Search

Humans' trust in AI constitutes a pivotal element in fostering a synergistic relationship between humans and AI. This is particularly significant in the context of systems that leverage AI technology, such as autonomous driving systems and human-robot interaction. Trust facilitates appropriate utilization of these systems, thereby optimizing their potential benefits. If humans over-trust or under-trust an AI, serious problems such as misuse and accidents occur. To prevent over/under-trust, it is necessary to predict trust dynamics. However, trust is an internal state of humans and hard to directly observe. Therefore, we propose a prediction model for trust dynamics using dynamic structure equation modeling, which extends SEM that can handle time-series data. A path diagram, which shows causalities between variables, is developed in an exploratory way and the resultant path diagram is optimized for effective path structures. Over/under-trust was predicted with 90\% accuracy in a drone simulator task,, and it was predicted with 99\% accuracy in an autonomous driving task. These results show that our proposed method outperformed the conventional method including an auto regression family.

This paper reviews our previous trials of Nudge-XAI, an approach that introduces automatic biases into explanations from explainable AIs (XAIs) with the aim of leading users to better decisions, and it discusses the benefits and challenges. Nudge-XAI uses a user model that predicts the influence of providing an explanation or emphasizing it and attempts to guide users toward AI-suggested decisions without coercion. The nudge design is expected to enhance the autonomy of users, reduce the risk associated with an AI making decisions without users' full agreement, and enable users to avoid AI failures. To discuss the potential of Nudge-XAI, this paper reports a post-hoc investigation of previous experimental results using cluster analysis. The results demonstrate the diversity of user behavior in response to Nudge-XAI, which supports our aim of enhancing user autonomy. However, it also highlights the challenge of users who distrust AI and falsely make decisions contrary to AI suggestions, suggesting the need for personalized adjustment of the strength of nudges to make this approach work more generally., Comment: Accepted at the 9th issue of the International Conference Series on Robot Ethics and Standards (ICRES 2024)

As anthropomorphic agents (AI and robots) are increasingly used in society, empathy and trust between people and agents are becoming increasingly important. A better understanding of agents by people will help to improve the problems caused by the future use of agents in society. In the past, there has been a focus on the importance of self-disclosure and the relationship between agents and humans in their interactions. In this study, we focused on the attributes of self-disclosure and the relationship between agents and people. An experiment was conducted to investigate hypotheses on trust and empathy with agents through six attributes of self-disclosure (opinions and attitudes, hobbies, work, money, personality, and body) and through competitive and cooperative relationships before a robotic agent performs a joint task. The experiment consisted of two between-participant factors: six levels of self-disclosure attributes and two levels of relationship with the agent. The results showed that the two factors had no effect on trust in the agent, but there was statistical significance for the attribute of self-disclosure regarding a person's empathy toward the agent. In addition, statistical significance was found regarding the agent's ability to empathize with a person as perceived by the person only in the case where the type of relationship, competitive or cooperative, was presented. The results of this study could lead to an effective method for building relationships with agents, which are increasingly used in society., Comment: 8 pages, 5 figures, 4 tables, submitted RO-MAN2024. arXiv admin note: text overlap with arXiv:2306.09447

Communication robots have the potential to contribute to effective human-XAI interaction as an interface that goes beyond textual or graphical explanations. One of their strengths is that they can use physical and vocal expressions to add detailed nuances to explanations. However, it is not clear how a robot can apply such expressions, or in particular, how we can develop a strategy to adaptively use such expressions depending on the task and user in dynamic interactions. To address this question, this paper proposes DynEmph, a method for a communication robot to decide where to emphasize XAI-generated explanations with physical expressions. It predicts the effect of emphasizing certain points on a user and aims to minimize the expected difference between predicted user decisions and AI-suggested ones. DynEmph features a strategy for deciding where to emphasize in a data-driven manner, relieving engineers from the need to manually design a strategy. We further conducted experiments to investigate how emphasis selection strategies affect the performance of user decisions. The results suggest that, while a naive strategy (emphasizing explanations for an AI's most probable class) does not necessarily work better, DynEmph effectively guides users to better decisions under the condition that the performance of the AI suggestion is high.

