Högskolan i Skövde

The human–robot interaction (HRI) field goes beyond the mere technical aspects of developing robots, often investigating how humans perceive robots. Human perceptions and behavior are determined, in part, by expectations. Given the impact of expectations on behavior, it is important to understand what expectations individuals bring into HRI settings and how those expectations may affect their interactions with the robot over time. For many people, social robots are not a common part of their experiences, thus any expectations they have of social robots are likely shaped by other sources. As a result, individual expectations coming into HRI settings may be highly variable. Although there has been some recent interest in expectations within the field, there is an overall lack of empirical investigation into its impacts on HRI, especially in-person robot interactions. To this end, a within-subject in-person study () was performed where participants were instructed to engage in open conversation with the social robot Pepper during two 2.5 min sessions. The robot was equipped with a custom dialogue system based on the GPT-3 large language model, allowing autonomous responses to verbal input. Participants’ affective changes towards the robot were assessed using three questionnaires, NARS, RAS, commonly used in HRI studies, and Closeness, based on the IOS scale. In addition to the three standard questionnaires, a custom question was administered to capture participants’ views on robot capabilities. All measures were collected three times, before the interaction with the robot, after the first interaction with the robot, and after the second interaction with the robot. Results revealed that participants to large degrees stayed with the expectations they had coming into the study, and in contrast to our hypothesis, none of the measured scales moved towards a common mean. Moreover, previous experience with robots was revealed to be a major factor of how participants experienced the robot in the study. These results could be interpreted as implying that expectations of robots are to large degrees decided before interactions with the robot, and that these expectations do not necessarily change as a result of the interaction. Results reveal a strong connection to how expectations are studied in social psychology and human-human interaction, underpinning its relevance for HRI research.

This paper explores the complex and time-critical work practices within operational train traffic in Sweden by reporting on an incident causing an infrastructure breakdown and large traffic disruptions. Based on a workplace study approach, we report on how the control room workers – train traffic controllers and information officers – grasp, make sense of, and handle the consequences of the incident as it unfolds in real-time. We portray how the workers develop and acquire a sense of place in relation to the incident’s severity which is essential for successfully handling the situation. By introducing the ‘sense of place’ concept originally derived from the field of natural resources to the domain of operational train traffic, we provide a deepened understanding of the challenges characterising remote control work from a safety-critical socio-technical systems perspective. Finally, reflections on the application of the ‘sense of place’ concept, safety aspects and directions for future research are provided.

Expectations shape our experience with the world, including our interaction with technology. There is a mismatch between whathumans expect of social robots and what they are actually capable of.Expectations are dynamic and can change over time. We have previ- AQ1ously developed a framework for studying these expectations over timein human-robot interaction (HRI). In this work, we applied the socialrobot expectation gap evaluation framework in an HRI scenario from aUX evaluation perspective, by analyzing a subset of data collected froma larger experiment. The framework is based on three factors of expectation: affect, cognitive processing, as well as behavior and performance. Four UX goals related to a human-robot interaction scenario were evaluated. Results show that expectations change over time with an overallimproved UX in the second interaction. Moreover, even though some UX goals were partly fulfilled, there are severe issues with the conversation between the user and the robot, ranging from the quality of theinteraction to the users’ utterances not being recognized by the robot.This work takes the initial steps towards disentangling how expectations work and change over time in HRI. Future work includes expanding the metrics to study expectations and to further validate the framework.

The benefits of feeding calves more milk are increasingly being recognized by dairy farmers. However, most producers have still not implemented higher feeding plans. The aim of the present study was to gain a deeper understanding of farmer and farm staff attitudes, and the perceptions and factors considered in their decision-making regarding daily milk allowances. We collected data through focus group interviews with dairy farmers, farm managers, and calf-care workers who were selected using purposive and snowball sampling. In total, 40 persons (24 women and 16 men) joined a focus group interview (6 in all, each with 5–8 participants). Interviews were recorded, and recordings were transcribed and analyzed thematically. Participants had contrasting opinions about the minimum, maximum, and recommended daily milk allowances to their calves. Their suggested lowest daily milk allowance to sustain animal welfare ranged from 4 to 8–10 L and the maximum allowance from 6 to 15 L. We found that farmers' and farm staff's choices and recommendations of milk-feeding protocols were influenced by a large number of factors that could be grouped into 4 themes: (1) Life beyond work, (2) Farm facilities and equipment, (3) Care of the calves, and (4) Profitability and production. Participants' considerations were similar and aimed to maximize daily milk allowance based on farm conditions. However, the allowances they described as optimal for their calves often differed from what they considered practically feasible. We found that the care of the calves and the well-being of the owners and the staff was central in the participants' decision-making, but that this care perspective was challenged by the social and economic sustainability of the farm. Most participants fed their calves twice daily and did not think that increasing that number would be practically feasible. Our results indicate that the participants' viewpoints regarding calves were important for their decision-making about milk allowances. We suggest that a more holistic perspective should be used when advising farmers about milk allowances, putting particular emphasis on the caring and social sustainability aspects of the individual farm. 

