Browse AI research papers authored by Martin Baumann. Found 5 papers.

arXiv:2508.13699v1 Announce Type: new Abstract: As autonomous robots become more common in public spaces, spontaneous encounters with laypersons are more frequent. For this, robots need to be equipped with communication strategies that enhance momentary transparency and reduce the probability of critical situations. Adapting these robotic strategies requires consideration of robot movements, environmental conditions, and user characteristics and states. While numerous studies have investigated the impact of distraction on pedestrians' movement behavior, limited research has examined this behavior in the presence of autonomous robots. This research addresses the impact of robot type and robot movement pattern on distracted and undistracted pedestrians' movement behavior. In a field setting, unaware pedestrians were videotaped while moving past two working, autonomous cleaning robots. Out of N=498 observed pedestrians, approximately 8% were distracted by smartphones. Distracted and undistracted pedestrians did not exhibit significant differences in their movement behaviors around the robots. Instead, both the larger sweeping robot and the offset rectangular movement pattern significantly increased the number of lateral adaptations compared to the smaller cleaning robot and the circular movement pattern. The offset rectangular movement pattern also led to significantly more close lateral adaptations. Depending on the robot type, the movement patterns led to differences in the distances of lateral adaptations. The study provides initial insights into pedestrian movement behavior around an autonomous cleaning robot in public spaces, contributing to the growing field of HRI research.

## Overview

- **Autonomous robots** are increasingly present in public spaces
- The study examines pedestrian behavior around cleaning robots
- Researchers investigated how robot type and movement affect pedestrian interactions
- Smartphone distraction was a key variable in the research
- Nearly 8% of observed pedestrians were using smartphones during encounters

## Plain English Explanation

Imagine walking through a public space and suddenly encountering an autonomous [cleaning robot](https://aimodels.fyi/papers/arxiv/leveraging-sidewalk-robots-walkability-related-analyses). Most people might not even notice these machines, but researchers wanted to understand exactly how humans naturally respond to their presence.

The research focused on how different robots and their movement patterns influence pedestrian behavior. It's like studying how people unconsciously adjust their walking when passing a moving object. The team set up a field experiment to capture these subtle interactions, tracking how people move around robots in real-world environments.

## Key Findings

The study revealed several fascinating insights:

- **Distraction Didn't Matter**: Whether pedestrians were using smartphones or not, their movement around robots remained surprisingly consistent
- **Robot Size Impact**: Larger robots prompted more significant lateral movement adaptations
- **Movement Patterns**: Rectangular movement patterns caused more noticeable pedestrian adjustments compared to circular patterns
- **Close Interactions**: Offset rectangular movements led to more frequent close lateral adaptations

## Technical Explanation

Researchers conducted a field study observing **498 pedestrians** interacting with two autonomous [cleaning robots](https://aimodels.fyi/papers/arxiv/pedestrians-robots-novel-dataset-learning-distinct-social). The experiment tracked pedestrian movement patterns, focusing on:

- Robot type variations
- Different movement patterns (circular vs. rectangular)
- Pedestrian distraction levels
- Lateral adaptation distances

By videotaping unaware pedestrians, the team could objectively analyze natural interaction behaviors without introducing experimental bias.

## Critical Analysis

While the study provides valuable insights, several limitations exist:

- **Limited Sample Size**: 498 pedestrians might not represent global behavioral patterns
- **Single Location Context**: Results might vary in different environments
- **Robot Types**: Only cleaning robots were studied, potentially limiting generalizability
- **Cultural Variations**: No exploration of potential cross-cultural differences in [pedestrian robot interactions](https://aimodels.fyi/papers/arxiv/cross-cultural-analysis-pedestrian-group-behaviour-influence)

## Conclusion

This research contributes crucial understanding to [human-robot interaction](https://aimodels.fyi/papers/arxiv/assessing-pedestrian-behavior-around-autonomous-cleaning-robots) in public spaces. By revealing how pedestrians naturally adapt to autonomous robots, the study provides foundational knowledge for designing more intuitive and socially integrated robotic systems.

The findings suggest that robot designers should consider movement patterns and size when developing machines intended for public spaces, as these factors significantly influence human comfort and interaction.

