Embedding a concurrent autonomous agent in a microcontrollers network

In this paper, a microcontroller heterogeneous network is proposed to embed a concurrent autonomous agent. The network was designed to fit the concurrency requirements of the cognitive model of the aforementioned agent. The architecture of the agent comprises three levels, namely, the reactive level, instinctive level and the cognitive level, which runs concurrently. The reactive level is embedded in a PSoC 5LP, consisting of behaviours created over a embedded kinematic controller. The instinctive level runs in a mbed NXP LPC1768, which receives perceptions from and sends the active behaviour to the reactive level through a CAN bus. And The cognitive level runs on a DNP/2486 which, in turn, receives symbolic information from and sends new local goals to instinctive level through an Ethernet network. Finally, the architecture used in the experiments is presented, followed by the results.