Fig 8 - uploaded by Akanksha Baranwal
Content may be subject to copyright.
Similar publications
Citations
FPGAs constitute a flexible and increasingly popular controlling solution for robotic applications. Their core advantages regarding high computational performance and software-like flexibility make them suitable controller platforms for robots. These robotic applications include localization / navigation, image processing, industrial or even more complex procedures such as operating on medical or human assistant tasks. This paper provides an overview of the publications regarding different robotic FPGA application fields as well as the most commonly-used robot types used for those applications for the 10-year period of 2010-2019. A short description of each paper reviewed is also included, providing a total view of FPGA technology trends in robotic applications over the last decade.
An energy-efficient convolutional neural network (CNN) processor is proposed for real-time image segmentation on mobile devices. The proposed processor utilizes Region of Interest (ROI) based image segmentation to speed up the process and reduce the overall external memory access. Although the ROI based image segmentation degrades the segmentation accuracy, the proposed dilation rate adjustment algorithm, which regulates the receptive field depending on the ROI resolution during dilated convolution, compensates for the accuracy degradation up to 0.2310 mean Intersection over Union (mIoU). In addition, the processor accelerates the dilated and transposed convolution by skipping the redundant zero computations with the proposed delay cells. As a result, the throughput of dilated and transposed convolution is increased up to ×159 and ×3.84 . The delay cells can also support the variable dilation rates in dilated convolution caused by the dilation rate adjustment algorithm. Moreover, the processor selects the operating frequency based on the ROI resolution to save power consumption up to 81.2%. The processor is simulated in 65 nm CMOS technology, and the 6.8 mm
<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>
processor consumes the 206 mW power consumption with the 4.66 ms of processing time and 3.22 TOPS/W energy-efficiency at the target image segmentation dataset.
