Comparing Computing Platforms for Deep Learning on a Humanoid Robot

TL;DR

This paper compares two computing platforms, Intel NUC7i7BNH and NVIDIA Jetson TX2, to evaluate their suitability for running deep neural networks in humanoid robots, considering performance and power consumption.

Contribution

It provides an empirical comparison of CPU and GPU-based platforms for deep learning applications in humanoid robotics, highlighting their respective strengths and weaknesses.

Findings

Platforms have different advantages in performance and power efficiency.

Unexpected results in benchmarking tasks.

Trade-offs between computational speed and energy consumption.

Abstract

The goal of this study is to test two different computing platforms with respect to their suitability for running deep networks as part of a humanoid robot software system. One of the platforms is the CPU-centered Intel NUC7i7BNH and the other is a NVIDIA Jetson TX2 system that puts more emphasis on GPU processing. The experiments addressed a number of benchmarking tasks including pedestrian detection using deep neural networks. Some of the results were unexpected but demonstrate that platforms exhibit both advantages and disadvantages when taking computational performance and electrical power requirements of such a system into account.