This Small Business Innovation Research (SBIR) Phase I project aims to develop a robotic instrument to provide quantitative characterization of surface properties that humans can perceive by touch. In contrast to machine vision, which operates on images captured passively with video cameras, "machine touch" requires physical interaction between the robotic sensors and the object. In fact, tactile signals are affected more by the choice of exploratory movement than by the properties of the object, making selection and control of these movements essential. Current generations of robots rely on primitive contact sensors that are of little use in enabling more human-like perception, movement, dexterity and reflexes. Robots equipped with more humanlike tactile perception and intelligent exploratory strategies will be used to characterize and identify common objects with accuracy and speed similar to humans. They will be able to learn and continuously improve their performance as they interact with objects over time.
The broader impact/commercial potential of this project will be the enabling of advanced, autonomous functionality in the next generation of robots. Robots need to be able to perceive the world and interact with the world more like humans in order to better work alongside us in unstructured environments. Assistive robots for care of the disabled and the elderly are but one example of how next generation robotics will improve the quality of life for many. Better understanding of the haptic properties of consumer products will facilitate development of new products that ?feel? better to human users and the development of quality control systems to assure that those products consistently attain those desirable properties during manufacture. Because these robots employ biomimetic strategies for haptic perception, their performance can be compared to that of humans to provide insights into the perceptual and cognitive strategies employed by the human mind.
