High-level Perception and Control for Autonomous Reconfigurable Modular Robots

Abstract:

The objective of this research is to develop the theory, hardware and computational infrastructure that will enable automatically transforming user-defined, high-level tasks into correct, low-level perception informed control and configurations for modular robots. Modular robots are composed of simple individual modules with limited sensing and actuation; while each module can locomote in the environment, connecting multiple modules in different configurations allows modular robots to perform complex actions such as climbing, manipulating objects and traveling in unstructured environments. Furthermore, modular robots can divide into multiple robots and then reconfigure as one. The posters describe the progress in the first two years of the project; the hardware development of the SMORES modules, incorporating sensors as specialty modules, creating hardware-constrained perception algorithms, creating a framework for composing configurations and gaits from basic components using the notion of series-parallel graphs, creating a game-based environment for crowdsourcing controller and configuration design (can be found at http://vsparc.org) and developing a library of controllers that will be used, in the third year of the project, to create high-level behaviors for modular robots.