Expanding a robot's life: Low power object recognition via FPGA-based DCNN deployment

TL;DR

This paper demonstrates how deploying a low-power FPGA-based SqueezeNet deep convolutional neural network enhances object recognition capabilities in robots by improving performance and reducing power consumption compared to traditional systems.

Contribution

It introduces FPGA-based deployment of SqueezeNet for robotic object recognition, showcasing performance and power efficiency improvements over conventional computational platforms.

Findings

FPGA deployment achieves lower power consumption.

Performance benchmarks show competitive speed.

Enhanced suitability for robotic applications.

Abstract

FPGAs are commonly used to accelerate domain-specific algorithmic implementations, as they can achieve impressive performance boosts, are reprogrammable and exhibit minimal power consumption. In this work, the SqueezeNet DCNN is accelerated using an SoC FPGA in order for the offered object recognition resource to be employed in a robotic application. Experiments are conducted to investigate the performance and power consumption of the implementation in comparison to deployment on other widely-used computational systems.