Multicore and FPGA implementations of emotional-based agent architectures

Abstract

Control architectures based on Emotions are becoming promising solutions for the implementation of future robotic agents. The basic controllers of the architecture are the emotional processes that decide which behaviors of the robot must activate to fulfill the objectives. The number of emotional processes increases (hundreds of millions/s) with the complexity level of the application, limiting the processing capacity of the main processor to solve complex problems (millions of decisions in a given instant). However, the potential parallelism of the emotional processes permits their execution in parallel on FPGAs or Multicores, thus enabling slack computing in the main processor to tackle more complex dynamic problems. In this paper, an emotional architecture for mobile robotic agents is presented. The workload of the emotional processes is evaluated. Then, the main processor is extended with FPGA co-processors, which are in charged of the parallel execution of the emotional processes. Different Stratix FPGAs are compared to analyze their suitability to cope with the proposed mobile robotic agent applications.The applications are set-up taking into account different environmental conditions, robot dynamics and emotional states. Moreover, the applications are run also on Multicore processors to compare their performance in relation to the FPGAs. Experimental results show that, Stratix IV FPGA increases the performance in about one order of magnitude over the main processor and solves all the considered problems. Quad-Core increases the performance in 3.64 times, allowing to tackle about 89% of the considered problems. Stratix III could be applied to solve problems with around the double of the requirements that the main processor could support and a Dual-Core provides slightly better performance than stratix III and it is relatively cheaper.

Embedded GPU and multicore processors for emotional-based mobile robotic agents

“…However, the application consists of the control of a simple crane, which could be solved using a traditional PID controller. In [17], different possibilities to parallelize a limited subset of motivational processes and its implementation using a Stratix IV FPGA are proposed. The results obtained improve the implementation of the system on a single-core processor.…”

“…Table 5 shows the characteristics of these GPUs. For comparison purposes, results for the sequential algorithm running on one core and for an implementation based on FPGAs [17] [17].…”

“…In our preliminary experiments, Stratix IV [16] was able to solve even complex problems. However, they have a high cost [17].…”