This paper addresses the challenge of selecting explanations for XAI (Explainable AI)-based Intelligent Decision Support Systems (IDSSs). IDSSs have shown promise in improving user decisions through XAI-generated explanations along with AI predictions, and the development of XAI made it possible to generate a variety of such explanations. However, how IDSSs should select explanations to enhance user decision-making remains an open question. This paper proposes X-Selector, a method for selectively presenting XAI explanations. It enables IDSSs to strategically guide users to an AI-suggested decision by predicting the impact of different combinations of explanations on a user's decision and selecting the combination that is expected to minimize the discrepancy between an AI suggestion and a user decision. We compared the efficacy of X-Selector with two naive strategies (all possible explanations and explanations only for the most likely prediction) and two baselines (no explanation and no AI support). The results suggest the potential of X-Selector to guide users to AI-suggested decisions and improve task performance under the condition of a high AI accuracy., Comment: Accepted at the 2024 33rd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)

Cooperative relationships between humans and agents are becoming more important for the social coexistence of anthropomorphic agents, including virtual agents and robots. One way to improve the relationship between humans and agents is for humans to empathize with the agents. Empathy can help humans become more accepting of agents. In this study, we focus on the IKEA effect in creating agents and investigate human empathy toward agents through relationships with others in the same space. For this reason, this study used a robot assembly task in which two participants cooperatively build the same robot or individually their own robot. We conducted experiments to examine the relationship between participants, the IKEA effect in creating an agent, and the influence of the empathy object on human empathy. The results showed that the IKEA effect promoted empathy toward the agent regardless of the relationship between participants. On the other hand, there was no significant difference in empathy from one participant to another before and after the task. These results indicate that regardless of the relationship between participants in the same space, the creation of an agent can promote empathy toward the agent., Comment: 19 pages, 9 figures, 4 tables, submitted International Journal of Social Robotics

As AI technology develops, trust in AI agents is becoming more important for more AI applications in human society. Possible ways to improve the trust relationship include empathy, success-failure series, and capability (performance). Appropriate trust is less likely to cause deviations between actual and ideal performance. In this study, we focus on the agent's empathy and success-failure series to increase trust in AI agents. We experimentally examine the effect of empathy from agent to person on changes in trust over time. The experiment was conducted with a two-factor mixed design: empathy (available, not available) and success-failure series (phase 1 to phase 5). An analysis of variance (ANOVA) was conducted using data from 198 participants. The results showed an interaction between the empathy factor and the success-failure series factor, with trust in the agent stabilizing when empathy was present. This result supports our hypothesis. This study shows that designing AI agents to be empathetic is an important factor for trust and helps humans build appropriate trust relationships with AI agents., Comment: 9 pages, 7 figures, 4tables, submitted HAI2023

One way to improve the relationship between humans and anthropomorphic agents is to have humans empathize with the agents. In this study, we focused on a task between an agent and a human in which the agent makes a mistake. To investigate significant factors for designing a robotic agent that can promote humans empathy, we experimentally examined the hypothesis that agent reaction and human's preference affect human empathy and acceptance of the agent's mistakes. The experiment consisted of a four-condition, three-factor mixed design with agent reaction, selected agent's body color for human's preference, and pre- and post-task as factors. The results showed that agent reaction and human's preference did not affect empathy toward the agent but did allow the agent to make mistakes. It was also shown that empathy for the agent decreased when the agent made a mistake on the task. The results of this study provide a way to control impressions of the robotic virtual agent's behaviors, which are increasingly used in society., Comment: 13 pages, 4 figures, 5 tables, submitted ICSR2023. arXiv admin note: text overlap with arXiv:2206.06128

