study was to identify the main contributors to travelling more by AV.We analysed the L3Pilot project’s pilot site questionnaire data from 359 respondents who had ridden in a conditionally automated car (SAE level 3) either as a driver or as a passenger. The questionnaire queried the respondents’ user experience with the automated driving function, current barriers of travelling by car, previous experience with advanced driving assistance systems, and general priorities in travelling. The answers to these questions were used to predict willingness to travel more or longer trips by AV, and to use AVs on currently undertaken trips. The most predictive subset of variables was identified using Bayesian cumulative ordinal regression with a shrinkage prior (regularised horseshoe).The current study found that conditionally automated cars have a substantial potential to increase travelling by car once they become available. Willingness to perform leisure activities during automated driving, experienced usefulness of the system, and unmet travel needs, which AVs could address by making travelling easier, were the main contributors to expecting to travel more by AV. For using AVs on current trips, leisure activities, trust in AVs, satisfaction with the system, and traffic jams as barriers to current car use were important contributors. In other words, perceived usefulness motivated travelling more by AV and using AVs on current trips, but also other factors were important for using them on current trips. This suggests that one way to limit the growth of traffic with private AVs could be to address currently unmet travel needs with alternative, more sustainable travel modes.

How users of automated vehicles benefit from predictive ambient light displays

With the introduction of Level 3 and 4 automated driving, the engagement in a variety of non-driving related activities (NDRAs) will become legal. Previous research has shown that users desire information about the remaining time in automated driving mode and system status information to plan and terminate their activity engagement. In past studies, however, the positive effect of this additional information was realized when it was integrated in or displayed close by the NDRA. As future activities and corresponding items will be diverse, a device-independent and non-interruptive way of communication is required to continuously keep the user informed, thus avoiding negative effects on driver comfort and safety. With a set of two driving simulator studies, we have investigated the effectiveness of ambient light display (ALD) concepts communicating remaining time and system status when engaged in visually distracting NDRAs. In the first study with 21 participants, a traffic light color-coded ALD concept (LED stripe positioned at the bottom of the windshield) was compared to a baseline concept in two subsequent drives. Subjects were asked to rate usability, workload, trust, and their use of travel time after each drive. Furthermore, gaze data and NDRA disengagement timing was analyzed. The ALD with three discrete time steps led to improved usability ratings and lower workload levels compared to the baseline interface without any ALD. No significant effects on trust, attention ratio, travel time evaluation, and NDRA continuation were found, but a vast majority favored the ALD. Due to this positive evaluation, the traffic light ALD concept was subsequently improved and compared to an elapsing concept in a subsequent study with 32 participants. In addition to the first study, the focus was on the intuitiveness of the developed concepts. In a similar setting, results revealed no significant differences between the ALD concepts in subjective ratings (workload, usability, trust, travel time ratings), but advantages of the traffic light concept can be found in terms of its intuitiveness and the level of support experienced.

Human machine interface design for continuous support of mode awareness during automated driving: An online simulation

In the transition towards higher levels of vehicle automation, one of the key concerns with regards to human factors is to avoid mode confusion, when drivers misinterpret the driving mode and therewith misjudge their own tasks and responsibility. To enhance mode awareness, a clear human centered Human Machine Interface (HMI) is essential. The HMI should support the driver tasks of both supervising the driving environment when needed and self-regulating their non-driving related activities (NDRAs). Such support may be provided by either presenting continuous information on automation reliability, from which the driver needs to infer what task is required, or by presenting continuous information on the currently required driving task and allowed NDRA directly. Additionally, it can be valuable to provide continuous information to support anticipation of upcoming changes in the automation mode and its associated reliability or required and allowed driver task(s). Information that could support anticipation includes the available time until a change in mode (i.e. time budget), information on the upcoming mode, and reasons for changing to the upcoming mode. The current work investigates the effects of communicating this potentially valuable information through HMI design. Participants received information from an HMI during simulated drives in a simulated car presented online (using Microsoft Teams) with an experimenter virtually accompanying and guiding each session. The HMI either communicated on automation reliability or on the driver task, and either included information supporting anticipation or did not include such information. Participants were thinking aloud during the simulated drives and reported on their experience and preferences afterwards. Anticipatory information supported understanding about upcoming changes without causing information overload or overreliance. Moreover, anticipatory information and information on automation reliability, and especially a combination of the two, best supported understandability and usability. Recommendations are provided for future work on facilitating supervision and NDRA self-regulation during automated driving through HMI design.

