Working with roubles and failures in conversation between humans and robots: workshop report.

This paper summarizes the structure and findings from the first Workshop on Troubles and Failures in Conversations between Humans and Robots. The workshop was organized to bring together a small, interdisciplinary group of researchers working on miscommunication from two complementary perspectives. One group of technology-oriented researchers was made up of roboticists, Human-Robot Interaction (HRI) researchers and dialogue system experts. The second group involved experts from conversation analysis, cognitive science, and linguistics. Uniting both groups of researchers is the belief that communication failures between humans and machines need to be taken seriously and that a systematic analysis of such failures may open fruitful avenues in research beyond current practices to improve such systems, including both speech-centric and multimodal interfaces. This workshop represents a starting point for this endeavour. The aim of the workshop was threefold: Firstly, to establish an interdisciplinary network of researchers that share a common interest in investigating communicative failures with a particular view towards robotic speech interfaces; secondly, to gain a partial overview of the "failure landscape" as experienced by roboticists and HRI researchers; and thirdly, to determine the potential for creating a robotic benchmark scenario for testing future speech interfaces with respect to the identified failures. The present article summarizes both the "failure landscape" surveyed during the workshop as well as the outcomes of the attempt to define a benchmark scenario.

Impact of resolution, colour, and motion on object identification in digital twins from robot sensor data.

This paper makes a contribution to research on digital twins that are generated from robot sensor data. We present the results of an online user study in which 240 participants were tasked to identify real-world objects from robot point cloud data. In the study we manipulated the render style (point clouds vs voxels), render resolution (i.e., density of point clouds and granularity of voxel grids), colour (monochrome vs coloured points/voxels), and motion (no motion vs rotational motion) of the shown objects to measure the impact of these attributes on object recognition performance. A statistical analysis of the study results suggests that there is a three-way interaction between our independent variables. Further analysis suggests: 1) objects are easier to recognise when rendered as point clouds than when rendered as voxels, particularly lower resolution voxels; 2) the effect of colour and motion is affected by how objects are rendered, e.g., utility of colour decreases with resolution for point clouds; 3) an increased resolution of point clouds only leads to an increased object recognition if points are coloured and static; 4) high resolution voxels outperform medium and low resolution voxels in all conditions, but there is little difference between medium and low resolution voxels; 5) motion is unable to improve the performance of voxels at low and medium resolutions, but is able to improve performance for medium and low resolution point clouds. Our results have implications for the design of robot sensor suites and data gathering and transmission protocols when creating digital twins from robot gathered point cloud data.

Mutual Shaping in Swarm Robotics: User Studies in Fire and Rescue, Storage Organization, and Bridge Inspection.

Many real-world applications have been suggested in the swarm robotics literature. However, there is a general lack of understanding of what needs to be done for robot swarms to be useful and trusted by users in reality. This paper aims to investigate user perception of robot swarms in the workplace, and inform design principles for the deployment of future swarms in real-world applications. Three qualitative studies with a total of 37 participants were done across three sectors: fire and rescue, storage organization, and bridge inspection. Each study examined the users' perceptions using focus groups and interviews. In this paper, we describe our findings regarding: the current processes and tools used in these professions and their main challenges; attitudes toward robot swarms assisting them; and the requirements that would encourage them to use robot swarms. We found that there was a generally positive reaction to robot swarms for information gathering and automation of simple processes. Furthermore, a human in the loop is preferred when it comes to decision making. Recommendations to increase trust and acceptance are related to transparency, accountability, safety, reliability, ease of maintenance, and ease of use. Finally, we found that mutual shaping, a methodology to create a bidirectional relationship between users and technology developers to incorporate societal choices in all stages of research and development, is a valid approach to increase knowledge and acceptance of swarm robotics. This paper contributes to the creation of such a culture of mutual shaping between researchers and users, toward increasing the chances of a successful deployment of robot swarms in the physical realm.

Confidence in uncertainty: Error cost and commitment in early speech hypotheses.

Interactions with artificial agents often lack immediacy because agents respond slower than their users expect. Automatic speech recognisers introduce this delay by analysing a user's utterance only after it has been completed. Early, uncertain hypotheses of incremental speech recognisers can enable artificial agents to respond more timely. However, these hypotheses may change significantly with each update. Therefore, an already initiated action may turn into an error and invoke error cost. We investigated whether humans would use uncertain hypotheses for planning ahead and/or initiating their response. We designed a Ghost-in-the-Machine study in a bar scenario. A human participant controlled a bartending robot and perceived the scene only through its recognisers. The results showed that participants used uncertain hypotheses for selecting the best matching action. This is comparable to computing the utility of dialogue moves. Participants evaluated the available evidence and the error cost of their actions prior to initiating them. If the error cost was low, the participants initiated their response with only suggestive evidence. Otherwise, they waited for additional, more confident hypotheses if they still had time to do so. If there was time pressure but only little evidence, participants grounded their understanding with echo questions. These findings contribute to a psychologically plausible policy for human-robot interaction that enables artificial agents to respond more timely and socially appropriately under uncertainty.

Ghost-in-the-Machine reveals human social signals for human-robot interaction.

We used a new method called "Ghost-in-the-Machine" (GiM) to investigate social interactions with a robotic bartender taking orders for drinks and serving them. Using the GiM paradigm allowed us to identify how human participants recognize the intentions of customers on the basis of the output of the robotic recognizers. Specifically, we measured which recognizer modalities (e.g., speech, the distance to the bar) were relevant at different stages of the interaction. This provided insights into human social behavior necessary for the development of socially competent robots. When initiating the drink-order interaction, the most important recognizers were those based on computer vision. When drink orders were being placed, however, the most important information source was the speech recognition. Interestingly, the participants used only a subset of the available information, focussing only on a few relevant recognizers while ignoring others. This reduced the risk of acting on erroneous sensor data and enabled them to complete service interactions more swiftly than a robot using all available sensor data. We also investigated socially appropriate response strategies. In their responses, the participants preferred to use the same modality as the customer's requests, e.g., they tended to respond verbally to verbal requests. Also, they added redundancy to their responses, for instance by using echo questions. We argue that incorporating the social strategies discovered with the GiM paradigm in multimodal grammars of human-robot interactions improves the robustness and the ease-of-use of these interactions, and therefore provides a smoother user experience.

Systematic analysis of video data from different human-robot interaction studies: a categorization of social signals during error situations.

Human-robot interactions are often affected by error situations that are caused by either the robot or the human. Therefore, robots would profit from the ability to recognize when error situations occur. We investigated the verbal and non-verbal social signals that humans show when error situations occur in human-robot interaction experiments. For that, we analyzed 201 videos of five human-robot interaction user studies with varying tasks from four independent projects. The analysis shows that there are two types of error situations: social norm violations and technical failures. Social norm violations are situations in which the robot does not adhere to the underlying social script of the interaction. Technical failures are caused by technical shortcomings of the robot. The results of the video analysis show that the study participants use many head movements and very few gestures, but they often smile, when in an error situation with the robot. Another result is that the participants sometimes stop moving at the beginning of error situations. We also found that the participants talked more in the case of social norm violations and less during technical failures. Finally, the participants use fewer non-verbal social signals (for example smiling, nodding, and head shaking), when they are interacting with the robot alone and no experimenter or other human is present. The results suggest that participants do not see the robot as a social interaction partner with comparable communication skills. Our findings have implications for builders and evaluators of human-robot interaction systems. The builders need to consider including modules for recognition and classification of head movements to the robot input channels. The evaluators need to make sure that the presence of an experimenter does not skew the results of their user studies.