We propose the Mood Board Composer (MBC), which supports concept designers in retrieving and composing images on a 2-D concept space to communicate design concepts. The MBC allows users to iterate adaptive image retrievals intuitively. Our new contribution to the mood board tool is to adapt the query vector for the next iteration according to the user's rearrangement of images on the 2-D space. The algorithm emphasizes the meaning of the labels on the x- and y-axes by calculating the mean vector of the images on the mood board multiplied by the weights assigned to each cell of the 3 x 3 grid. The next image search is performed by obtaining the most similar words from the mean vector thus obtained and using them as a new query. In addition to the algorithm described above, we conducted the participant experiment with two other interaction algorithms to compare. The first allows users to delete unwanted images and go on to the next searches. The second utilizes the semantic labels on each image, on which users can provide negative feedback for query modification for the next searches. Although we did not observe significant differences among the three proposed algorithms, our experiment with 420 cases of mood board creation confirmed the effectiveness of adaptive iterations by the Creativity Support Index (CSI) score., Comment: 14 pages, 7 figures

For effective collaboration between humans and intelligent agents that employ machine learning for decision-making, humans must understand what agents can and cannot do to avoid over/under-reliance. A solution to this problem is adjusting human reliance through communication using reliance calibration cues (RCCs) to help humans assess agents' capabilities. Previous studies typically attempted to calibrate reliance by continuously presenting RCCs, and when an agent should provide RCCs remains an open question. To answer this, we propose Pred-RC, a method for selectively providing RCCs. Pred-RC uses a cognitive reliance model to predict whether a human will assign a task to an agent. By comparing the prediction results for both cases with and without an RCC, Pred-RC evaluates the influence of the RCC on human reliance. We tested Pred-RC in a human-AI collaboration task and found that it can successfully calibrate human reliance with a reduced number of RCCs., Comment: 8 pages

This study used XAI, which shows its purposes and attention as explanations of its process, and investigated how these explanations affect human trust in and use of AI. In this study, we generated heat maps indicating AI attention, conducted Experiment 1 to confirm the validity of the interpretability of the heat maps, and conducted Experiment 2 to investigate the effects of the purpose and heat maps in terms of reliance (depending on AI) and compliance (accepting answers of AI). The results of structural equation modeling (SEM) analyses showed that (1) displaying the purpose of AI positively and negatively influenced trust depending on the types of AI usage, reliance or compliance, and task difficulty, (2) just displaying the heat maps negatively influenced trust in a more difficult task, and (3) the heat maps positively influenced trust according to their interpretability in a more difficult task., Comment: Published in Proceedings of the 45th Annual Meeting of the Cognitive Science Society (CogSci2023)

This study investigated how wait time influences trust in and reliance on a robot. Experiment 1 was conducted as an online experiment manipulating the wait time for the task partner's action from 1 to 20 seconds and the anthropomorphism of the partner. As a result, the anthropomorphism influenced trust in the partner and did not influence reliance on the partner. However, the wait time negatively influenced trust in and reliance on the partner. Moreover, a mediation effect of trust from the wait time on reliance on the partner was confirmed. Experiment 2 was conducted to confirm the effects of wait time on trust and reliance in a human-robot face-to-face situation. As a result, the same effects of wait time found in Experiment 1 were confirmed. This study revealed that wait time is a strong and controllable factor that influences trust in and reliance on a robot.

The social acceptance of AI agents, including intelligent virtual agents and physical robots, is becoming more important for the integration of AI into human society. Although the agents used in human society share various tasks with humans, their cooperation may frequently reduce the task performance. One way to improve the relationship between humans and AI agents is to have humans empathize with the agents. By empathizing, humans feel positively and kindly toward agents, which makes it easier to accept them. In this study, we focus on tasks in which humans and agents have various interactions together, and we investigate the properties of agents that significantly influence human empathy toward the agents. To investigate the effects of task content, difficulty, task completion, and an agent's expression on human empathy, two experiments were conducted. The results of the two experiments showed that human empathy toward the agent was difficult to maintain with only task factors, and that the agent's expression was able to maintain human empathy. In addition, a higher task difficulty reduced the decrease in human empathy, regardless of task content. These results demonstrate that an AI agent's properties play an important role in helping humans accept them., Comment: 17 pages, 12 figures, 5 tables, submitted IEEE Access. arXiv admin note: substantial text overlap with arXiv:2206.06128

