On the construction of a skill-based wheelchair navigation profile.

Assisted wheelchair navigation is of key importance for persons with severe disabilities. The problem has been solved in different ways, usually based on the shared control paradigm. This paradigm consists of giving the user more or less control on a need basis. Naturally, these approaches require personalization: each wheelchair user has different skills and needs and it is hard to know a priori from diagnosis how much assistance must be provided. Furthermore, since there is no such thing as an average user, sometimes it is difficult to quantify the benefits of these systems. This paper proposes a new method to extract a prototype user profile using real traces based on more than 70 volunteers presenting different physical and cognitive skills. These traces are clustered to determine the average behavior that can be expected from a wheelchair user in order to cope with significant situations. Processed traces provide a prototype user model for comparison purposes, plus a simple method to obtain without supervision a skill-based navigation profile for any user while he/she is driving. This profile is useful for benchmarking but also to determine the situations in which a given user might require more assistance after evaluating how well he/she compares to the benchmark. Profile-based shared control has been successfully tested by 18 volunteers affected by left or right brain stroke at Fondazione Santa Lucia, in Rome, Italy.

Wheelchair collaborative control for disabled users navigating indoors.

OBJECTIVE: Mobility is of key importance for autonomous living. Persons with severe disabilities may be assisted by robotic wheelchairs when manual control is not possible. However, these persons should contribute to control as much as they can to avoid loss of residual skills and frustration. Traditionally, wheelchair shared control approaches either give control to person or robot depending on the situation. METHODS AND MATERIALS: We propose a new shared control technique where robot and person contribute simultaneously to control. Their commands are weighted according to their respective local efficiencies and then combined via a reactive navigation strategy. Thus, assistance adapts to the user's needs. We refer to this approach as collaborative control. RESULTS: Collaborative control was tested in a home environment in Fondazione Santa Lucia (Rome) by 18 volunteers presenting different degrees of physical and cognitive disability. All of them successfully finished a complex test path with assistance. Both users and caregivers' opinion on the system was very positive. Acceptance was very good according to the psychosocial impact of assistive devices scale. CONCLUSIONS: Collaborative control adapts to the person's needs and assists him/her when necessary, locally compensating any problem related to specific disabilities. An ANOVA returned a p-value of 0.016, meaning that there is significant improvement in task performance when collaborative control is used.