Carrillo-Zapata Daniel, Milner Emma, Hird Julian, Tzoumas Georgios, Vardanega Paul J, Sooriyabandara Mahesh, Giuliani Manuel, Winfield Alan F T, Hauert Sabine
Bristol Robotics Laboratory, Bristol, United Kingdom.
University of Bristol, Bristol, United Kingdom.
Front Robot AI. 2020 Apr 21;7:53. doi: 10.3389/frobt.2020.00053. eCollection 2020.
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.
群体机器人技术文献中已经提出了许多实际应用。然而，对于机器人集群要在现实中对用户有用并值得信赖需要做些什么，人们普遍缺乏了解。本文旨在调查用户对工作场所中机器人集群的看法，并为未来集群在实际应用中的部署提供设计原则。我们在消防救援、仓储管理和桥梁检测这三个领域开展了三项定性研究，共有37名参与者。每项研究都通过焦点小组和访谈来考察用户的看法。在本文中，我们描述了我们的研究结果，内容涉及：这些行业目前使用的流程和工具及其主要挑战；对机器人集群协助他们工作的态度；以及鼓励他们使用机器人集群的要求。我们发现，对于机器人集群用于信息收集和简单流程的自动化，人们普遍持积极态度。此外，在决策方面，人们更倾向于有人参与其中。提高信任度和接受度的建议涉及透明度、问责制、安全性、可靠性、易于维护和易于使用。最后，我们发现相互塑造是一种在用户和技术开发者之间建立双向关系，以便在研发的各个阶段纳入社会选择的方法，是增加对群体机器人技术的了解和接受度的有效途径。本文有助于在研究人员和用户之间营造这种相互塑造的文化，以增加机器人集群在现实领域成功部署的机会。
