Suna Bensch

For the widespread deployment of robots in everyday tasks, robot’s actions, decisions and intentions must be understood by users. A fundamental factor affecting robot understandability is the underlying discrepancy between the robot’s and human’s state-of-minds. This paper contributes to the field of robot understandability by providing valuable insights into how discrepancy and robot understandability are connected, how human behavior indicates underlying discrepancy and how robots can use hidden Markov models to estimate varying discrepancy levels during interaction. We propose a systematic method to study human behavior indicators for assessing discrepancies. An exploratory study that involved 36 participants interacting with a robot revealed that the smaller the discrepancy level between robot and human, the more efficient and successful the interactions are, despite vague or short robot instructions. The findings of the exploratory study were used to implement and train hidden Markov models to estimate varying levels of discrepancy. With this model, a robot may continuously assess the discrepancy during an interaction and adapt its behavior aiming to decrease discrepancy.

The deployment of robots in environments shared with humans implies that they must be able to justify or explain their behavior to nonexpert users when the user, or the situation itself, requires it. We propose a framework for robots to generate personalized explanations of their behavior by integrating cause-and-effect structures, social roles, and natural language queries. Robot events are stored as cause–effect pairs in a causal log. Given a human natural language query, the system uses machine learning to identify the matching cause-and-effect entry in the causal log and determine the social role of the inquirer. An initial explanation is generated and is then further refined by a large language model (LLM) to produce linguistically diverse responses tailored to the social role and the query. This approach maintains causal and factual accuracy while providing language variation in the generated explanations. Qualitative and quantitative experiments show that combining the causal information with the social role and the query when generating the explanations yields the most appreciated explanations.

In recent years, there has been growing interest in developing robots capable of explaining their behavior, thereby improving their acceptance by humans with whom they share their environment. Proposed software designs are typically based on the advances being made in conversational systems built on deep learning techniques. However, apart from the ability to formulate explanations, the robot also needs an internal episodic memory, where it stores information from the continuous stream of experiences. Most previous proposals are designed to deal with short streams of episodic data (several minutes long). With the aim of managing larger experiences, we propose in this work a high-level episodic memory, where relevant events are abstracted to natural language concepts. The proposed framework is intimately linked to a software architecture in which the explanations, whether externalized or not, are shaped internally in a collaborative process involving the task-oriented software agents that make up the architecture. The core of this process is a runtime knowledge model, employed as working memory whose evolution allows for capturing the causal events stored in the episodic memory. We present several use cases that illustrate how the suggested framework allows an autonomous robot to generate correct and relevant explanations of its actions and behavior.

This study investigates user experiences of interactions with two types of robots: Pepper, a social humanoid robot, and Double 3, a self-driving telepresence robot. Conducted in a controlled setting with a specific participant group, this research aims to understand how the design and functionality of these robots influence user perception, interaction patterns, and emotional responses. The findings reveal diverse participant reactions, highlighting the importance of adaptability, effective communication, autonomy, and perceived credibility in robot design. Participants showed mixed responses to human-like emotional displays and expressed a desire for robots capable of more nuanced and reliable behaviors. Trust in robots was influenced by their perceived functionality and reliability. Despite limitations in sample size, the study provides insights into the ethical and social considerations of integrating AI in public and professional spaces, offering guidance for enhancing user-centered designs and expanding applications for social and telepresence robots in society.

This study investigates user experiences of interaction with two types of robots: Pepper, a social humanoid robot, and Double 3, a self-driving telepresence robot. Conducted in a controlled setting with a specific participant group, this research aims to understand how different robot embodiments affect user perception, interaction patterns, and emotional responses. The findings underscore the role of adaptability, effective communication, autonomy, and perceived credibility in user-centered robot design. Despite limitations in sample size, the study provides insights into the ethical and social considerations of integrating AI in public and professional spaces, highlighting implications for enhancing user-centered design and expanding applications for Social and Telepresence robots in society.

This paper presents a taxonomy of agents’ embodiment in physical and virtual environments. It categorizes embodiment based on five entities: the agent being embodied, the possible mediator of the embodiment, the environment in which sensing and acting take place, the degree of body, and the intertwining of body, mind, and environment. The taxonomy is applied to a wide range of embodiment of humans, artifacts, and programs, including recent technological and scientific innovations related to virtual reality, augmented reality, telepresence, the metaverse, digital twins, and large language models. The presented taxonomy is a powerful tool to analyze, clarify, and compare complex cases of embodiment. For example, it makes the choice between a dualistic and non-dualistic perspective of an agent’s embodiment explicit and clear. The taxonomy also aided us to formulate the term “embodiment by proxy” to denote how seemingly non-embodied agents may affect the world by using humans as “extended arms”. We also introduce the concept “off-line embodiment” to describe large language models’ ability to create an illusion of human perception.

We investigate interaction patterns for humans interacting with explainable and non-explainable robots. Non-explainable robots are here robots that do not explain their actions or non-actions, neither do they give any other feedback during interaction, in contrast to explainable robots. We video recorded and analyzed human behavior during a board game, where 20 humans verbally instructed either an explainable or non-explainable Pepper robot to move objects on the board. The transcriptions and annotations of the videos were transformed into transactions for association rule mining. Association rules discovered communication patterns in the interaction between the robots and the humans, and the most interesting rules were also tested with regular chi-square tests. Some statistically significant results are that there is a strong correlation between men and non-explainable robots and women and explainable robots, and that humans mirror some of the robot's modality. Our results also show that it is important to contextualize human interaction patterns, and that this can be easily done using association rules as an investigative tool. The presented results are important when designing robots that should adapt their behavior to become understandable for the interacting humans.

The ability to understand the surrounding environment and being able to communicate with interacting humans are important functionalities for many automated systems where visual input (e.g., images, video) and natural language input (speech or text) have to be related to each other. Possible applications are automatic image caption generation, interactive surveillance systems, or human robot interaction. In this paper, we propose algorithms for automatic responses to natural language queries about an image. Our approach uses a predefined neural net for detection of bounding boxes and objects in images, spatial relations between bounding boxes are modeled with a neural net, the queries are analyzed with a syntactic parser, and algorithms to map natural language to properties in the images are introduced. The algorithms make use of semantic similarity and antonyms. We evaluate the performance of our approach with test users assessing the quality of our system’s generated answers.