Automated vehicles (AVs) consistently encounter ethically ambiguous situations in everyday driving, scenarios involving conflicting human interests and no clearly optimal course of action. While existing work often focuses on rare, high-stakes dilemmas (e.g., crash avoidance or trolley problems), routine decisions such as overtaking cyclists or navigating social interactions remain underexplored. This study addresses that gap by applying the tracking condition of Meaningful Human Control (MHC), which holds that AV behaviour should align with human reasons—the values, intentions, or expectations that justify actions. We conducted semi-structured interviews with 18 AV experts, who explained the reasons behind the considerations AV should make when planning a manoeuvre. Thirteen reason categories emerged, organised across normative, strategic, tactical, and operational levels. Using a case study on cyclist overtaking, we demonstrate how these reasons interact in practice and expose tensions in the decision-making process. Building on this analysis, we derive a reason-prioritisation principle grounded in the cyclist-overtaking scenario for AV behaviour in ethically ambiguous routine situations: prioritising vulnerable road users’ safety above all, treating systemic safety and regulation as important but conditional, and permitting secondary values only when safety is not compromised. This hierarchy supports human-aligned behaviour by allowing pragmatic actions when strict legal compliance would undermine higher-priority values. Our findings offer conceptual principles intended to inform future research and design for AV decision-making in ethically challenging routine situations.

Merging onto a highway is a safety-critical task resulting in a large number of traffic accidents; fundamental research into merging behavior of human drivers can help reduce this toll. Two cognitive processes critical to merging, attention allocation and decision making, have been extensively studied in real-world and simulated driving scenarios. However, how these processes interact during highway merging remains poorly understood. While the relationship between attention and decision making has been widely examined in cognitive science, this work has largely relied on simple decision-making paradigms involving choices between static items on a computer screen, which limits the understanding of more dynamic and naturalistic decisions such as in driving. To address this gap, we investigated the relationship between attention and decision making in a simplified highway merging task. In a video-based experiment, participants (N=24) repeatedly made merging gap acceptance decisions based on the dynamic information about the distance and time-to-arrival to the end of the merging lane and the gap to the target-lane vehicle (available in the front view and the side mirror, respectively). Participants’ decisions, response times, and eye movements were recorded. We found that decisions to accept a gap were considerably faster than decisions to reject a gap. Decision outcomes and timing depended on the distance to and time-to-arrival of the target-lane vehicle, but also on the time pressure due to approaching the end of the merging lane. Most importantly, under high time pressure, a greater proportion of time spent looking at the side mirror was associated with a lower probability of accepting the gap. This finding indicates that differences in visual information sampling can be closely linked to decision outcomes when time budgets are constrained. Our results provide initial empirical insights relevant for future cognitive modeling of the interplay between decision making and attention during highway merging. This work can inform early-stage exploration of driver monitoring and support systems for partially automated driving.

The introduction of automated driving systems (ADS) presents significant regulatory and operational challenges to ensure safe and responsible deployment in mixed traffic environments. Despite much academic work and efforts of practitioners, these challenges remain open, requiring a transdisciplinary integration of perspectives. This paper draws on insights from a recent transdisciplinary workshop, highlighting the key issues in ADS deployment, including misalignment between regulations and system capabilities, emerging accident types, and gaps in driver understanding and training. Current regulations struggle to keep pace with the advancing capabilities of ADS, resulting in unclear accountability frameworks and inadequate safety measures. The concept of meaningful human control was used as a basis to identify issues. Workshop participants agreed that meaningful human control has an essential role to play to address the identified issues by ensuring that humans can adequately interact with ADS and that ADS are designed in a manner that ensures safe and responsible deployment with clear fail-safes and redundancy mechanisms. The paper advocates for meaningful human control through continuous driver and vehicle assessment, dynamic safety certifications, and stronger communication between regulators and manufacturers to ensure safe and responsible design, regulation and deployment of automated vehicles. Implementing these actions will strengthen ADS regulation and help navigate the ethical and operational complexities of automated driving systems.