The industrial evolutions require robots to be able to share physical and social space with humans in such a way that interaction and coexistence arepositively experienced by human workers. A prerequisite is the possibility for the human and the robot to mutually perceive, interpret and act on each other's actions and intentions. To achieve this, strategies for human-robot interaction are needed that are adapted to operators’ needs and characteristics in the industrial contexts. In this paper, we aim to present various taxonomies of levels of automation, humanrobot interaction, and human-robot collaboration suggested for the envisioned factories of the future. Based on this foundation, we propose a compass direction for continued research efforts which both zooms in and zooms out on how to develop applicable human-robot interaction strategies that are worker-centric in order to obtain effective, efficient, safe, sustainable, and pleasant human-robot collaboration and coexistence.

The industrial transition to Industrie 4.0 and subsequently Industrie 5.0 requires robots to be able to share physical and social space with humans in such a way that interaction and coexistence are positively experienced by the humans and where it is possible for the human and the robot to mutually perceive, interpret and act on each other's actions and intentions. To achieve this, strategies for humanrobot interaction are needed that are adapted to operators’ needs and characteristics in an industrial context, i.e., Operator 5.0. This paper presents a research design for the development of a framework for human-robot interaction strategies based on ANEMONE, which is an evaluation framework based on activity theory, the seven stages of action model, and user experience (UX) evaluation methodology. At two companies, ANEMONE is applied in two concrete use cases, collaborative kitting and mobile robot platforms for chemical laboratory assignments. The proposed research approach consists of 1) evaluations of existing demonstrators, 2) development of preliminary strategies that are implemented, 3) re-evaluations and 4) cross-analysis of results to produce an interaction strategy framework. The theoretically and empirically underpinned framework-to-be is expected to, in the long run, contribute to a sustainable work environment for Operator 5.0.

Pedagogisk meritering får en mer central plats inom högre utbildning. Dels finns det ettpågående krav från studentperspektivet där Sveriges förenade studentkårer (SFS) driverett arbete för en god undervisningskvalitet (SFS-webb). Dels ambitionen att sträva efteren hög kvalitet i den pedagogiska praktiken utifrån ett akademiskt lärarskap (Kreber,2002) vilket ska främja ett vetenskapligt förhållningssätt till studenternas lärande, bådehos lärarna samt även i organisationen. Genom att fokusera på pedagogisk meritering ärdetta ett sätt att låta dessa perspektiv mötas. Lindblom och Kjellström (2018)presenterade revidering samt vidareutveckling av innehållet i och processerna förpedagogisk meritering vid Högskolan i Skövde med syftet att meritera engagerade,kunniga och ämneskompetenta lärare utifrån ett akademiskt lärarskap. Målet medpedagogiska karriärstege är att kompetensutveckla och bedöma ämneskunniga läraresskicklighet i att bedriva pedagogisk verksamhet i praktiken (Dnr HS 2021/43). Syftet med detta bidrag är att beskriva samt reflektera över möjligheter och utmaningarsom vi i våra roller stött på från 2018 till idag. Vi presenterar resultatet av det kontinuerliga lärande som sker hos de personer som arbetar med att stötta och geåterkoppling på de inkomna pedagogiska portföljerna samt vilka utmaningar vi haridentifierat som de sökande brottas med och hur vi försöker hantera dem på ett trovärdigtsätt. Några av de utmaningar som vi identifierat via samtal och intervjuer är lärarnas svårighetatt sätta ord på sin tysta kunskap och att relatera denna kunskap till en pedagogiskgrundsyn som de kanske för första gången som lärare söker formulera. Det är synligt hurspråket har en betydelsefull roll för utvecklandet av kunskap hos den enskilde läraren men också emellan lärarna (Molander, 1993) i samband med skrivandet av portföljen. En annan utmaning som vi sett är att den kritiska reflektionen över sin lärarpraktik och att i någon mån begreppsliggöra sin pedagogiska grundsyn är processer som kan ta tid och innebära olika former av känslor exempelvis frustration, otålighet, tillfredsställelse och glädje. Skrivandet av portföljen och deltagande i workshops kan innebära en kritisk reflektion som leder till ett transformativt lärande (Mezirow, 1990). Att inta ett nyttförhållningssätt till sin lärarpraktik i termer av ett akademiskt lärarskap, ser vi gynnas av att meriteringsprocessen sker i två steg. Första steget är att bli meriterad lärare, därefter sker en tid då läraren använder sin nya kunskap om akademiskt lärarskap. Genom att omsätta den nya kunskapen i praktiken blir arbetet med portföljen för nivån excellent medvetet, insiktsfullt och strategiskt.

