Chenxu Hao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chenxu Hao has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Bernd Dudzik
Intelligent Systems/Pattern Recognition & Bioinformatics, Delft University of Technology, Delft, Netherlands
3 shared publications - Philipp Beckerle
Chair of Autonomous Systems and Mechatronics, Department of Electrical Engineering, Friedrich-Alexander-Universitt Erlangen-Nrnberg, Erlangen, Germany
3 shared publications - Tiffany Matej Hrkalovic
Jheronimus Academy of Data Science, 's-Hertogenbosch, Netherlands and Tilburg University, Tilburg, Netherlands
3 shared publications - Anany Dwivedi
Artificial Intelligence (AI) Institute, Division of Health, Engineering, Computing and Science, University of Waikato, Hamilton 3216, New Zealand
2 shared publications - Hayley Hung
Intelligent Systems, Delft University of Technology, Delft, Netherlands
2 shared publications Richard L. Lewis
Department of Psychology, University of Michigan, United States of America; Weinberg Institute for Cognitive Science, University of Michigan, United States of America
2 shared publications
Latest Publications
- Open Access
- 4 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 428-436
I Don’t Always Do What I Am Told: The Case for Task Incongruence-Aware Systems for Technology-Supported Reflection on Social Interactions
Technology-supported Self-Reflection (TSR) systems aim to facilitate learning through self-reflection. In the social domain, these systems often nudge individuals to perform better towards a certain outcome in a targeted task. Typically, this idea of support assumes that users pursue specific goals, which system creators anticipate will govern users’ behavior in targeted tasks. However, how goals shape behaviors in social interactions is complex: individuals’ goals can be highly idiosyncratic and multifaceted, sometimes contradictory to their best interest, and they are often not explicitly formulated in advance. We believe that viewing this complex landscape through the lens of a simple task formulation imposes limitations on the type of support these systems can provide. In this paper, we take a first step towards investigating the incongruence between assumed task goals and observed users’ behaviors and decisions in a partner selection setting, where participants need to select a partner for a cooperation task, and the apparent task goal can co-exist with other personal or relationship-oriented goals. First, we identify task-incongruent decisions, showing that even in a highly structured and incentivized setting, some choices deviate from the assumed task goal. Second, using a Large Language Model (LLM) to analyze conversational behavior, we explore topic-based and interactional indicators of task incongruence. Although the behavioral evidence is mixed, these findings still illustrate that what appears to be a reasonably assumed goal by the system may not be what users end up pursuing. In designing TSR systems, we believe that it is crucial to have capabilities for Task-Incongruence Awareness (TIA), enabling meaningful reflections on how users’ consciously or unconsciously self-ascribed goals are aligned with their behaviors and decisions.
- 4 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 428-436
Open AccessI Don’t Always Do What I Am Told: The Case for Task Incongruence-Aware Systems for Technology-Supported Reflection on Social Interactions
Technology-supported Self-Reflection (TSR) systems aim to facilitate learning through self-reflection. In the social domain, these systems often nudge individuals to perform better towards a certain outcome in a targeted task. Typically, this idea of support assumes that users pursue specific goals, which system creators anticipate will govern users’ behavior in targeted tasks. However, how goals shape behaviors in social interactions is complex: individuals’ goals can be highly idiosyncratic and multifaceted, sometimes contradictory to their best interest, and they are often not explicitly formulated in advance. We believe that viewing this complex landscape through the lens of a simple task formulation imposes limitations on the type of support these systems can provide. In this paper, we take a first step towards investigating the incongruence between assumed task goals and observed users’ behaviors and decisions in a partner selection setting, where participants need to select a partner for a cooperation task, and the apparent task goal can co-exist with other personal or relationship-oriented goals. First, we identify task-incongruent decisions, showing that even in a highly structured and incentivized setting, some choices deviate from the assumed task goal. Second, using a Large Language Model (LLM) to analyze conversational behavior, we explore topic-based and interactional indicators of task incongruence. Although the behavioral evidence is mixed, these findings still illustrate that what appears to be a reasonably assumed goal by the system may not be what users end up pursuing. In designing TSR systems, we believe that it is crucial to have capabilities for Task-Incongruence Awareness (TIA), enabling meaningful reflections on how users’ consciously or unconsciously self-ascribed goals are aligned with their behaviors and decisions.
