Improving the performance of motor-impaired users with automatically-generated, ability-based interfaces

We evaluate two systems for automatically generating per-sonalized interfaces adapted to the individual motor capa-bilities of users with motor impairments. The first system, SUPPLE, adapts to users ’ capabilities indirectly by first us-ing the ARNAULD preference elicitation engine to model a user’s preferences regarding how he or she likes the inter-faces to be created. The second system, SUPPLE++, mod-els a user’s motor abilities directly from a set of one-time motor performance tests. In a study comparing these ap-proaches to baseline interfaces, participants with motor im-pairments were 26.4 % faster using ability-based user inter-faces generated by SUPPLE++. They also made 73 % fewer errors, strongly preferred those interfaces to the manufactur-ers ’ defaults, and found them more efficient, easier to use, and much less physically tiring. These findings indicate that rather than requiring some users with motor impairments to adapt themselves to software using separate assistive tech-nologies, software can now adapt itself to the capabilities of its users