Assessing Pedestrian Behavior Around Autonomous Cleaning Robots in Public Spaces: Findings from a Field Observation

The technological properties of a system delivering simulation experience are a crucial dimension of immersion. To create a sense of presence and reproduce drivers behaviour as realistically as possible, we need reliable driving simulators that allow drivers to become highly immersed. This study investigates the impact of a system immersion of a driving simulator on the drivers' brain activity while operating a conditionally automated vehicle. Nineteen participants drove approximately 40 minutes while their brain activity was recorded using electroencephalography (EEG). We found a significant effect of the system immersion in the occipital and parietal areas, primarily in the high-Beta bandwidth. No effect was found in the Theta, Alpha, and low-Beta bandwidths. These findings suggest that the system immersion might influence the drivers' physiological arousal, consequently influencing their cognitive and emotional processes.

## Overview

- This study investigates the impact of a driving simulator's system immersion on the brain activity of drivers operating a conditionally automated vehicle.
- The researchers used electroencephalography (EEG) to measure the brain activity of 19 participants while they drove for approximately 40 minutes in the simulator.
- The study found significant effects of system immersion in the occipital and parietal areas of the brain, primarily in the high-Beta bandwidth, suggesting that system immersion may influence the drivers' physiological arousal and cognitive/emotional processes.

## Plain English Explanation

The researchers wanted to understand how the level of immersion in a driving simulator affects the brain activity of drivers using a partially self-driving car. To do this, they had 19 people drive in a simulator for around 40 minutes while their brain waves were measured using EEG technology.

The key finding was that the level of immersion in the simulator seemed to influence the drivers' brain activity in certain areas, particularly in the high-Beta frequency range. This suggests that a more immersive simulator experience may impact the drivers' physiological arousal, as well as their cognitive and emotional processes, compared to a less immersive setup.

In other words, the way the driving simulator is designed and how realistic it feels to the user could potentially affect how the driver's brain responds while operating a partially automated vehicle. This is an important consideration for creating driving simulators that can accurately reproduce real-world driving behavior and experiences.

## Technical Explanation

The researchers investigated the impact of the [system immersion](https://aimodels.fyi/papers/arxiv/human-machine-interface-evaluation-using-eeg-driving) of a driving simulator on the brain activity of drivers operating a [conditionally automated vehicle](https://aimodels.fyi/papers/arxiv/fatigue-mental-underload-further-pronounced-l3-conditionally). Nineteen participants drove in the simulator for approximately 40 minutes while their brain activity was recorded using electroencephalography (EEG).

The results showed a significant effect of system immersion in the occipital and parietal areas of the brain, primarily in the high-Beta bandwidth. No effects were found in the Theta, Alpha, and low-Beta bandwidths. These findings suggest that the [system immersion](https://aimodels.fyi/papers/arxiv/quantitative-evaluation-drivers-situation-awareness-virtual-driving) of the driving simulator may influence the drivers' physiological arousal, consequently affecting their cognitive and emotional processes.

## Critical Analysis

The study provides valuable insights into how the design and immersiveness of a driving simulator can impact the brain activity of drivers using partially automated vehicles. However, the researchers acknowledge that further research is needed to [explore the influence of driving context](https://aimodels.fyi/papers/arxiv/exploring-influence-driving-context-lateral-driving-style) on driver behavior and brain activity.

Additionally, the study's sample size was relatively small, and the experiment was conducted in a controlled laboratory setting. It would be beneficial to replicate the study with a larger and more diverse sample, as well as in more natural driving environments, to [assess the workload and cognitive demands](https://aimodels.fyi/papers/arxiv/workload-assessment-human-machine-interface-simulator-study) placed on drivers in real-world scenarios.

## Conclusion

This study provides evidence that the level of immersion in a driving simulator can influence the brain activity of drivers using a conditionally automated vehicle. The findings suggest that the design of driving simulators should consider the impact on physiological arousal, cognitive processing, and emotional responses to ensure that the simulated experience accurately reflects real-world driving behavior. Further research is needed to fully understand the complex relationship between simulator design, driver cognition, and the use of partially autonomous vehicle technologies.

System Immersion of a Driving Simulator Affects the Oscillatory Brain Activity

Human-machine Interface (HMI) is critical for safety during automated driving, as it serves as the only media between the automated system and human users. To enable a transparent HMI, we first need to know how to evaluate it. However, most of the assessment methods used for HMI designs are subjective and thus not efficient. To bridge the gap, an objective and standardized HMI assessment method is needed, and the first step is to find an objective method for workload measurement for this context. In this study, two psychophysiological measures, electrocardiography (ECG) and electrodermal activity (EDA), were evaluated for their effectiveness in finding differences in mental workload among different HMI designs in a simulator study. Three HMI designs were developed and used. Results showed that both workload measures were able to identify significant differences in objective mental workload when interacting with in-vehicle HMIs. As a first step toward a standardized assessment method, the results could be used as a firm ground for future studies. Marie Sk{l}odowska-Curie Actions; Innovative Training Network (ITN); SHAPE-IT; Grant number 860410; Publication date: [29 Sep 2023]; DOI: [10.54941/ahfe1004172]

## Overview

* This paper explores the use of psychophysiological measures, such as electroencephalography (EEG) and electrocardiography (ECG), to assess the cognitive workload of human-machine interface (HMI) tasks in a driving simulator. 

