Sensing-Enhanced Therapy System for Assessing Children With Autism Spectrum Disorders: A Feasibility Study

Abstract

It is evident that recently reported robot-assisted therapy systems for assessment of children with autism spectrum disorder (ASD) lack autonomous interaction abilities and require significant human resources. This paper proposes a sensing system that automatically extracts and fuses sensory features such as body motion features, facial expressions, and gaze features, further assessing the children behaviours by mapping them to therapist-specified behavioural classes. Experimental results show that the developed system has a capability of interpreting characteristic data of children with ASD, thus has the potential to increase the autonomy of robots under the supervision of a therapist and enhance the quality of the digital description of children with ASD. The research outcomes pave the way to a feasible machine-assisted system for their behaviour assessment.

The DREAM Dataset: Supporting a data-driven study of autism spectrum disorder and robot enhanced therapy

“…Relative eye-gaze Two-eye model-based gaze estimation based on RGBD [42] Head pose Pose from Orthog-raphy and Scaling with ITerations (POSIT) [43] Gaze estimation A 3D gaze vector is achieved by combining the relative eye-gaze with calculated head pose [24] Face detection Boosted cascade face detector [44] Facial features Supervised descent method proposed by [45] Face expressions Frontalised Local Binary Patterns (LBP) classified using SVM [46] 3D skeleton Microsoft Kinect SDK Action recognition 3D joints Moving Trend method based on skeleton data [47] Object tracking GM-PHD Tracker [48] Sound direction Microsoft Kinect SDK Performance evaluations of each sensor primitive is available in Cai et al [24].…”

“…All therapy sessions were recorded using the same sensorized therapy table [24]. The table was equipped with three high-resolution RGB cameras and two RGBD (Kinect) cameras that, in combination with state of the art sensor interpretation methods, provide information about the child's position, motion, eye-gaze, face expressions, and verbal utterances.…”

“…All therapies were recorded using a sensorized intervention table able to record and interpret the child's behavior during the intervention (analyzing, for example, eye gaze, body movement, facial expression) [24]. The table was developed in order to inform the control of a supervised-autonomous robot used in RET [13], but was also used to support assessment and analysis of SHT.…”

How Much Information Does a Robot Need? Exploring the Benefits of Increased Sensory Range in a Simulated Crowd Navigation Task

“…In many applications, it is also the case that current on-board sensors are often insufficient and external sensors therefore unavoidable. This is for example typically the case in robots used for ASD therapy [10]. Last, a comprehensive study of this trade-off would ideally require a range of different hardware set-ups available in the same task, which is often not feasible in practice given cost and resource constraints.…”

Gaze-Guided Control of an Autonomous Mobile Robot Using Type-2 Fuzzy Logic

“…Gaze-based robot control work done in this regard is relatively scarce. Combining different types of technology with eye based systems [36][37][38][39][40] integration can be useful for disabled, elderly and patients peoples that especially with neuro-motor disabilities. They can remotely control a moving platform [11,12,41,42] with these technologies in complex daily tasks [14,43].…”