One way to improve the relationship between humans and anthropomorphic agents is to have humans empathize with the agents. In this study, we focused on a task between agents and humans. We experimentally investigated hypotheses stating that task difficulty and task content facilitate human empathy. The experiment was a two-way analysis of variance (ANOVA) with four conditions: task difficulty (high, low) and task content (competitive, cooperative). The results showed no main effect for the task content factor and a significant main effect for the task difficulty factor. In addition, pre-task empathy toward the agent decreased after the task. The ANOVA showed that one category of empathy toward the agent increased when the task difficulty was higher than when it was lower.This indicated that this category of empathy was more likely to be affected by the task. The task itself used can be an important factor when manipulating each category of empathy., Comment: Accepted by RO-MAN2022, 7 pages, 5 figures, 3 tables

Perspective taking, which allows people to imagine another's thinking and goals, is known to be an effective method for promoting prosocial behaviors in human-computer interactions. However, most of the previous studies have focused on simulating human-human interactions in the real world by offering participants experiences related to various moral tasks through the use of human-like virtual agents. In this study, we investigated whether taking the perspective of a different robot in a robot-altruistic task would influence the social behaviors of participants in a dictator game. Our findings showed that participants who watched the help-receiver view exhibited more altruistic behaviors toward a robot than those who watched the help-provider view. We also found that, after watching robots from two different viewpoints in the task, participants did not change their behavior toward another participant.

This study investigated whether human trust in a social robot with anthropomorphic physicality is similar to that in an AI agent or in a human in order to clarify how anthropomorphic physicality influences human trust in an agent. We conducted an online experiment using two types of cognitive tasks, calculation and emotion recognition tasks, where participants answered after referring to the answers of an AI agent, a human, or a social robot. During the experiment, the participants rated their trust levels in their partners. As a result, trust in the social robot was basically neither similar to that in the AI agent nor in the human and instead settled between them. The results showed a possibility that manipulating anthropomorphic features would help assist human users in appropriately calibrating trust in an agent., Comment: Published in Proceedings of the 10th International Conference on Human-Agent Interaction (HAI2022)

We propose an AI-assisted design concept exploration tool, the "Character Space Construction" ("CSC"). Concept designers explore and articulate the target product aesthetics and semantics in language, which is expressed using "Design Concept Phrases" ("DCPs"), that is, compound adjective phrases, and contrasting terms that convey what are not their target design concepts. Designers often utilize this dichotomy technique to communicate the nature of their aesthetic and semantic design concepts with stakeholders, especially in an early design development phase. The CSC assists this designers' cognitive activity by constructing a "Character Space" ("CS"), which is a semantic quadrant system, in a structured manner. A CS created by designers with the assistance of the CSC enables them to discern and explain their design concepts in contrast with opposing terms. These terms in a CS are retrieved and combined in the CSC by using a knowledge graph. The CSC presents terms and phrases as lists of candidates to users from which users will choose in order to define the target design concept, which is then visualized in a CS. The participants in our experiment, who were in the "arts and design" profession, were given two conditions under which to create DCPs and explain them. One group created and explained the DCPs with the assistance of the proposed CSC, and the other did the same task without this assistance, given the freedom to use any publicly available web search tools instead. The result showed that the group assisted by the CSC indicated their tasks were supported significantly better, especially in exploration, as measured by the Creativity Support Index (CSI)., Comment: 21 pages, 7 figures

We present an AI-assisted search tool, the "Design Concept Exploration Graph" ("D-Graph"). It assists automotive designers in creating an original design-concept phrase, that is, a combination of two adjectives that conveys product aesthetics. D-Graph retrieves adjectives from a ConceptNet knowledge graph as nodes and visualizes them in a dynamically scalable 3D graph as users explore words. The retrieval algorithm helps in finding unique words by ruling out overused words on the basis of word frequency from a large text corpus and words that are too similar between the two in a combination using the cosine similarity from ConceptNet Numberbatch word embeddings. Our experiment with participants in the automotive design field that used both the proposed D-Graph and a baseline tool for design-concept-phrase creation tasks suggested a positive difference in participants' self-evaluation on the phrases they created, though not significant. Experts' evaluations on the phrases did not show significant differences. Negative correlations between the cosine similarity of the two words in a design-concept phrase and the experts' evaluation were significant. Our qualitative analysis suggested the directions for further development of the tool that should help users in adhering to the strategy of creating compound phrases supported by computational linguistic principles., Comment: 16 pages, 6 figures