One of the key issues in human-robot collaboration is the development of computational models that allow robots to predict and adapt to human behavior. Much progress has been achieved in developing such models, as well as control techniques that address the autonomy problems of motion planning and decision-making in robotics. However, the integration of computational models of human behavior with such control techniques still poses a major challenge, resulting in a bottleneck for efficient collaborative human-robot teams. In this context, we present a novel architecture for human-robot collaboration: Adaptive Robot Motion for Collaboration with Humans using Adversarial Inverse Reinforcement learning (ARMCHAIR). Our solution leverages adversarial inverse reinforcement learning and model predictive control to compute optimal trajectories and decisions for a mobile multi-robot system that collaborates with a human in an exploration task. During the mission, ARMCHAIR operates without human intervention, autonomously identifying the necessity to support and acting accordingly. Our approach also explicitly addresses the network connectivity requirement of the human-robot team. Extensive simulation-based evaluations demonstrate that ARMCHAIR allows a group of robots to safely support a simulated human in an exploration scenario, preventing collisions and network disconnections, and improving the overall performance of the task.

Understanding how human drivers handle inter-actions with each other can aid the development of automated vehicles capable of operating in mixed traffic. Interactions between human drivers are often complex, so driver behavior models are needed to better understand them. However, existing models mostly focus on the behavior of one driver, which limits their ability to explain complex reciprocal interactions between multiple drivers. At the same time, the prior research that does focus on interactive behaviors of two or more drivers is typically limited to describing drivers' tactical decisions, limiting the understanding of how these decisions are related to operational aspects of behavior (safety margins and control inputs). In this work, we address this gap, focusing specif-ically on highway merging interactions. We build upon the Communication-Enabled Interactions (CEI) framework - a previously proposed holistic approach to interaction modeling. We develop a CEI-based model of highway merging that captures both tactical and operational aspects of the behavior of two drivers interacting in a highway merging scenario. Our model exhibits human-like behavior aligned with empirical observations of high-level decisions (i.e., who goes first?), safety margins (headways), and position and velocity profiles. Based on our model, we identify key mechanisms regarding drivers' beliefs, velocity perception, and planning, which can potentially generalize beyond highway merging to other interactive human driving behaviors. Our findings highlight the potential of the CEI framework in modeling reciprocal traffic interactions in realistic traffic scenarios, and contribute to understanding the complexities of interactions between human drivers.

Background: Robotic devices have shown promise in supporting motor (re)learning. However, there is a limited understanding of how personality traits influence the effectiveness of robot-aided training strategies. Methods: We conducted a motor learning experiment with 40 unimpaired participants who trained to control a virtual pendulum using a robotic haptic device. Before the experiment, we assessed personality traits including the perceived control over life events (Locus of Control), the tendency to turn challenges into engaging activities (Transform of Challenge), and other subscales from Autotelic and Hexad gaming style questionnaires. Participants were divided into two groups, one receiving haptic guidance during training and a second one without assistance. Short- and long-term retention was assessed, and relationships between personality traits, performance metrics, and human-robot interaction metrics were analyzed. Results: Participants with high Transform of Challenge or external Locus of Control characteristics who received physical guidance during training reduced the human-robot interaction forces to a lesser extent compared to the ones who did not receive guidance. Additionally, participants with a high Free Spirit gaming style showed greater sensitivity to how their perception of the guidance affected their performance during the retention phases. Conclusion: Our findings suggest that autotelic personality, Locus of Control, and gaming style modulate motor learning outcomes during robotic-assisted training, affecting both performance and human-robot interaction metrics. This highlights the potential of integrating personality-based adaptations in robot-aided rehabilitation protocols to enhance performance and motor (re)learning. Future works should explore the relationship between personality traits and psychological states (e.g., perceived difficulty, attention) across diverse tasks and guidance methods in clinical populations.