* The researchers aimed to develop a reliable method for evaluating the cognitive demands of HMI systems, which is crucial for ensuring safety and user experience in human-machine interactions.

## Plain English Explanation

The paper investigates how well we can measure the mental effort required for people to use different types of human-machine interfaces, such as those found in cars. The researchers used special sensors to track brain activity (EEG) and heart rate (ECG) while people performed tasks in a driving simulator. 

The goal was to find reliable ways to assess the cognitive workload, or mental strain, that these interfaces place on users. This is important because we want to design interfaces that are easy and safe for people to use, without overwhelming them. By understanding the mental demands of different interface designs, we can improve the overall interaction between humans and machines.

## Technical Explanation

The paper describes an experiment that used a driving simulator to evaluate the cognitive workload associated with various human-machine interface (HMI) tasks. The researchers collected electroencephalography (EEG) and electrocardiography (ECG) data from participants as they performed different interface-related activities while driving in the simulator.

The experiment was designed to simulate real-world driving conditions and assess how the cognitive demands of HMI tasks can impact driving performance and safety. The researchers analyzed the physiological data to identify patterns that could be used to reliably measure the mental workload imposed by the HMI systems.

The findings provide insights into the cognitive processes involved in interacting with in-vehicle technologies and offer a framework for evaluating the usability and safety of HMI designs. This research contributes to the growing body of literature on [adaptive human-swarm interaction based workload measurement](https://aimodels.fyi/papers/arxiv/adaptive-human-swarm-interaction-based-workload-measurement) and the use of [wearable devices for physiological signal monitoring and assessment](https://aimodels.fyi/papers/arxiv/wearable-device-based-physiological-signal-monitoring-assessment).

## Critical Analysis

The paper provides a comprehensive and well-designed study that leverages psychophysiological measures to assess the cognitive workload of HMI tasks in a driving simulator. However, the authors acknowledge several limitations and areas for further research.

One limitation is that the experiment was conducted in a simulated environment, which may not fully capture the complexity and demands of real-world driving. Additionally, the study focused on a limited set of HMI tasks, and the findings may not generalize to a wider range of interface designs or use cases.

The authors also suggest that future research should explore the relationship between cognitive control, mental workload, and multitasking, as these factors can significantly impact human-machine interactions. This could build on existing work in [cognitive control and mental workload in multitasking](https://aimodels.fyi/papers/arxiv/cognitive-control-mental-workload-multitasking).

Furthermore, the paper highlights the need for more research on the [automatic classification of subjective time perception using multimodal data](https://aimodels.fyi/papers/arxiv/automatic-classification-subjective-time-perception-using-multi), as this can provide additional insights into the cognitive processes involved in HMI tasks.

## Conclusion

This paper presents a comprehensive study that leverages psychophysiological measures to assess the cognitive workload associated with human-machine interface (HMI) tasks in a driving simulator. The findings provide valuable insights into the cognitive demands of interacting with in-vehicle technologies and offer a framework for evaluating the usability and safety of HMI designs.

The research contributes to the ongoing efforts to develop reliable methods for measuring and optimizing the cognitive workload in human-machine interactions, which is crucial for ensuring the safety and user experience of emerging technologies. The insights from this study can inform the design of more intuitive and user-friendly interfaces, ultimately enhancing the overall interaction between humans and machines.

Workload Assessment of Human-Machine Interface: A Simulator Study with Psychophysiological Measures

Manipulating MW in driving simulator studies without the need to introduce a non-driving-related task remains challenging. This study aims to empirically evaluate the modified speed regulation n-back task, a tool to manipulate drivers' MW. Our experiment involved 23 participants who experienced a 0-back and 2-back driving condition, with task-irrelevant novel environmental sounds used to elicit P3a event-related potentials. Results indicate that the 2-back condition was perceived as more demanding, evidenced by higher NASA-TLX scores (overall score, mental and temporal demand, effort, frustration). The mean P3a amplitude was diminished during the 2-back condition compared to the 0-back condition, suggesting that drivers experienced higher MW and had fewer resources available to process the novel environmental sounds. This study provides empirical evidence indicating that the speed regulation n-back task could be a valid, effective, and reproducible method to manipulate MW in driving research.