How the initial level of trust in automated driving impacts drivers’ behaviour and early trust construction

Trust in Automation is known to influence human-automation interaction and user behaviour. In the Automated Driving (AD) context, studies showed the impact of drivers’ Trust in Automated Driving (TiAD), and linked it with, e.g., difference in environment monitoring or driver’s behaviour. This study investigated the influence of driver’s initial level of TiAD on driver’s behaviour and early trust construction during Highly Automated Driving (HAD). Forty drivers participated in a driving simulator study. Based on a trust questionnaire, participants were divided in two groups according to their initial level of TiAD: high (Trustful) vs. low (Distrustful). Declared level of trust, gaze behaviour and Non-Driving-Related Activities (NDRA) engagement were compared between the two groups over time. Results showed that Trustful drivers engaged more in NDRA and spent less time monitoring the road compared to Distrustful drivers. However, an increase in trust was observed in both groups. These results suggest that initial level of TiAD impact drivers’ behaviour and further trust evolution.

Drivers' Performance in Non-critical Take-Overs From an Automated Driving System-An On-Road Study.

The objective of this semi-controlled study was to investigate drivers' performance when resuming control from an Automated Driving System (ADS), simulated through the Wizard of Oz method, in real traffic. Research on take-overs has primarily focused on urgent scenarios. This article aims to shift the focus to non-critical take-overs from a system operating in congested traffic situations. Twenty drivers drove a selected route in rush-hour traffic in the San Francisco Bay Area, CA, USA. During the drive, the ADS became available when predetermined availability conditions were fulfilled. When the system was active, the drivers were free to engage in non-driving related activities. The results show that drivers' transition time goes down with exposure, making it reasonable to assume that some experience is required to regain control with comfort and ease. The novel analysis of after-effects of automated driving on manual driving performance implies that the after-effects were close to negligible. Observational data indicate that, with exposure, a majority of the participants started to engage in non-driving related activities to some extent, but it is unclear how the activities influenced the take-over performance. The results indicate that drivers need repeated exposure to take-overs to be able to fully resume manual control with ease. Take-over signals (e.g., visuals, sounds, and haptics) should be carefully designed to avoid startle effects and the human-machine interface should provide clear guidance on the required take-over actions.

Towards Personalized 3D Augmented Reality Windshield Displays in the Context of Automated Driving

As vehicle automation advances, drivers of automated vehicles become more disengaged from the primary driving task. Windshield displays provide a large screen space supporting drivers in non-driving related activities. This article presents user preferences as well as task and safety issues for 3D augmented reality windshield displays in automated driving. Participants of a user study (n = 24) customized two modes of content presentation (multiple content-specific windows vs. one main window), and could freely adjust visual parameters for these content windows using a simulated “ideal” windshield display in a virtual reality driving simulator. We found that user preferences differ with respect to contextual aspects. Additionally, using one main content window resulted in better task performance and lower take-over times, but the subjective user experience was higher for the multi-window user interface. These findings help automotive interface designers to improve experiences in automated vehicles.

자율주행 시 차량 시트의 햅틱 피드백 감지

초록·키워드 목차 오류제보하기 Objective: The goal of this research is to study the driver"s acceptable level of vibration intensity and duration as haptic feedback during conditional automated driving.Background: Gradually, the driving of a vehicle is being automated, which frees the driver from driving. As various activities become possible as non-driving related activities (NDRAs) in the vehicle, driver"s attention level gets lowered and accordingly, visual, auditory, and tactile-based feedback must be properly provided. Unlike visual and auditory information, which can interfere with driver"s concentration and confuse situational awareness due to information from many systems, tactile feedback is presented as an important feedback method in a way that can improve the efficiency of information delivery about safety. However, although there are various situations in which the driver is informed of the change of control right in the NDRT (Non-Driving Related Task) situation, there is still a lack of research about the intensity and duration as haptic feedback.Method: By establishing an experimental environment similar to that of a vehicle, the vibration actuators were placed on the seat in a 2 × 2 arrangement on the seat pan and seat back. The vibration was implemented using Arduino equipment and PWM control. The experiment was conducted by combining the independent variables, the intensity of vibration (1~5V), and the level of stimulation time(1.5s, 2.5s, 3.5s, 4.5s). Dependent variables, Error rate and Preference were selected, and Preference for the seat vibration stimulus position (1. Seat back & pan, 2. Seat back, 3. Seat pan) was investigated. Preferences were all collected on a 7-point likert scale.Results: Through ANOVA analysis, there were significant differences in the intensity of vibration, stimulation time, and the interaction between the two variables, and there was no significant difference in gender or age. Subjects were able to identify vibrations from 3V, and in the case of stimulation time of 3.5s was the most preferred at 3V and 4V, which recognize most vibrations, and 1.5s and 4.5s had lower preferences. At 5V, 2.5s was the most preferred, and from 3.5s the preference decreased sharply. In the case of the vibration stimulation position of the seat, the seat back had the highest preference, and in the case of the seat pan, the preference was very lower than that of the seat back and seat back & pan.Conclusion: In this study, the minimum level for recognizing the vibration stimulation of the haptic feedback in the vehicle seat and the optimal stimulation time according to the vibration intensity was investigated through experiments, and the range that could accommodate the haptic feedback was derived.Application: Based on the results of the vibration stimulation level and stimulation time level for the haptic feedback of the vehicle seat in this study, it can be used as a reference index when designing the haptic feedback of the vehicle in the future. #Haptic feedback in the vehicle seat #Vibrator locations of the vehicle seat #Vibration recognition 1. Introduction2. Method3. Results4. Discussion5. ConclusionReferences