Detecting abnormal driving behavior is critical for road traffic safety and the evaluation of drivers’ behavior. With the advancement of machine learning (ML) algorithms and the accumulation of naturalistic driving data, many ML models have been adopted for abnormal driving behavior detection (also referred to in this paper as “anomalies”). Most existing ML-based detectors rely on (fully) supervised ML methods, which require substantial labeled data. However, ground truth labels are not always available in the real world, and labeling large amounts of data is tedious. Thus, there is a need to explore unsupervised or semi-supervised methods to make the anomaly detection process more feasible and efficient. To fill this research gap, this study analyzes large-scale real-world data revealing several abnormal driving behaviors (e.g., sudden acceleration, rapid lane-changing) and develops a hierarchical extreme learning machine (HELM)-based semi-supervised ML method using partly labeled data to accurately detect the identified abnormal driving behaviors. Moreover, previous ML-based approaches predominantly utilized basic vehicle motion features (such as velocity and acceleration) to label and detect abnormal driving behaviors, while this study seeks to introduce event-level safety indicators as input features for ML models to improve the detection performance. Results from extensive experiments demonstrate the effectiveness of the proposed semi-supervised ML model with the introduced safety indicators serving as important features. The proposed semi-supervised ML method outperforms other baseline semi-supervised or unsupervised methods as far as various metrics are concerned: for example, it delivers the best accuracy at 99.58% and the best F1-score at 0.9913. The ablation study further highlights the significance of safety indicators for advancing the detection performance of abnormal driving behaviors.

Home-based rehabilitation is essential for stroke survivors, facilitating motor recovery and improving activities-of-daily-life performance. Recent advances in wearable technologies and machine learning promise to revolutionize home-based arm rehabilitation by providing detailed movement analysis. However, machine learning algorithms for arm movement identification are predominantly trained and tested in the same environments. Their ability to generalize to novel environments remains largely unknown, hindering practical applications. This paper investigates the ability of two established machine learning models to generalize a structured, lab-based environment to a more realistic, semi-structured kitchen environment. Twelve healthy participants performed various arm activities, involving three arm movement types (reaching, lifting, and pronation/supination). In addition to evaluating the generalization of movement identification, we compared algorithm performance for two different sensor configurations: four Inertial Measurement Units (IMUs) on the arm versus a single IMU on the wrist. We employed a Random Forest (RF) classifier and a hybrid deep learning model combining convolutional and recurrent neural networks, evaluating both subject-specific and group approaches. Trained in the structured environment, the RF classifier predicted activities in the semi-structured environment with 86.54% (subject-specific) and 77.37% (group) balanced accuracy, based on the four-sensor configuration, while the hybrid model reached 87.96% and 82.96% accuracy. The accuracy was lower with a single wrist IMU; the RF classifier showed a smaller decrease than the hybrid model. Our findings demonstrate that the investigated arm movement identification algorithms generalize well across environments even with the minimal sensor configuration, indicating the potential for future applications in home-based stroke rehabilitation.

Ensuring safe interactions between autonomous vehicles (AVs) and human drivers in mixed traffic systems remains a major challenge, particularly in complex, high-risk scenarios. This paper presents a cognition-decision framework that integrates individual variability and commonalities in driver behavior to quantify risk cognition and model dynamic decision-making. First, a risk sensitivity model based on a multivariate Gaussian distribution is developed to characterize individual differences in risk cognition. Then, a cognitive decision-making model based on the drift diffusion model (DDM) is introduced to capture common decision-making mechanisms in high-risk environments. The DDM dynamically adjusts decision thresholds by integrating initial bias, drift rate, and boundary parameters, adapting to variations in speed, relative distance, and risk sensitivity to reflect diverse driving styles and risk preferences. By simulating high-risk scenarios with lateral, longitudinal, and multidimensional risk sources in a driving simulator, the proposed model accurately predicts cognitive responses and decision behaviors during emergency maneuvers. Specifically, by incorporating driver-specific risk sensitivity, the model enables dynamic adjustments of key DDM parameters, allowing for personalized decision-making representations in diverse scenarios. Comparative analysis with IDM, Gipps, and MOBIL demonstrates that DDM more precisely captures human cognitive processes and adaptive decision-making in high-risk scenarios. These findings provide a theoretical basis for modeling human driving behavior and offer critical insights for enhancing AV-human interaction in real-world traffic environments.