## Overview

- This paper examines the impact of the Speed Regulation N-Back Task on drivers' mental workload, using NASA-TLX (Task Load Index) and Auditory P3a measurements.
- The study aims to manipulate and evaluate drivers' mental workload in a driving simulator environment.
- The researchers investigate how the Speed Regulation N-Back Task, which requires drivers to regulate their speed while performing a memory task, affects their cognitive and physiological responses.

## Plain English Explanation

The study looks at how a specific driving task, called the Speed Regulation N-Back Task, impacts a driver's mental workload. The N-Back task involves remembering a series of numbers or letters and trying to match them to what was presented a certain number of steps back. 

In this experiment, the researchers had drivers perform the N-Back task while also trying to regulate their driving speed. They measured the drivers' mental workload using two different methods: the NASA-TLX questionnaire, which asks people to rate different aspects of the task's difficulty, and the Auditory P3a, which is a brainwave response that indicates how much attention the driver is paying to something.

The goal was to see how this combined speed regulation and memory task affects the driver's cognitive and physical responses, which could help understand how different types of in-vehicle tasks impact a driver's mental resources and ability to safely operate a vehicle.

## Technical Explanation

The researchers designed an experiment to manipulate and evaluate drivers' mental workload using the Speed Regulation N-Back Task in a driving simulator environment. The task required participants to regulate their driving speed while also performing an N-Back memory task, which involved comparing the current stimulus to one presented a certain number of steps prior.

The study used two measures to assess mental workload: the NASA-TLX self-report questionnaire and the Auditory P3a event-related potential (ERP) component. The NASA-TLX assessed subjective mental workload across six dimensions, while the Auditory P3a measured participants' attention allocation to auditory stimuli presented during the driving task.

Participants completed the Speed Regulation N-Back Task in the driving simulator under different levels of task difficulty (0-back, 1-back, 2-back). The researchers analyzed the NASA-TLX ratings and Auditory P3a responses to understand how the cognitive demands of the task impacted the drivers' mental workload.

## Critical Analysis

The study provides valuable insights into how complex in-vehicle tasks can affect a driver's mental resources and ability to safely operate a vehicle. By combining the Speed Regulation and N-Back tasks, the researchers were able to systematically manipulate and measure drivers' mental workload using both subjective and objective metrics.

However, the study is limited to a driving simulator environment, which may not fully capture the cognitive and physiological demands of real-world driving. Additionally, the sample size was relatively small, and the study did not investigate potential individual differences in how drivers respond to such tasks.

Future research could explore the impact of the Speed Regulation N-Back Task in more realistic driving scenarios, as well as examine how driver characteristics, such as age or experience, might modulate the effects on mental workload. Incorporating additional physiological measures, such as heart rate or eye-tracking, could also provide a more comprehensive understanding of the drivers' cognitive and attentional states.

## Conclusion

This study demonstrates the value of using a neuroergonomic approach to evaluate the impact of in-vehicle tasks on drivers' mental workload. By combining the Speed Regulation and N-Back tasks, the researchers were able to manipulate and assess the cognitive demands placed on drivers using both subjective and objective measures.

The findings suggest that complex tasks that require simultaneous speed regulation and memory processing can significantly increase a driver's mental workload, potentially compromising their ability to safely operate a vehicle. This has important implications for the design of in-vehicle technologies and the need to carefully consider the cognitive demands placed on drivers to support safe and efficient driving.

Manipulating Drivers' Mental Workload: Neuroergonomic Evaluation of the Speed Regulation N-Back Task Using NASA-TLX and Auditory P3a

Drivers' role changes with increasing automation from the primary driver to a system supervisor. This study investigates how supervising an SAE L2 and L3 automated vehicle (AV) affects drivers' mental workload and sleepiness compared to manual driving. Using an AV prototype on a test track, the oscillatory brain activity of 23 adult participants was recorded during L2, L3, and manual driving. Results showed decreased mental workload and increased sleepiness in L3 drives compared to L2 and manual drives, indicated by self-report scales and changes in the frontal alpha and theta power spectral density. These findings suggest that fatigue and mental underload are significant issues in L3 driving and should be considered when designing future AV interfaces.

## Overview

- This paper examines the effects of conditional automation (Level 3 autonomy) on driver fatigue and mental underload during a test track experiment.
- The researchers used electroencephalography (EEG) to measure changes in brain activity as drivers navigated the test track in manual and automated driving modes.
- The results suggest that fatigue and mental underload are more pronounced in conditional automation compared to manual driving, highlighting the need for effective countermeasures.

