Research Problems

Up People Research Problems Demos and Movies Publications

Distributed Learning

We are researching machine learning algorithms that would enable automatic controller design for modular robots and other distributed robotic systems. The ultimate goal is to create a control architecture that would achieve fast online adaptation in a completely distributed fashion.

Click for more information on Distributed Learning

Distributed Control

We are developing distributed control laws for networked teams of robots that self-organize in response to the sensed environment. Such control laws would enable teams of robots to carry out group tasks, such as maintaining a formation or monitoring an environment, in a distributed fashion.

Click for more information on Distributed Control

Distributed Algorithm Design

We propose a swarm programming language that provides abstractions for global program
flow control, dynamic task assignment, shared variable creation and scoping, and code
modularization.  A language composed of these components will allow the developer to
build high-level swarm programs by specifying a global, hierarchical, finite-state
machine.

Click for more information on Distributed Algorithm Design

Research sponsored by Boeing