Light detection and ranging (LiDAR) plays a crucial role in machine perception for advanced driver assistance systems. Existing LiDARs, however, do not adapt their sensing strategy to complement driver's perception. We demonstrate a novel LiDAR prototype that dynamically adapts its range and resolution over the field of view, according to real-time driver gaze. Our gaze-aware LiDAR emphasizes scanning peripheral zones the driver may overlook, i.e., critical areas during driving. Our demonstration showcases enhanced perception, highlighting the potential of hybrid human-machine sensing for safer driving.

Partially automated driving systems are designed to perform specific driving tasks—such as steering, accelerating, and braking—while still requiring human drivers to monitor the environment and intervene when necessary. This shift of driving responsibilities from human drivers to automated systems raises concerns about accountability, particularly in scenarios involving unexpected events. To address these concerns, the concept of meaningful human control (MHC) has been proposed. MHC emphasises the importance of humans retaining oversight and responsibility for decisions made by automated systems. Despite extensive theoretical discussion of MHC in driving automation, there is limited empirical research on how real-world partially automated systems align with MHC principles. This study offers two main contributions: (1) an empirical evaluation of MHC in partially automated driving, based on 103 semi-structured interviews with users of Tesla's Autopilot and Full Self-Driving (FSD) Beta systems; and (2) a methodological framework for assessing MHC through qualitative interview data. We operationalise the previously proposed tracking and tracing conditions of MHC using a set of evaluation criteria to determine whether these systems support meaningful human control in practice. Our findings indicate that several factors influence the degree to which MHC is achieved. Failures in tracking—where drivers' expectations regarding system safety are not adequately met—arise from technological limitations, susceptibility to environmental conditions (e.g., adverse weather or inadequate infrastructure), and discrepancies between technical performance and user satisfaction. Tracing performance—the ability to clearly assign responsibility—is affected by inconsistent adherence to safety protocols, varying levels of driver confidence, and the specific driving mode in use (e.g., Autopilot versus FSD Beta). These findings contribute to ongoing efforts to design partially automated driving systems that more effectively support meaningful human control and promote more appropriate use of automation.

Understanding human behavior in overtaking scenarios is crucial for enhancing road safety in mixed traffic with automated vehicles (AVs). Computational models of behavior play a pivotal role in advancing this understanding, as they can provide insight into human behavior generalizing beyond empirical studies. However, existing studies and models of human overtaking behavior have mostly focused on scenarios with simplistic, constant-speed dynamics of oncoming vehicles, disregarding the potential of AVs to proactively influence the decision-making process of the human drivers via implicit communication. Furthermore, despite numerous studies in other scenarios, so far it remained unknown whether overtaking decisions of human drivers are affected by whether they are interacting with an AV or a human-driven vehicle (HDV). To address these gaps, we conducted a “reverse Wizard-of-Oz” driving simulator experiment with 30 participants who repeatedly interacted with oncoming AVs and HDVs, measuring the drivers' gap acceptance decisions and response times. The oncoming vehicles featured time-varying dynamics designed to influence the overtaking decisions of the participants by briefly decelerating and then recovering to their initial speed. We found no evidence of differences in participants' overtaking behavior when interacting with oncoming AVs compared to HDVs. Furthermore, we did not find any evidence of brief decelerations of the oncoming vehicle affecting the decisions or response times of the participants. Cognitive modeling of the obtained data revealed that a generalized drift-diffusion model with dynamic drift rate and velocity-dependent decision bias best explained the gap acceptance outcomes and response times observed in the experiment. Overall, our findings highlight that cognitive models of the kind considered here can provide a generalizable description of human overtaking decisions and their timing. Such models can thus help further advance the ongoing development of safer interactions between human drivers and AVs during overtaking maneuvers.

