Tamie Salter

Learning about natural human–robot interaction styles

Abstract If we are to achieve natural human–robot interaction, we may need to complement current vision and speech interfaces. Touch may provide us with an extra tool in this quest. In this paper we demonstrate the role of touch in interaction between a robot and a human. We show how infrared sensors located on robots can be easily used to detect and distinguish human interaction, in this case interaction with individual children. This application of infrared sensors potentially has many uses; for example, in entertainment or service robotics. This system could also benefit therapy or rehabilitation, where the observation and recording of movement and interaction is important. In the long term, this technique might enable robots to adapt to individuals or individual types of user.

Going into the wild in child–robot interaction studies: issues in social robotic development

As robots move into more human centric environments we require methods to develop robots that can naturally interact with humans. Doing so requires testing in the real-world and addressing multidisciplinary challenges. Our research is focused on child–robot interaction which includes very young children, for example toddlers, and children diagnosed with autism. More traditional forms of human–robot communication, such as speech or gesture recognition, may not be appropriate with these users, where as touch may help to provide a more natural and appropriate means of communication for such instances. In this paper, we present our findings on these topics obtained from a project involving a spherical robot that acquires information regarding natural touch from analysing sensory patterns over-time to characterize the information. More specifically, from this project we have derived important factors for future consideration, we describe our iterative experimental methodology of testing in and out of the ‘wild’ (lab based and real world), and outline discoveries that were made by doing so.

Towards adaptive autonomous robots in autism therapy: varieties of interactions

This paper reports results deriving from the Aurora project (www.aurora-project.com) where we have pioneered research into the possible use of robots in autism therapy. Autistic children have difficulties in social interaction, communication and fantasy and imagination. As part of the project we run trials where autistic children are playing with a small, non-humanoid mobile robot that can engage children in simple interaction games. In our project we focus on the behavioural, rather than the affective level of robots used in therapy. In this paper we first discuss in more detail varieties of interactions where one child, or two children simultaneously, play with a robot. We then outline a new research direction in the project which studies how a mobile robot can adapt to individual children. Quantitative examples of activity levels in child-robot interactions are included. The paper concludes by outlining future research directions for adaptive robots in autism therapy.

Robots moving out of the laboratory - detecting interaction levels and human contact in noisy school environments

To achieve natural human-robot interaction, robots need to distinguish humans from other parts of the environment. We investigate how infrared sensors currently being used on a mobile robot can be used to distinguish human interaction. Different from the previous work, that had been conducted under laboratory conditions involving selected children, the current study took place in noisy school environments with a mix of children. Also, while in previous work each child was only exposed once to the robot in the current longitudinal study, each child encounters the robot five times. The technique that we developed previously for detecting human contact still proved to be reliable, however, results are not as clear-cut, due to noisy and rather unstructured environments that interfered with the robots sensor readings. We discuss expected as well as unexpected results in light of the challenge to develop robots that can operate under real-life conditions.

Recognizing interaction from a robot's perspective

For meaningful interaction between a robot and a human, an autonomous robot must recognize whether the experienced situation is created by people or by the environment. Using only proprioceptive data from a mobile robotic platform, we discover that it is possible to distinguish sensory data patterns involving interaction. These patterns are obtained whilst navigating varying environments, both human populated and unpopulated. The paper reports the initial set of trials using Roball, a spherical mobile robot. Also described is the experimental methodology currently followed to validate the hypothesis that child interaction can be perceived directly from navigation sensors onboard a robotic platform.

Using proprioceptive sensors for categorizing human-robot interactions

Increasingly researchers are looking outside of normal communication channels (such as video and audio) to provide additional forms of communication or interaction between a human and a robot, or a robot and its environment. Amongst the new channels being investigated is the detection of touch using infrared, proprioceptive and temperature sensors. Our work aims at developing a system that can detect natural touch or interaction coming from children playing with a robot, and adapt to this interaction. This paper reports trials carried out using Roball, a spherical mobile robot, demonstrating how sensory data patterns can be identified in human-robot interaction, and exploited for achieving behavioral adaptation. The experimental methodology used for these trials is reported, which validated the hypothesis that human interaction can not only be perceived from proprioceptive sensors on-board a robotic platform, but that this perception has the ability to lead to adaptation.

Perspectives on Mobile Robots as Tools for Child Development and Pediatric Rehabilitation

Mobile robots (i.e., robots capable of translational movements) can be designed to become interesting tools for child development studies and pediatric rehabilitation. In this article, the authors present two of their projects that involve mobile robots interacting with children: One is a spherical robot deployed in a variety of contexts, and the other is mobile robots used as pedagogical tools for children with pervasive developmental disorders. Locomotion capability appears to be key in creating meaningful and sustained interactions with children: Intentional and purposeful motion is an implicit appealing factor in obtaining childrens attention and engaging them in interaction and learning. Both of these projects started with robotic objectives but are revealed to be rich sources of interdisciplinary collaborations in the field of assistive technology. This article presents perspectives on how mobile robots can be designed to address the requirements of child-robot interactions and studies. The authors also argue that mobile robot technology can be a useful tool in rehabilitation engineering, reaching its full potential through strong collaborations between roboticists and pediatric specialists.

How wild is wild? A taxonomy to characterize the ‘wildness’ of child-robot interaction

When thinking about Child-Robot Interaction (CRI) in the ‘wild’ or natural settings, many ideas come to mind, such as a home or a school that involve chaotic settings with autonomous robotic devices and people that are freely interacting with them. However, there certainly are degrees of ‘wild’, and different experimental settings can have varying levels of control in place. It would be helpful to have a common framework to interpret and identify the many different influencing factors or levels of control surrounding CRI experimentation. Having a framework to help towards standardizing evaluation of CRI studies would benefit researchers wishing to identify or plan the varying dimensions present in CRI experimentation. This paper presents a simple taxonomy to characterize the ‘wildness’ factors in CRI over two main dimensions (Participant and Robotic) that can effect the overall outcome of such studies. The use of this taxonomy is illustrated by its application to current CRI research. Specifically, we use it in reflection to rate six of our CRI trials that have been conducted over a ten year period. From the classification of these studies, a general view of our work so far is outlined and new research perspectives are identified. The application of the taxonomy is also validated by reviewing a selection of other CRI studies.

Guidelines for robot-human environments in therapy

In This work we propose guidelines for environmental conditions when using autonomous mobile robots in therapy. We investigate readings from infrared sensors on-board a mobile robot whilst the robot is maneuvering in noisy cluttered environments. Suggestions on how to structure the environment to minimise noise within the robots sensor readings are given. Effect of different environmental conditions on the infrared readings are catalogued, including boxes and chairs. Specifically, we investigate under what conditions a method developed by Salter et al., which, used infrared sensors to distinguish between the environment and human contact, is reliable. We also discuss related research and how the guidelines proposed here might extend past proposals for using robots in therapy situations to general robot-human environments.

What are the benefits of adaptation when applied in the domain of child-robot interaction?

There is great potential for robotic devices when being applied with children. They can be used from play to assistive applications. We develop robotic devices for a diverse range of children that differ in age, gender and ability, which includes children that are diagnosed with cognitive difficulties such as autism. Every child is an individual and they vary in their personalities and styles of interaction. Therefore, being able to adjust the robots behaviour to the type of interaction it is receiving was believed to be essential. In this abstract we examine a series of trials which investigated how adaptation (through changes in motion and sound) on a fully autonomous rolling robot could help gain and sustain the interest of five different children. We discovered surprising benefits to having adaptation on-board Roball.