Researchers say the development of adaptable robots requires centralized sensory processing, environmental perception, and decision-making software.
Cornell University roboticist Hadas Kress-Gazit and colleagues developed modular self-reconfigurable robots (MSRR), which they described as the first to autonomously solved problems by reconfiguring in response to a changing environment.
The robot used in the experiment, SMORES-EP, is composed of any number of cube-like modules that connect to each other in different ways using magnets.
The researchers built a software library of possible actions, such as driving or collecting an object, and the shape the robot would need to be to complete the action.
Mark Kim of the University of Pennsylvania, who also worked on the project, said, "The robotics community has been making a lot of progress in understanding the environment. The thing that we are doing [that is] new here is understanding the capabilities of the robot."
From IEEE Spectrum
View Full Article
Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA