Natural interfaces and virtual environments for the acquisition of street crossing and path following skills in adults with Autism Spectrum Disorders: A feasibility study

BACKGROUND: Lack of social skills and/or a reduced ability to determine when to use them are common symptoms of Autism Spectrum Disorder (ASD). Here we examine whether an integrated approach based on virtual environments and natural interfaces is effective in teaching safety skills in adults with ASD. We specifically focus on pedestrian skills, namely street crossing with or without traffic lights, and following road signs. METHODS: Seven adults with ASD explored a virtual environment (VE) representing a city (buildings, sidewalks, streets, squares), which was continuously displayed on a wide screen. A markerless motion capture device recorded the subjects' movements, which were translated into control commands for the VE according to a predefined vocabulary of gestures. The treatment protocol consisted of ten 45-minutes sessions (1 session/week). During a familiarization phase, the participants practiced the vocabulary of gestures. In a subsequent training phase, participants had to follow road signs (to either a police station or a pharmacy) and to cross streets with and without traffic lights. We assessed the performance in both street crossing (number and type of errors) and navigation (walking speed, path length and ability to turn without stopping). To assess their understanding of the practiced skill, before and after treatment subjects had to answer a test questionnaire. To assess transfer of the learned skill to real-life situations, another specific questionnaire was separately administered to both parents/legal guardians and the subjects' personal caregivers. RESULTS: One subject did not complete the familiarization phase because of problems with depth perception. The six subjects who completed the protocol easily learned the simple body gestures required to interact with the VE. Over sessions they significantly improved their navigation performance, but did not significantly reduce the errors made in street crossing. In the test questionnaire they exhibited no significant reduction in the number of errors. However, both parents and caregivers reported a significant improvement in the subjects' street crossing performance. Their answers were also highly consistent, thus pointing at a significant transfer to real-life behaviors. CONCLUSIONS: Rehabilitation of adults with ASD mainly focuses on educational interventions that have an impact in their quality of life, which includes safety skills. Our results confirm that interaction with VEs may be effective in facilitating the acquisition of these skills.