Developing standards for affordances on embedded devices: poster abstract.
ABSTRACT Embedded devices are ubiquitous in our environment, including computing systems as widely diverse as digital watches, automobile dashboards, factory controllers, thermostats and other appliances. Traditionally, little attention has been paid to the user interface in such low-cost, dedicated-function devices. However, new technologies such as touchscreens are changing the landscape of embedded user interface design. Additionally, recent research has demonstrated that usability can have a significant effect on embedded device efficiency. Research on programmable thermostats in particular points to the need for proficient and consistent user interface design in order to realize energy savings nationwide. We discuss preliminary results from an in-depth usability study conducted on five programmable thermostat interfaces (three touchscreen, one web, and one-button based) with 31 participants. Our research suggests that users lacked a consistent mental model of how to interact with buttons, text, icons, and other features of the device. We hypothesize that discrepancies between perceived and actual affordances on the device had a measurable impact on users' ability to successfully accomplish key tasks on the thermostats.
SourceAvailable from: Alexandre Bernardino[Show abstract] [Hide abstract]
ABSTRACT: Affordances encode relationships between actions, objects, and effects. They play an important role on basic cognitive capabilities such as prediction and planning. We address the problem of learning affordances through the interaction of a robot with the environment, a key step to understand the world properties and develop social skills. We present a general model for learning object affordances using Bayesian networks integrated within a general developmental architecture for social robots. Since learning is based on a probabilistic model, the approach is able to deal with uncertainty, redundancy, and irrelevant information. We demonstrate successful learning in the real world by having an humanoid robot interacting with objects. We illustrate the benefits of the acquired knowledge in imitation games.IEEE Transactions on Robotics 03/2008; DOI:10.1109/TRO.2007.914848 · 2.65 Impact Factor