## Plain English Explanation

The paper investigates how a certain level of automated driving, known as "conditional automation" or Level 3, can impact a driver's mental state and level of fatigue. In this type of automation, the car can handle some driving tasks on its own, but the driver must still be ready to take back control at any moment.

The researchers ran an experiment where they had drivers navigate a test track, both in manual driving mode and in the conditional automation mode. They used EEG, which measures electrical activity in the brain, to see how the drivers' brains responded in these different conditions.

The key finding is that drivers experienced more fatigue and mental underload (a state of boredom or lack of mental stimulation) when using the conditional automation compared to manual driving. This suggests that even though the car is handling some of the driving, the driver still has to remain vigilant and ready to intervene, which can be mentally draining over time.

The implication is that as we move towards higher levels of automated driving, we'll need to find ways to keep drivers engaged and alert, so they don't become overly fatigued or mentally checked out. This could involve better interface designs, additional tasks to keep the driver's mind active, or ways to detect when the driver is starting to experience fatigue and provide timely warnings or intervention.

## Technical Explanation

The paper presents an [EEG experiment](https://aimodels.fyi/papers/arxiv/manipulating-drivers-mental-workload-neuroergonomic-evaluation-speed) conducted on a test track to evaluate the effects of [Level 3 conditional automation](https://aimodels.fyi/papers/arxiv/towards-context-aware-modeling-situation-awareness-conditionally) on driver fatigue and mental underload.

The experiment involved 22 participants navigating a test track in two conditions: manual driving and conditional automation (L3). EEG data was collected to measure changes in brain activity, which the researchers used as indicators of fatigue and mental underload.

The results showed that fatigue and mental underload were more pronounced in the L3 conditional automation condition compared to manual driving. Specifically, the EEG data revealed increased theta and alpha power, which are associated with drowsiness and disengagement, in the L3 condition.

These findings suggest that even though the car is handling some driving tasks, the driver still needs to remain vigilant and ready to take over, leading to greater mental strain over time. This underscores the need for [effective countermeasures](https://aimodels.fyi/papers/arxiv/human-machine-interaction-automated-vehicles-reducing-voluntary) to maintain driver engagement and alertness in [conditionally automated driving](https://aimodels.fyi/papers/arxiv/personalized-autonomous-driving-large-language-models-field).

## Critical Analysis

The paper provides valuable insights into the cognitive challenges faced by drivers in conditional automation scenarios. However, it is important to note some potential limitations and areas for further research.

The experiment was conducted on a test track, which may not fully capture the complexity and distractions of real-world driving conditions. Additionally, the sample size of 22 participants, while not uncommon for EEG studies, could be expanded to increase the generalizability of the findings.

[Future research](https://aimodels.fyi/papers/arxiv/accelerating-autonomy-insights-from-pro-racers-era) could explore the effects of prolonged exposure to conditional automation, as well as the potential impacts of individual differences in factors like age, experience, and personality on driver fatigue and mental underload.

It would also be interesting to investigate the effectiveness of various [countermeasures](https://aimodels.fyi/papers/arxiv/human-machine-interaction-automated-vehicles-reducing-voluntary), such as adaptive interface designs, task-based interventions, or physiological monitoring, in maintaining driver engagement and alertness in conditionally automated driving scenarios.

## Conclusion

This study highlights the cognitive challenges associated with [Level 3 conditional automation](https://aimodels.fyi/papers/arxiv/towards-context-aware-modeling-situation-awareness-conditionally), where drivers must remain vigilant and ready to take over driving tasks at any moment. The findings suggest that fatigue and mental underload are more pronounced in this level of automation compared to manual driving.

As the automotive industry continues to develop and deploy more advanced autonomous technologies, it will be crucial to address these human factors challenges to ensure the safety and well-being of drivers. [Effective countermeasures](https://aimodels.fyi/papers/arxiv/human-machine-interaction-automated-vehicles-reducing-voluntary) and [personalized approaches](https://aimodels.fyi/papers/arxiv/personalized-autonomous-driving-large-language-models-field) will be necessary to maintain driver engagement and prevent the negative impacts of conditional automation on cognitive states.

Martin Baumann

Keywords

Authored papers

When a cleaning robot rolls up, do people move out of the way, or strike up a conversation?

Can a souped-up driving simulator actually change your brain waves?

Can brainwave data reveal if your self-driving car's interface is secretly stressing you out?

Can a driving task alone really dial up the mental strain without adding distractions?

Is Level 3 automation actually making drivers more tired and bored?

Claim this author profile