- Open Access
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 1951-1967
User Reliance on AI Support for Collaborative Partner Selection
Whether choosing teammates for a project or partners for everyday life tasks, people constantly decide with whom to work. However, in these decisions, they often overemphasize characteristics that are not directly relevant to task performance. For example, prioritizing a partner’s trustworthiness for a task where competence is more important for good task performance. Artificial intelligence (AI) systems have the potential to mitigate these judgment errors by guiding decision-makers toward placing greater weight on traits that are more predictive of success for the specific task at hand. Although the potential usefulness of such systems is evident, previous work leaves unclear under what conditions and for what type of AI support people are willing to rely on and trust AI systems for such relational decisions (i.e., selecting a collaboration partner). To bridge this gap, our study examined how different forms of AI support shape users’ perceptions of the AI’s intellectual and social capabilities, their sense of autonomy, and their willingness to rely on and trust in AI when selecting a partner for a collaborative task. To do this, a total of 397 participants designed ideal partners for two collaborative tasks while receiving one of three forms of AI support: (1) recommendation, (2) explanation, or (3) knowledge nudges. This was tested in two different tasks: a competency-based task and a trustworthiness-based task. We found that richer AI support (through explanations or nudges) enhances perceived AI’s social and intellectual capabilities, but not autonomy. Perceptions of intellectual capabilities, rather than social capabilities, predict greater reliance. Both perceptions of AI capabilities mediate the effect of the type of AI support on reliance. Overall, the study advances understanding of human–AI collaboration by revealing how AI design features shape user perceptions and reliance when users need to evaluate and select their collaborators.
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 1951-1967
Open AccessUser Reliance on AI Support for Collaborative Partner Selection
Whether choosing teammates for a project or partners for everyday life tasks, people constantly decide with whom to work. However, in these decisions, they often overemphasize characteristics that are not directly relevant to task performance. For example, prioritizing a partner’s trustworthiness for a task where competence is more important for good task performance. Artificial intelligence (AI) systems have the potential to mitigate these judgment errors by guiding decision-makers toward placing greater weight on traits that are more predictive of success for the specific task at hand. Although the potential usefulness of such systems is evident, previous work leaves unclear under what conditions and for what type of AI support people are willing to rely on and trust AI systems for such relational decisions (i.e., selecting a collaboration partner). To bridge this gap, our study examined how different forms of AI support shape users’ perceptions of the AI’s intellectual and social capabilities, their sense of autonomy, and their willingness to rely on and trust in AI when selecting a partner for a collaborative task. To do this, a total of 397 participants designed ideal partners for two collaborative tasks while receiving one of three forms of AI support: (1) recommendation, (2) explanation, or (3) knowledge nudges. This was tested in two different tasks: a competency-based task and a trustworthiness-based task. We found that richer AI support (through explanations or nudges) enhances perceived AI’s social and intellectual capabilities, but not autonomy. Perceptions of intellectual capabilities, rather than social capabilities, predict greater reliance. Both perceptions of AI capabilities mediate the effect of the type of AI support on reliance. Overall, the study advances understanding of human–AI collaboration by revealing how AI design features shape user perceptions and reliance when users need to evaluate and select their collaborators.
- Open Access
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 249-264
Multimodal Quantitative Measures for Multiparty Behavior Evaluation
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 249-264
Open AccessMultimodal Quantitative Measures for Multiparty Behavior Evaluation
- 2 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 111-118
Conceptualizing the Integration of Cognitive and Physical Models to Enable Continuous Human-Robot Interaction
Research in human-robot interaction (HRI) often puts emphasis on either the cognitive level or on the physical level. In a scenario, where a robot physically guides a person to perform a complex series of tasks (e.g., a patient making tea), information is exchanged on the cognitive level and forces/torques are exchanged on the physical level, continuously. Such a continuous co-adaptive interaction between both agents and the environment requires the robot to be anticipating, proactive, and able to react flexibly to the user's intentions and situation context. The unification of sequential cognitive situation modeling and continuous robotic movement control is a challenge currently missing a conceptual framework. We conceptualize strategies on how to connect models of physical HRI and models of cognitive HRI, depending on the level of assistance provided by the robot system, from mere warnings of dangerous situations (level 1) to on-body continuous movement guidance (level 4). In this, we consider the requirements for the robot to be aware of the interaction environment and have a dynamic representation of the individual user. Our conceptual framework is intended to spark discussions and formalize assistance approaches with the aim to integrate cognitive and physical human-robot interaction approaches for anticipatory assistance in continuous dynamic tasks.
