ERR@HRI 2024 Challenge: Multimodal Detection of Errors and Failures in Human-Robot Interactions

Despite the recent advancements in robotics and machine learning (ML), the deployment of autonomous robots in our everyday lives is still an open challenge. This is due to multiple reasons among which are their frequent mistakes, such as interrupting people or having delayed responses, as well as their limited ability to understand human speech, i.e., failure in tasks like transcribing speech to text. These mistakes may disrupt interactions and negatively influence human perception of these robots. To address this problem, robots need to have the ability to detect human-robot interaction (HRI) failures. The ERR@HRI 2024 challenge tackles this by offering a benchmark multimodal dataset of robot failures during human-robot interactions (HRI), encouraging researchers to develop and benchmark multimodal machine learning models to detect these failures. We created a dataset featuring multimodal non-verbal interaction data, including facial, speech, and pose features from video clips of interactions with a robotic coach, annotated with labels indicating the presence or absence of robot mistakes, user awkwardness, and interaction ruptures, allowing for the training and evaluation of predictive models. Challenge participants have been invited to submit their multimodal ML models for detection of robot errors and to be evaluated against various performance metrics such as accuracy, precision, recall, F1 score, with and without a margin of error reflecting the time-sensitivity of these metrics. The results of this challenge will help the research field in better understanding the robot failures in human-robot interactions and designing autonomous robots that can mitigate their own errors after successfully detecting them.

Designing Social Robots that Engage Older Adults in Exercise: A Case Study

We present and evaluate a prototype social robot to encourage daily exercise among older adults in a home setting. Our prototype system, designed to lead users through exercise sessions with motivational feedback, was assessed through a case study with a 78-year-old participant for one week. Our case study highlighted preferences for greater user control over exercise choices and questioned the necessity of precise motion tracking. Feedback also indicated a desire for more varied exercises and suggested improvements in user engagement techniques. The insights suggest that further research is needed to enhance system adaptability and effectiveness to better promote daily exercise. Future efforts will aim to refine the prototype based on participant feedback and extend the evaluation to broader in-home deployments.

"You Might Like It": How People Respond to Small Talk in Human-Robot Collaboration

In this work, we investigate people's engagement and attitudes towards a non-anthropomorphic robot manipulator that initiates small talk with the user during a collaborative assembly task, and explore how the presence of negative team feedback may affect team dynamics and blame attribution. Through an exploratory study with 20 participants, we found that 18 individuals interacted socially with the robot, nine of which initiated questions back to the robot. We report the frequency and length of users' responses in task-oriented and non-task-oriented dialogue, and further elaborate on people's reactions to the negative system feedback and robot-initiated small talk. We discuss the potential for integrating small talk in non-social robots, and propose three design guidelines to enhance human-robot small talk interactions.

An Introduction to Causal Inference Methods for Observational Human-Robot Interaction Research

Quantitative methods in Human-Robot Interaction (HRI) research have primarily relied upon randomized, controlled experiments in laboratory settings. However, such experiments are not always feasible when external validity, ethical constraints, and ease of data collection are of concern. Furthermore, as consumer robots become increasingly available, increasing amounts of real-world data will be available to HRI researchers, which prompts the need for quantative approaches tailored to the analysis of observational data. In this article, we present an alternate approach towards quantitative research for HRI researchers using methods from causal inference that can enable researchers to identify causal relationships in observational settings where randomized, controlled experiments cannot be run. We highlight different scenarios that HRI research with consumer household robots may involve to contextualize how methods from causal inference can be applied to observational HRI research. We then provide a tutorial summarizing key concepts from causal inference using a graphical model perspective and link to code examples throughout the article, which are available at https://gitlab.com/causal/causal_hri. Our work paves the way for further discussion on new approaches towards observational HRI research while providing a starting point for HRI researchers to add causal inference techniques to their analytical toolbox.

Designing AI Support for Human Involvement in AI-assisted Decision Making: A Taxonomy of Human-AI Interactions from a Systematic Review

Efforts in levering Artificial Intelligence (AI) in decision support systems have disproportionately focused on technological advancements, often overlooking the alignment between algorithmic outputs and human expectations. To address this, explainable AI promotes AI development from a more human-centered perspective. Determining what information AI should provide to aid humans is vital, however, how the information is presented, e. g., the sequence of recommendations and the solicitation of interpretations, is equally crucial. This motivates the need to more precisely study Human-AI interaction as a pivotal component of AI-based decision support. While several empirical studies have evaluated Human-AI interactions in multiple application domains in which interactions can take many forms, there is not yet a common vocabulary to describe human-AI interaction protocols. To address this gap, we describe the results of a systematic review of the AI-assisted decision making literature, analyzing 105 selected articles, which grounds the introduction of a taxonomy of interaction patterns that delineate various modes of human-AI interactivity. We find that current interactions are dominated by simplistic collaboration paradigms and report comparatively little support for truly interactive functionality. Our taxonomy serves as a valuable tool to understand how interactivity with AI is currently supported in decision-making contexts and foster deliberate choices of interaction designs.