In mixed traffic, one of the challenges for autonomous driving technology is how to safe and socially acceptable interaction with human-driven vehicles (HVs). Understanding human cognitive processes during decision-making in interactions with other road users is crucial for enhancing the smooth execution of driving tasks by autonomous vehicles (AVs). This paper proposes a cognitive model of the driver's cumulative information processing based on drift-diffusion model (DDM). By incorporating the initial decision biases, drift rate, and boundary (depending on the initial speed and gaps between ego vehicle and surrounding users) into the existing DDM, our model captures the integrated interaction between individual drivers and other road users. Classic emergency collision avoidance scenarios were constructed based on a driving simulation platform. Our cognitive model accurately described human decision-making in high-risk scenarios, identified key qualitative and quantitative input variables affecting the driver's cognitive processes, and quantified the safety thresholds of the driver's cumulative information processing. Results can support the personalized modeling of human drivers' cognition and facilitate safe and effective interactions between HVs and AVs.

The provision of robotic assistance during motor training has proven to be effective in enhancing motor learning in some healthy trainee groups as well as patients. Personalizing such robotic assistance can help further improve motor (re)learning outcomes and cater better to the trainee's needs and desires. However, the development of personalized haptic assistance is hindered by the lack of understanding of the link between the trainee's personality and the effects of haptic guidance during human-robot interaction. To address this gap, we ran an experiment with 40 healthy participants who trained with a robotic device to control a virtual pendulum to hit incoming targets, either with or without haptic guidance. We found that certain personal traits affected how users adapt and interact with the guidance during training. In particular, those participants with an 'Achiever gaming style' performed better and applied lower interaction forces to the robotic device than the average participant as the training progressed. Conversely, participants with the 'Free spirit game style' increased the interaction force in the course of training. We also found an interaction between some personal characteristics and haptic guidance. Specifically, participants with a higher 'Transformation of challenge' trait exhibited poorer performance during training while receiving haptic guidance compared to an average participant receiving haptic guidance. Furthermore, individuals with an external Locus of Control tended to increase their interaction force with the device, deviating from the pattern observed in an average participant under the same guidance. These findings suggest that individual characteristics may play a crucial role in the effectiveness of haptic guidance training strategies.

When a person makes a decision, it is automatically accompanied by a subjective probability judgment of the decision being correct, in other words, a confidence judgment. A better understanding of the mechanisms responsible for these confidence judgments could provide novel insights into human behavior. However, so far confidence judgments have been mostly studied in simplistic laboratory tasks while little is known about confidence in naturalistic dynamic tasks such as driving. In this study, we made a first attempt of connecting fundamental research on confidence with naturalistic driver behavior. We investigated the confidence of drivers in left-turn gap acceptance decisions in a driver simulator experiment (N = 17). We found that confidence in these decisions depends on the size of the gap to the oncoming vehicle. Specifically, confidence increased with the gap size for trials in which the gap was accepted, and decreased with the gap size for rejected gaps. Similarly to more basic tasks, confidence was negatively related to the response times and correlated with action dynamics during decision execution. Finally, we found that confidence judgments can be captured with an extended dynamic drift–diffusion model. In the model, the drift rate of the evidence accumulator as well as the decision boundaries are functions of the gap size. Furthermore, we demonstrated that allowing for post-decision evidence accumulation in the model increases its ability to describe confidence judgments in rejected gap decisions. Overall, our study confirmed that principles known from fundamental confidence research extend to confidence judgments in dynamic decisions during a naturalistic task.