- 2 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 111-118
Conceptualizing the Integration of Cognitive and Physical Models to Enable Continuous Human-Robot Interaction
Research in human-robot interaction (HRI) often puts emphasis on either the cognitive level or on the physical level. In a scenario, where a robot physically guides a person to perform a complex series of tasks (e.g., a patient making tea), information is exchanged on the cognitive level and forces/torques are exchanged on the physical level, continuously. Such a continuous co-adaptive interaction between both agents and the environment requires the robot to be anticipating, proactive, and able to react flexibly to the user's intentions and situation context. The unification of sequential cognitive situation modeling and continuous robotic movement control is a challenge currently missing a conceptual framework. We conceptualize strategies on how to connect models of physical HRI and models of cognitive HRI, depending on the level of assistance provided by the robot system, from mere warnings of dangerous situations (level 1) to on-body continuous movement guidance (level 4). In this, we consider the requirements for the robot to be aware of the interaction environment and have a dynamic representation of the individual user. Our conceptual framework is intended to spark discussions and formalize assistance approaches with the aim to integrate cognitive and physical human-robot interaction approaches for anticipatory assistance in continuous dynamic tasks.
- Open Access
- 24 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 1354-1365
Technologies Supporting Self-Reflection on Social Interactions: A Systematic Review
- 24 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 1354-1365
Open AccessTechnologies Supporting Self-Reflection on Social Interactions: A Systematic Review
- Open Access
- 7 August 2024
- Published by Elsevier in Cognitive Psychology
- Vol. 153, 101672
Ethical choice reversals
- 7 August 2024
- Published by Elsevier in Cognitive Psychology
- Vol. 153, 101672
Open AccessEthical choice reversals
- 29 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Haptics
- Vol. 17 (2) , 292-301
How Positioning Wearable Haptic Interfaces on Limbs Influences Virtual Embodiment
With increasing use of computer applications and robotic devices in our everyday life, and with the advent of metaverse, there is an urgent need of developing new types of interfaces that facilitate a more intuitive interaction in physical and virtual space. In this work, we investigate the influence of the location of haptic feedback devices on embodiment of virtual hands and user load during an interactive pick-and-place task. To do this, we conducted a user study with a 3x2 repeated measure experiment design: feedback position is varied between the distal phalanx of the index finger and the thumb, the proximal phalanx of the index finger and the thumb, and the wrist. These conditions of feedback are tested with the stimuli applied synchronously to the participant in one case, and with an additional delay of 350 ms in the second case. The results show that the location of the haptic feedback device does not affect embodiment, whereas the delay, i.e., whether the feedback is applied synchronously or asynchronously, affects embodiment. This suggests that for pick-and-place tasks, haptic feedback devices can be placed on the user's wrist without compromising performance making the hands to remain free, allowing unobstructed hand visibility for precise motion tracking, thereby improving accuracy.
- 29 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Haptics
- Vol. 17 (2) , 292-301
How Positioning Wearable Haptic Interfaces on Limbs Influences Virtual Embodiment
With increasing use of computer applications and robotic devices in our everyday life, and with the advent of metaverse, there is an urgent need of developing new types of interfaces that facilitate a more intuitive interaction in physical and virtual space. In this work, we investigate the influence of the location of haptic feedback devices on embodiment of virtual hands and user load during an interactive pick-and-place task. To do this, we conducted a user study with a 3x2 repeated measure experiment design: feedback position is varied between the distal phalanx of the index finger and the thumb, the proximal phalanx of the index finger and the thumb, and the wrist. These conditions of feedback are tested with the stimuli applied synchronously to the participant in one case, and with an additional delay of 350 ms in the second case. The results show that the location of the haptic feedback device does not affect embodiment, whereas the delay, i.e., whether the feedback is applied synchronously or asynchronously, affects embodiment. This suggests that for pick-and-place tasks, haptic feedback devices can be placed on the user's wrist without compromising performance making the hands to remain free, allowing unobstructed hand visibility for precise motion tracking, thereby improving accuracy.
