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.

Continuously measuring the engagement of users with a robot in a Human-Robot Interaction (HRI) setting paves the way toward in-situ reinforcement learning, improve metrics of interaction quality, and can guide interaction design and behavior optimization. However, engagement is often considered very multi-faceted and difficult to capture in a workable and generic computational model that can serve as an overall measure of engagement. Building upon the intuitive ways humans successfully can assess situation for a degree of engagement when they see it, we propose a novel regression model (utilizing CNN and LSTM networks) enabling robots to compute a single scalar engagement during interactions with humans from standard video streams, obtained from the point of view of an interacting robot. The model is based on a long-term dataset from an autonomous tour guide robot deployed in a public museum, with continuous annotation of a numeric engagement assessment by three independent coders. We show that this model not only can predict engagement very well in our own application domain but show its successful transfer to an entirely different dataset (with different tasks, environment, camera, robot and people). The trained model and the software is available to the HRI community, at https://github.com/LCAS/engagement_detector, as a tool to measure engagement in a variety of settings.

In this paper, we present a human-in-the-loop learning framework for mobile robots to generate effective local policies in order to recover from navigation failures in longterm autonomy. We present an analysis of failure and recovery cases derived from long-term autonomous operation of a mobile robot, and propose a two-layer learning framework that allows to detect and recover from such navigation failures. Employing a learning by demonstration (LbD) approach, our framework can incrementally learn to autonomously recover from situations it initially needs humans to help with. The learning framework allows for both real-time failure detection and regression using Gaussian processes (GPs). Our empirical results on two different failure scenarios indicate that given 40 failure state observations, the true positive rate of the failure detection model exceeds 90%, ending with successful recovery actions in more than 90% of all detected cases.

The use of robots in educational and STEM engagement activities is widespread. In this paper we describe a system developed for engaging learners with the design of dialogue-based interactivity for mobile robots. With an emphasis on a web-based solution that is grounded in both a real robot system and a real application domain-a museum guide robot-our intent is to enhance the benefits to both driving research through potential user-group engagement, and enhancing motivation by providing a real application context for the learners involved. The proposed system is designed to be highly scalable to both many simultaneous users and to users of different age groups, and specifically enables direct deployment of implemented systems onto both real and simulated robots. Our observations from preliminary events, involving both children and adults, support the view that the system is both usable and successful in supporting engagement with the dialogue interactivity problem presented to the participants, with indications that this engagement can persist over an extended period of time.

The agricultural domain offers a working environment where many human laborers are nowadays employed to maintain or harvest crops, with huge potential for productivity gains through the introduction of robotic automation. Detecting and localizing humans reliably and accurately in such an environment, however, is a prerequisite to many services offered by fleets of mobile robots collaborating with human workers. Consequently, in this paper, we expand on the concept of a topological particle filter (TPF) to accurately and individually localize and track workers in a farm environment, integrating information from heterogeneous sensors and combining local active sensing (exploiting a robot's onboard sensing employing a Next-Best-Sense planning approach) and global localization (using affordable IoT GNSS devices). We validate the proposed approach in topologies created for the deployment of robotics fleets to support fruit pickers in a real farm environment. By combining multi-sensor observations on the topological level complemented by active perception through the NBS approach, we show that we can improve the accuracy of picker localization in comparison to prior work.