Lindsey the Tour Guide Robot - Usage Patterns in a Museum Long-Term Deployment

Abstract

The long-term deployment of autonomous robots co-located with humans in real-world scenarios remains a challenging problem. In this paper, we present the "Lindsey" tour guide robot system in which we attempt to increase the social capability of current state-of-the-art robotic technologies. The robot is currently deployed at a museum displaying local archaeology where it is providing guided tours and information to visitors. The robot is operating autonomously daily, navigating around the museum and engaging with the public, with on-site assistance from roboticists only in cases of hardware/software malfunctions. In a deployment lasting seven months up to now, it has travelled nearly 300km and has delivered more than 2300 guided tours. First, we describe the robot framework and the management interfaces implemented. We then analyse the data collected up to now with the goal of understanding and modelling the visitors' behavior in terms of their engagement with the technology. These data suggest that while short-term engagement is readily gained, continued engagement with the robot tour guide is likely to require more refined and robust socially interactive behaviours. The deployed system presents us with an opportunity to empirically address these issues.

Are You Still With Me? Continuous Engagement Assessment From a Robot's Point of View

“…In this section, we briefly report the architecture of the robot system, a description of the robot behaviors and an up-to-date analysis of the deployment. For a more detailed description of these aspects of the project, the reader is redirected to our previous work (Del Duchetto et al, 2019 ).…”

“…Previous work on robot deployment in museum contexts (Del Duchetto et al, 2019 ) provide evidence on how user engagement during robot-guided tours easily degrades with time when employing an open-loop interactive behavior that does not take into account the engagement state of the other (human) parties.…”

Automatic Assessment and Learning of Robot Social Abilities

“…At this stage, we developed the tools necessary for the correct autonomous operations, such as: navigation stack, task scheduling, behavior specification, management and users interface. In our previous work [5] we describe the tools implemented, in particular we want to highlight here the integration of the Petri Net Plans (PNP) formalism [29] into our framework for the goal of specifying the robot behaviors and allowing their adaptation (see Sec. 4).…”

“…The tasks have an average duration of 20 seconds, 2 minutes and 10 minutes respectively, if not stopped by the user before their end. In our study [5], we have analysed the duration of a total of 5232 tasks, started over a period of 103 days of operation. The data suggests that:…”

“…Eliciting engagement during an interaction, and maintaining it after the initial phase of the interaction, is still an issue to be overcome. There is evidence that engagement in learning activities is higher in the presence of a robot, particularly if novel [1], but after the initial engagement state, long and non-interactive behaviors are detrimental to the continued engagement of the users [5,16]. Overcoming this limitation requires to design robots with enhanced social abilities that go past monolithic behaviours and introduces in-situ learning and adaptation to the specific users and situations.…”