This work proposes dedicated hardware to real-time cancer detection using Field-Programmable Gate Arrays (FPGA). The presented hardware combines a Multilayer Perceptron (MLP) Artificial Neural Networks (ANN) with Digital Image Processing (DIP) techniques. The DIP techniques are used to extract the features from the analyzed skin, and the MLP classifies the lesion into melanoma or non-melanoma. The classification results are validated with an open-access database. Finally, analysis regarding execution time, hardware resources usage, and power consumption are performed. The results obtained through this analysis are then compared to an equivalent software implementation embedded in an ARM A9 microprocessor.
Global path planning is one of the most important issues for multi-robot systems because it ensures the computation of feasible paths for the robots to perform safe movements inside an environment with obstacles. This approach typically uses the space topology to find paths for the robots in static environments. In this paper we present an off-line approach for global path planning based on Probabilistic Foam method (PFM) for a multi-robot system. PFM is a sampling-based path planner able to calculate obstacle-free paths with high clearance, using structures called bubble that tries to cover the free space. We propose some modifications in the original method in order to improve the area coverage strategy to guarantee that paths be found from different points in the space. Besides, an approach to compute bubbles using workspace information was implemented. Some experiments were performed using three wheeled-robots and a field of robot soccer as a test environment. Finally, we demonstrate that our approach was able to plan safe paths for all robots.