Paul Baxter

The use of social robots in therapy for children with autism has been explored for more than 20 years, but there still is limited clinical evidence. The work presented here provides a systematic approach to evaluating both efficacy and effectiveness, bridging the gap between theory and practice by targeting joint attention, imitation, and turn-taking as core developmental mechanisms that can make a difference in autism interventions. We present two randomized clinical trials with different robot-assisted therapy implementations aimed at young children. The first is an efficacy trial ( n = 69; mean age = 4.4 years) showing that 12 biweekly sessions of in-clinic robot-assisted therapy achieve equivalent outcomes to conventional treatment but with a significant increase in the patients’ engagement. The second trial ( n = 63; mean age = 5.9 years) evaluates the effectiveness in real-world settings by substituting the clinical setup with a simpler one for use in schools or homes. Over the course of a modest dosage of five sessions, we show equivalent outcomes to standard treatment. Both efficacy and effectiveness trials lend further credibility to the beneficial role that social robots can play in autism therapy while also highlighting the potential advantages of portable and cost-effective setups.

With the increasing application of robots in human-centred environments, there is increasing motivation for incorporating some degree of human-like social competences. Fields such as psychology and cognitive science not only provide guidance on the types of behaviour that could and should be exhibited by the robots, they may also indicate the manner in which these behaviours can be achieved. The domain of social child–robot interaction (sCRI) provides a number of challenges and opportunities in this regard; the application to an educational context allows child-learning outcomes to be characterised as a result of robot social behaviours. One such social behaviour that is readily (and unconsciously) used by humans is behavioural alignment, in which the behaviours expressed by one person adapts to that of their interaction partner, and vice versa. In this paper, the role that robot non-verbal behavioural alignment for their interaction partner can play in the facilitation of learning outcomes for the child is examined. This behavioural alignment is facilitated by a human memory-inspired learning algorithm that adapts in real-time over the course of an interaction. A large touchscreen is employed as a mediating device between a child and a robot. Collaborative sCRI is emphasised, with the touchscreen providing a common set of interaction affordances for both child and robot. The results show that an adaptive robot is capable of engaging in behavioural alignment, and indicate that this leads to greater learning gains for the children. This study demonstrates the specific contribution that behavioural alignment makes in improving learning outcomes for children when employed by social robot interaction partners in educational contexts.

Robots are interesting because they exist as a real technology that you can really study—you can get a degree in robotics—and they also have all this pop-culture real estate that they take up in people's minds.

The last few decades have seen widespread advances in technological means to characterise observable aspects of human behaviour such as gaze or posture. Among others, these developments have also led to significant advances in social robotics. At the same time, however, social robots are still largely evaluated in idealised or laboratory conditions, and it remains unclear whether the technological progress is sufficient to let such robots move “into the wild”. In this paper, we characterise the problems that a social robot in the real world may face, and review the technological state of the art in terms of addressing these. We do this by considering what it would entail to automate the diagnosis of Autism Spectrum Disorder (ASD). Just as for social robotics, ASD diagnosis fundamentally requires the ability to characterise human behaviour from observable aspects. However, therapists provide clear criteria regarding what to look for. As such, ASD diagnosis is a situation that is both relevant to real-world social robotics and comes with clear metrics. Overall, we demonstrate that even with relatively clear therapist-provided criteria and current technological progress, the need to interpret covert behaviour cannot yet be fully addressed. Our discussions have clear implications for ASD diagnosis, but also for social robotics more generally. For ASD diagnosis, we provide a classification of criteria based on whether or not they depend on covert information and highlight present-day possibilities for supporting therapists in diagnosis through technological means. For social robotics, we highlight the fundamental role of covert behaviour, show that the current state-of-the-art is unable to characterise this, and emphasise that future research should tackle this explicitly in realistic settings.

A robot was programmed to progressively learn appropriate social autonomous behavior from in situ human demonstrations and guidance.