Previous studies have found that nudging is key to promoting altruism in human-human interaction. However, in social robotics, there is still a lack of study on confirming the effect of nudging on altruism. In this paper, we apply two nudge mechanisms, peak-end and multiple viewpoints, to a video stimulus performed by social robots (virtual agents) to see whether a subtle change in the stimulus can promote human altruism. An experiment was conducted online through crowdsourcing with 136 participants. The result shows that the participants who watched the peak part set at the end of the video performed better at the Dictator game, which means that the nudge mechanism of the peak-end effect actually promoted human altruism., Comment: 11 pages, 5 figures, accepted by The Thirteenth International Conference on Social Robotics

The human-agent team, which is a problem in which humans and autonomous agents collaborate to achieve one task, is typical in human-AI collaboration. For effective collaboration, humans want to have an effective plan, but in realistic situations, they might have difficulty calculating the best plan due to cognitive limitations. In this case, guidance from an agent that has many computational resources may be useful. However, if an agent guides the human behavior explicitly, the human may feel that they have lost autonomy and are being controlled by the agent. We therefore investigated implicit guidance offered by means of an agent's behavior. With this type of guidance, the agent acts in a way that makes it easy for the human to find an effective plan for a collaborative task, and the human can then improve the plan. Since the human improves their plan voluntarily, he or she maintains autonomy. We modeled a collaborative agent with implicit guidance by integrating the Bayesian Theory of Mind into existing collaborative-planning algorithms and demonstrated through a behavioral experiment that implicit guidance is effective for enabling humans to maintain a balance between improving their plans and retaining autonomy.

As AI technologies progress, social acceptance of AI agents, including intelligent virtual agents and robots, is becoming even more important for more applications of AI in human society. One way to improve the relationship between humans and anthropomorphic agents is to have humans empathize with the agents. By empathizing, humans act positively and kindly toward agents, which makes it easier for them to accept the agents. In this study, we focus on self-disclosure from agents to humans in order to increase empathy felt by humans toward anthropomorphic agents. We experimentally investigate the possibility that self-disclosure from an agent facilitates human empathy. We formulate hypotheses and experimentally analyze and discuss the conditions in which humans have more empathy toward agents. Experiments were conducted with a three-way mixed plan, and the factors were the agents' appearance (human, robot), self-disclosure (high-relevance self-disclosure, low-relevance self-disclosure, no self-disclosure), and empathy before/after a video stimulus. An analysis of variance (ANOVA) was performed using data from 918 participants. We found that the appearance factor did not have a main effect, and self-disclosure that was highly relevant to the scenario used facilitated more human empathy with a statistically significant difference. We also found that no self-disclosure suppressed empathy.These results support our hypotheses. This study reveals that self-disclosure represents an important characteristic of anthropomorphic agents which helps humans to accept them., Comment: 24 pages, 9 figures, 3 tables, submitted to PLOS ONE Journal

Nowadays, a community starts to find the need for human presence in an alternative way, there has been tremendous research and development in advancing telepresence robots. People tend to feel closer and more comfortable with telepresence robots as many senses a human presence in robots. In general, many people feel the sense of agency from the face of a robot, but some telepresence robots without arm and body motions tend to give a sense of human presence. It is important to identify and configure how the telepresence robots affect a sense of presence and agency to people by including human face and slight face and arm motions. Therefore, we carried out extensive research via web-based experiment to determine the prototype that can result in soothing human interaction with the robot. The experiments featured videos of a telepresence robot n = 128, 2 x 2 between-participant study robot face factor: video-conference, robot-like face; arm motion factor: moving vs. static) to investigate the factors significantly affecting human presence and agency with the robot. We used two telepresence robots: an affordable robot platform and a modified version for human interaction enhancements. The findings suggest that participants feel agency that is closer to human-likeness when the robot's face was replaced with a human's face and without a motion. The robot's motion invokes a feeling of human presence whether the face is human or robot-like.