Autonomous vehicles currently suffer from a time-inefficient driving style caused by uncertainty about human behavior, which could be improved by accurate and reliable prediction models enabling more efficient trajectory planning. However, the evaluation of such models is commonly over-simplistic, ignoring the asymmetric importance of prediction errors and the heterogeneity of the datasets used for testing. We examine the potential of recasting interactions between vehicles as gap acceptance scenarios and evaluating models in this structured environment. To that end, we develop a framework aiming to facilitate the evaluation of any model, by any metric, and in any scenario. We then apply this framework to state-of-the-art prediction models, which all show themselves to be unreliable in the most safety-critical situations.

Autonomous vehicles rely on accurate trajectory prediction to inform decision-making processes related to navigation and collision avoidance. However, current trajectory prediction models show signs of overfitting, which may lead to unsafe or suboptimal behavior. To address these challenges, this paper presents a comprehensive framework that categorizes and assesses the definitions and strategies used in the literature on evaluating and improving the robustness of trajectory prediction models. This involves a detailed exploration of various approaches, including data slicing methods, perturbation techniques, model architecture changes, and post-training adjustments. In the literature, we see many promising methods for increasing robustness, which are necessary for safe and reliable autonomous driving.

The estimation of probability density functions is a fundamental problem in science and engineering. However, common methods such as kernel density estimation (KDE) have been demonstrated to lack robustness, while more complex methods have not been evaluated in multi-modal estimation problems. In this paper, we present ROME (RObust Multi-modal Estimator), a non-parametric approach for density estimation which addresses the challenge of estimating multi-modal, non-normal, and highly correlated distributions. ROME utilizes clustering to segment a multi-modal set of samples into multiple uni-modal ones and then combines simple KDE estimates obtained for individual clusters in a single multi-modal estimate. We compared our approach to state-of-the-art methods for density estimation as well as ablations of ROME, showing that it not only outperforms established methods but is also more robust to a variety of distributions. Our results demonstrate that ROME can overcome the issues of over-fitting and over-smoothing exhibited by other estimators.

Traffic interactions between merging and highway vehicles are a major topic of research, yielding many empirical studies and models of driver behaviour. Most of these studies on merging use naturalistic data. Although this provides insight into human gap acceptance and traffic flow effects, it obscures the operational inputs of interacting drivers. Besides that, researchers have no control over the vehicle kinematics (i.e., positions and velocities) at the start of the interactions. Therefore the relationship between initial kinematics and the outcome of the interaction is difficult to investigate. To address these gaps, we conducted an experiment in a coupled driving simulator with a simplified, top-down view, merging scenario with two vehicles. We found that kinematics can explain the outcome (i.e., which driver merges first) and the duration of the merging conflict. Furthermore, our results show that drivers use key decision moments combined with constant acceleration inputs (intermittent piecewise-constant control) during merging. This indicates that they do not continuously optimise their expected utility. Therefore, these results advocate the development of interaction models based on intermittent piecewise-constant control. We hope our work can contribute to this development and to the fundamental knowledge of interactive driver behaviour.

Unprecedented possibilities of quadruped robots have driven much research on the technical aspects of these robots. However, the social perception and acceptability of quadruped robots so far remain poorly understood. This work investigates whether the way we design quadruped robots' behaviours can affect people's perception of safety in interactions with these robots. We designed and tested a dominant and submissive personality for the quadruped robot (Boston Dynamics Spot). These were tested in two different walking scenarios (head-on and crossing interactions) in a 2x2 within-subjects study. We collected both behavioural data and subjective reports on participants' perception of the interaction. The results highlight that participants perceived the submissive robot as safer compared to the dominant one. The behavioural dynamics of interactions did not change depending on the robot's appearance. Participants' previous in-person experience with the robot was associated with lower subjective safety ratings but did not correlate with the interaction dynamics. Our findings have implications for the design of quadruped robots and contribute to the body of knowledge on the social perception of non-humanoid robots. We call for a stronger standing of felt experiences in human-robot interaction research.