Forgetful Large Language Models: Lessons Learned from Using LLMs in Robot Programming

Large language models offer new ways of empowering people to program robot applications-namely, code generation via prompting. However, the code generated by LLMs is susceptible to errors. This work reports a preliminary exploration that empirically characterizes common errors produced by LLMs in robot programming. We categorize these errors into two phases: interpretation and execution. In this work, we focus on errors in execution and observe that they are caused by LLMs being "forgetful" of key information provided in user prompts. Based on this observation, we propose prompt engineering tactics designed to reduce errors in execution. We then demonstrate the effectiveness of these tactics with three language models: ChatGPT, Bard, and LLaMA-2. Finally, we discuss lessons learned from using LLMs in robot programming and call for the benchmarking of LLM-powered end-user development of robot applications.

Older Adults' Task Preferences for Robot Assistance in the Home

Artificial intelligence technologies that can assist with at-home tasks have the potential to help older adults age in place. Robot assistance in particular has been applied towards physical and cognitive support for older adults living independently at home. Surveys, questionnaires, and group interviews have been used to understand what tasks older adults want robots to assist them with. We build upon prior work exploring older adults' task preferences for robot assistance through field interviews situated within older adults' aging contexts. Our findings support results from prior work indicating older adults' preference for physical assistance over social and care-related support from robots and indicating their preference for control when adopting robot assistance, while highlighting the variety of individual constraints, boundaries, and needs that may influence their preferences.

Multimodal Robot Programming by Demonstration: A Preliminary Exploration

Recent years have seen a growth in the number of industrial robots working closely with end-users such as factory workers. This growing use of collaborative robots has been enabled in part due to the availability of end-user robot programming methods that allow users who are not robot programmers to teach robots task actions. Programming by Demonstration (PbD) is one such end-user programming method that enables users to bypass the complexities of specifying robot motions using programming languages by instead demonstrating the desired robot behavior. Demonstrations are often provided by physically guiding the robot through the motions required for a task action in a process known as kinesthetic teaching. Kinesthetic teaching enables users to directly demonstrate task behaviors in the robot's configuration space, making it a popular end-user robot programming method for collaborative robots known for its low cognitive burden. However, because kinesthetic teaching restricts the programmer's teaching to motion demonstrations, it fails to leverage information from other modalities that humans naturally use when providing physical task demonstrations to one other, such as gaze and speech. Incorporating multimodal information into the traditional kinesthetic programming workflow has the potential to enhance robot learning by highlighting critical aspects of a program, reducing ambiguity, and improving situational awareness for the robot learner and can provide insight into the human programmer's intent and difficulties. In this extended abstract, we describe a preliminary study on multimodal kinesthetic demonstrations and future directions for using multimodal demonstrations to enhance robot learning and user programming experiences.

Modeling Human Response to Robot Errors for Timely Error Detection

In human-robot collaboration, robot errors are inevitable -- damaging user trust, willingness to work together, and task performance. Prior work has shown that people naturally respond to robot errors socially and that in social interactions it is possible to use human responses to detect errors. However, there is little exploration in the domain of non-social, physical human-robot collaboration such as assembly and tool retrieval. In this work, we investigate how people's organic, social responses to robot errors may be used to enable timely automatic detection of errors in physical human-robot interactions. We conducted a data collection study to obtain facial responses to train a real-time detection algorithm and a case study to explore the generalizability of our method with different task settings and errors. Our results show that natural social responses are effective signals for timely detection and localization of robot errors even in non-social contexts and that our method is robust across a variety of task contexts, robot errors, and user responses. This work contributes to robust error detection without detailed task specifications.

INTRPRT: A Systematic Review of and Guidelines for Designing and Validating Transparent AI in Medical Image Analysis

Transparency in Machine Learning (ML), attempts to reveal the working mechanisms of complex models. Transparent ML promises to advance human factors engineering goals of human-centered AI in the target users. From a human-centered design perspective, transparency is not a property of the ML model but an affordance, i.e. a relationship between algorithm and user; as a result, iterative prototyping and evaluation with users is critical to attaining adequate solutions that afford transparency. However, following human-centered design principles in healthcare and medical image analysis is challenging due to the limited availability of and access to end users. To investigate the state of transparent ML in medical image analysis, we conducted a systematic review of the literature. Our review reveals multiple severe shortcomings in the design and validation of transparent ML for medical image analysis applications. We find that most studies to date approach transparency as a property of the model itself, similar to task performance, without considering end users during neither development nor evaluation. Additionally, the lack of user research, and the sporadic validation of transparency claims put contemporary research on transparent ML for medical image analysis at risk of being incomprehensible to users, and thus, clinically irrelevant. To alleviate these shortcomings in forthcoming research while acknowledging the challenges of human-centered design in healthcare, we introduce the INTRPRT guideline, a systematic design directive for transparent ML systems in medical image analysis. The INTRPRT guideline suggests formative user research as the first step of transparent model design to understand user needs and domain requirements. Following this process produces evidence to support design choices, and ultimately, increases the likelihood that the algorithms afford transparency.