Reinforcement learning, which acquires a policy maximizing long-term rewards, has been actively studied. Unfortunately, this learning type is too slow and difficult to use in practical situations because the state-action space becomes huge in real environments. Many studies have incorporated human knowledge into reinforcement Learning. Though human knowledge on trajectories is often used, a human could be asked to control an AI agent, which can be difficult. Knowledge on subgoals may lessen this requirement because humans need only to consider a few representative states on an optimal trajectory in their minds. The essential factor for learning efficiency is rewards. Potential-based reward shaping is a basic method for enriching rewards. However, it is often difficult to incorporate subgoals for accelerating learning over potential-based reward shaping. This is because the appropriate potentials are not intuitive for humans. We extend potential-based reward shaping and propose a subgoal-based reward shaping. The method makes it easier for human trainers to share their knowledge of subgoals. To evaluate our method, we obtained a subgoal series from participants and conducted experiments in three domains, four-rooms(discrete states and discrete actions), pinball(continuous and discrete), and picking(both continuous). We compared our method with a baseline reinforcement learning algorithm and other subgoal-based methods, including random subgoal and naive subgoal-based reward shaping. As a result, we found out that our reward shaping outperformed all other methods in learning efficiency., Comment: This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible. arXiv admin note: substantial text overlap with arXiv:2104.06163

Social navigation has been gaining attentions with the growth in machine intelligence. Since reinforcement learning can select an action in the prediction phase at a low computational cost, it has been formulated in a social navigation tasks. However, reinforcement learning takes an enormous number of iterations until acquiring a behavior policy in the learning phase. This negatively affects the learning of robot behaviors in the real world. In particular, social navigation includes humans who are unpredictable moving obstacles in an environment. We proposed a reward shaping method with subgoals to accelerate learning. The main part is an aggregation method that use subgoals to shape a reinforcement learning algorithm. We performed a learning experiment with a social navigation task in which a robot avoided collisions and then reached its goal. The experimental results show that our method improved the learning efficiency from a base algorithm in the task., Comment: arXiv admin note: substantial text overlap with arXiv:2104.06163

Reinforcement learning, which acquires a policy maximizing long-term rewards, has been actively studied. Unfortunately, this learning type is too slow and difficult to use in practical situations because the state-action space becomes huge in real environments. The essential factor for learning efficiency is rewards. Potential-based reward shaping is a basic method for enriching rewards. This method is required to define a specific real-value function called a potential function for every domain. It is often difficult to represent the potential function directly. SARSA-RS learns the potential function and acquires it. However, SARSA-RS can only be applied to the simple environment. The bottleneck of this method is the aggregation of states to make abstract states since it is almost impossible for designers to build an aggregation function for all states. We propose a trajectory aggregation that uses subgoal series. This method dynamically aggregates states in an episode during trial and error with only the subgoal series and subgoal identification function. It makes designer effort minimal and the application to environments with high-dimensional observations possible. We obtained subgoal series from participants for experiments. We conducted the experiments in three domains, four-rooms(discrete states and discrete actions), pinball(continuous and discrete), and picking(both continuous). We compared our method with a baseline reinforcement learning algorithm and other subgoal-based methods, including random subgoal and naive subgoal-based reward shaping. As a result, our reward shaping outperformed all other methods in learning efficiency., Comment: accepted by The International Joint Conference on Neural Networks(IJCNN2021)

A recent approach based on Bayesian inverse planning for the "theory of mind" has shown good performance in modeling human cognition. However, perfect inverse planning differs from human cognition during one kind of complex tasks due to human bounded rationality. One example is an environment in which there are many available plans for achieving a specific goal. We propose a "plan predictability oriented model" as a model of inferring other peoples' goals in complex environments. This model adds the bias that people prefer predictable plans. This bias is calculated with simple plan prediction. We tested this model with a behavioral experiment in which humans observed the partial path of goal-directed actions. Our model had a higher correlation with human inference. We also confirmed the robustness of our model with complex tasks and determined that it can be improved by taking account of individual differences in "bounded rationality"., Comment: Accepted at Cogsci 2018