I have built and worked with several robotic test-beds to develop, refine, and test these control strategies.
Machine learning is revolutionizing a number of scientific and engineering disciplines by efficiently extracting information from noisy and uncertain data, e.g.
Their approaches seems to focus on self-organization, managing noise created by many interacting components, and using distributed reactive behaviors as feedback to adapt their strategies.
Can we build systems with similarly robust behavior?
Termites and other animals often take advantage of goopy, amorphous materials to build in irregularly shaped environments.
From a robotics perspective, this approach is appealing since mechanical feedback during construction not only makes the process robust but potentially allows for much coarser control and sensing requirements of the construction mechanism.
computer vision, medical screening, and model/parameter learning from vast amounts of data.
Systems Biology and other engineering disciplines that aim to design complex behaviors on a molecular level are currently plagued by noise and component uncertainty.
[mp4] (4.1 mb) The Factory Floor Testbed is an experiment to explore scalable, robust, multi robot construction hardware and algorithms.
It consists of modular robots that can build arbitrary lattice structures from two types of raw materials.