Self-reconfigurable control architecture for complex robots

Abstract

Advanced robot systems need to carry out increasingly complex task sets. However, they are typically optimized to a very restricted set of tasks and environments to solve demanding problems. This work will therefore propose a self-reconfigurable software and hardware architecture in order to enable the dynamic optimization of a robot system depending on the current situation, i.e. the current task, robot state, and environment. The proposed framework is based on organic computing principles and unsupervised machine learning techniques. It further uses dynamically reconfigurable Field Programmable Gate Arrays (FPGA) as hardware accelerators.