Seiji Yamada

Yosuke Fukuchi, Seiji Yamada

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.

Sota Kaneko, Seiji Yamada

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.

Yosuke Fukuchi, Seiji Yamada

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.

Yosuke Fukuchi, Seiji Yamada

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.

Yosuke Fukuchi, Seiji Yamada

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.

Akihiro Maehigashi, Takahiro Tsumura, Seiji Yamada

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.

Shin Sano, Seiji Yamada

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).

Shin Sano, Seiji Yamada

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.

Chenlin Hang, Tetsuo Ono, Seiji Yamada

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.

Ryo Nakahashi, Seiji Yamada

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.

Takahiro Tsumura, Seiji Yamada

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.

Nungduk Yun, Seiji Yamada

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.

Takato Okudo, Seiji Yamada

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.

Takato Okudo, Seiji Yamada

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.

Takato Okudo, Seiji Yamada

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.

Ryo Nakahashi, Seiji Yamada

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".