Referenser

Dnr HS 2021/43. Riktlinjer för pedagogisk karriärstege vid Högskolan i Skövde.

Lindblom, J och Kjellström, A. (2018). Pedagogisk meritering och pedagogiskkarriärstege utifrån ett akademiskt lärarskap. NU 2018: Det akademiska lärarskapet,artikel-id: 829

Kreber, C. (2002). Teaching excellence, teaching expertise, and the scholarship of teaching.Innovative Higher Education, 27(1), pp. 5-23.

Mezirow, J. (1990). Fostering Critical Reflection in Adulthood. San Francisco: Jossey-Bass

Molander, B. (1993). Kunskap i handling. Stockholm: Daidalos.

SFS:s webb: h ttps://sfs.se/var-politik/hogskolepedagogik/

Social robots are designed in manners that encourage users to interact and communicate with them in socially appropriate ways, which implies that these robots should copy many social human behaviors to succeed in social settings. However, this approach has implications for what humans subsequently expect from these robots. There is a mismatch between expected capabilities and actual capabilities of social robots. Expectations of social robots are thus of high relevance for the field of Human-Robot Interaction (HRI). While there is recent interest of expectations in the HRI field there is no widely adapted or well formulated evaluation framework that offers a deeper understanding of how these expectations affect the success of the interaction. With basis in social psychology, user experience, and HRI, we have developed an evaluation framework for studying users’ expectations of social robots. We have identified three main factors of expectations for assessing HRI: affect, cognitive processing, and behavior and performance. In our framework, we propose several data collection techniques and specific metrics for assessing these factors. The framework and its procedure enables analysis of the collected data via triangulation to identify problems and insights, which can grant us a richer understanding of the complex facets of expectations, including if the expectations were confirmed or disconfirmed in the interaction. Ultimately, by gaining a richer understanding of how expectations affect HRI, we can narrow the social robot expectation gap and create more successful interactions between humans and social robots in society. 

The ANEMONE is a methodological approach for user experience (UX) evaluation of action and intention recognition in human-robot interaction that has activity theory as its theoretical lens in combination with the seven stages of action model and UX evaluation methodology. ANEMONE has been applied in a case where a prototype has been evaluated. The prototype was a workstation in assembly in manufacturing consisting of a collaborative robot, a pallet, a tablet, and a workbench, where one operator is working in the same physical space as one robot. The purpose of this paper is to provide guidance on how to use ANEMONE, with a particular focus on the data analysis part, through describing a real example together with lessons learned and recommendations.

Context

In Sweden, 34% of herds in official statistics 2021 (77% of the cows) have an automatic milking system (AMS) and keep 19% of the dairy cows.

Objective

This study should be considered in relation to the rapid increase of digitalisation in agriculture. It aimed at investigating Swedish farmers’ experiences and reflections in dairy farming concerning AMS use from a care perspective, based on two research questions: 1) What kinds of success factors and management challenges do farmers experience with AMS usage? and 2) How do farmers view their work environment in this kind of system?

Methods

A mixed method approach was performed, using method triangulation through a questionnaire, interviews, and field visits. The Activity Theory (AT) was used as a theoretical lens to consider care practice in the dairy farming as a learning system.

Results and conclusions

Participating dairy farmers were found to be in a continuous learning process on different levels in their system, from detailed problems with an individual cow or the herd to the whole dairy system. Implementation of AMS required learning in order to manage, and thus care for, a system comprising of animals, technology, and humans, to increase business viability. In successful AMS use, willingness to learn, adapt to the local situation, and continually improve practice, or care as a patterning of activities, appeared to be the most important factors. With more people involved, differentiations were possible, which in turn accentuated the need for more trained staff who can perform more complicated tasks. The findings indicated high importance of experience and a ‘stockperson's eye’, in combination with tool-mediated seeing using data from the robot, in developing enhanced professional vision and good care. A good stockperson had broad competence combining a stockperson's eye with experience with robot data. One of the greatest challenges for dairy farms was finding a good stockperson as staff or advisor. Increased flexibility in work and better physical health were important driving forces for implementing AMS, while handling alarms was mentally stressful and gave different perspectives on AMS vulnerability. Overall, the analysis of the collected data showed that AMS had brought major, primarily positive, changes in daily work and increased work satisfaction for most farmers, with a clear majority of the respondents feeling good in their work situation and enjoying their work.

Significance

Application of AT in studying AMS from a care perspective, represents a shift from traditional research that normally addresses technological inventions, to studying farmers’ socio-technical system. The AT lens revealed the work practices in performing care, as a patterning of activities accomplished by a tinkering learning process, in the rich and messy matrix of humans, cows, and technology.