How Should Automated Vehicles Communicate Critical Situations?

Passengers of automated vehicles will likely engage in non-driving related activities like reading and, therefore, be disengaged from the driving task. However, especially in critical situations such as unexpected pedestrian crossings, it can be assumed that passengers request information about the vehicle's intention and an explanation. Some concepts were proposed for such communication from the automated vehicle to the passenger. However, results are not comparable due to varying information content and scenarios. We present a comparative study in Virtual Reality (N=20) of four visualization concepts and a baseline with Augmented Reality, a Head-Up Display, or Lightbands. We found that all concepts were rated reasonable and necessary and increased trust, perceived safety, perceived intelligence, and acceptance compared to no visualization. However, when visualizations were compared, there were hardly any significant differences between them.

First encounter effects in testing of highly automated vehicles during two experimental occasions – The need for recurrent testing

Abstract To explore driver behavior in highly automated vehicles (HAVs), independent researchers are mainly conducting short experiments. This limits the ability to explore drivers’ behavioral changes over time, which is crucial when research has the intention to reveal human behavior beyond the first-time use. The current paper shows the methodological importance of repeated testing in experience and behavior related studies of HAVs. The study combined quantitative and qualitative data to capture effects of repeated interaction between drivers and HAVs. Each driver ( n = 8 n=8 ) participated in the experiment on two different occasions (∼90 minutes) with one-week interval. On both occasions, the drivers traveled approximately 40 km on a rural road at AstaZero proving grounds in Sweden and encountered various traffic situations. The participants could use automated driving (SAE level 4) or choose to drive manually. Examples of data collected include gaze behavior, perceived safety, as well as interviews and questionnaires capturing general impressions, trust and acceptance. The analysis shows that habituation effects were attenuated over time. The drivers went from being exhilarated on the first occasion, to a more neutral behavior on the second occasion. Furthermore, there were smaller variations in drivers’ self-assessed perceived safety on the second occasion, and drivers were faster to engage in non-driving related activities and become relaxed (e. g., they spent more time glancing off road and could focus more on non-driving related activities such as reading). These findings suggest that exposing drivers to HAVs on two (or more) successive occasions may provide more informative and realistic insights into driver behavior and experience as compared to only one occasion. Repeating an experiment on several occasions is of course a balance between the cost and added value, and future research should investigate in more detail which studies need to be repeated on several occasions and to what extent.

The Decline of User Experience in Transition from Automated Driving to Manual Driving

Automated driving technologies are rapidly being developed. However, until vehicles are fully automated, the control of the dynamic driving task will be shifted between the driver and automated driving system. This paper aims to explore how transitions from automated driving to manual driving affect user experience and how that experience correlates to take-over performance. In the study 20 participants experienced using an automated driving system during rush-hour traffic in the San Francisco Bay Area, CA, USA. The automated driving system was available in congested traffic situations and when active, the participants could engage in non-driving related activities. The participants were interviewed afterwards regarding their experience of the transitions. The findings show that most of the participants experienced the transition from automated driving to manual driving as negative. Their user experience seems to be shaped by several reasons that differ in temporality and are derived from different phases during the transition process. The results regarding correlation between participants’ experience and take-over performance are inconclusive, but some trends were identified. The study highlights the need for new design solutions that do not only improve drivers’ take-over performance, but also enhance user experience during take-over requests from automated to manual driving.