- 2 January 2023
- Published by Springer Nature
- p. 1-13
A Literature-Based Perspective on Human-Centered Design and Evaluation of Interfaces for Virtual Reality in Robotics
- 2 January 2023
- Published by Springer Nature
- p. 1-13
A Literature-Based Perspective on Human-Centered Design and Evaluation of Interfaces for Virtual Reality in Robotics
- Open Access
- 28 December 2022
- Published by Springer Nature in Cognitive, Affective, & Behavioral Neuroscience
- Vol. 23 (3) , 543-556
Why do valence asymmetries emerge in value learning? A reinforcement learning account
The Value Learning Task (VLT; e.g., Raymond & O’Brien, 2009) is widely used to investigate how acquired value impacts how we perceive and process stimuli. The task consists of a series of trials in which participants attempt to maximize accumulated winnings as they make choices from a pair of presented images associated with probabilistic win, loss, or no-change outcomes. The probabilities and outcomes are initially unknown to the participant and thus the task involves decision making and learning under uncertainty. Despite the symmetric outcome structure for win and loss pairs, people learn win associations better than loss associations (Lin, Cabrera-Haro, & Reuter-Lorenz, 2020). This learning asymmetry could lead to differences when the stimuli are probed in subsequent tasks, compromising inferences about how acquired value affects downstream processing. We investigate the nature of the asymmetry using a standard error-driven reinforcement learning model with a softmax choice rule. Despite having no special role for valence, the model yields the learning asymmetry observed in human behavior, whether the model parameters are set to maximize empirical fit, or task payoff. The asymmetry arises from an interaction between a neutral initial value estimate and a choice policy that exploits while exploring, leading to more poorly discriminated value estimates for loss stimuli. We also show how differences in estimated individual learning rates help to explain individual differences in the observed win-loss asymmetries, and how the final value estimates produced by the model provide a simple account of a post-learning explicit value categorization task.
- 28 December 2022
- Published by Springer Nature in Cognitive, Affective, & Behavioral Neuroscience
- Vol. 23 (3) , 543-556
Open AccessWhy do valence asymmetries emerge in value learning? A reinforcement learning account
The Value Learning Task (VLT; e.g., Raymond & O’Brien, 2009) is widely used to investigate how acquired value impacts how we perceive and process stimuli. The task consists of a series of trials in which participants attempt to maximize accumulated winnings as they make choices from a pair of presented images associated with probabilistic win, loss, or no-change outcomes. The probabilities and outcomes are initially unknown to the participant and thus the task involves decision making and learning under uncertainty. Despite the symmetric outcome structure for win and loss pairs, people learn win associations better than loss associations (Lin, Cabrera-Haro, & Reuter-Lorenz, 2020). This learning asymmetry could lead to differences when the stimuli are probed in subsequent tasks, compromising inferences about how acquired value affects downstream processing. We investigate the nature of the asymmetry using a standard error-driven reinforcement learning model with a softmax choice rule. Despite having no special role for valence, the model yields the learning asymmetry observed in human behavior, whether the model parameters are set to maximize empirical fit, or task payoff. The asymmetry arises from an interaction between a neutral initial value estimate and a choice policy that exploits while exploring, leading to more poorly discriminated value estimates for loss stimuli. We also show how differences in estimated individual learning rates help to explain individual differences in the observed win-loss asymmetries, and how the final value estimates produced by the model provide a simple account of a post-learning explicit value categorization task.
- 20 December 2022
- Published by Elsevier in Cognitive Systems Research
- Vol. 79, 1-3
A Commentary on Towards autonomous artificial agents with an active self: Modeling sense of control in situated action
- 20 December 2022
- Published by Elsevier in Cognitive Systems Research
- Vol. 79, 1-3
A Commentary on Towards autonomous artificial agents with an active self: Modeling sense of control in situated action