Real-Time Robot Localization, Vision, and Speech Recognition on Nvidia Jetson TX1

TL;DR

This paper demonstrates the integration of real-time localization, vision, and speech recognition services on the Nvidia Jetson TX1 embedded platform, emphasizing energy efficiency and exploring cloud offloading for enhanced performance.

Contribution

It presents a comprehensive case study on deploying multiple AI services on a low-power embedded system, highlighting practical implementation and energy considerations.

Findings

Successful real-time integration within 10 W power envelope

Potential energy savings through cloud offloading

Feasibility of complex AI services on embedded platforms

Abstract

Robotics systems are complex, often consisted of basic services including SLAM for localization and mapping, Convolution Neural Networks for scene understanding, and Speech Recognition for user interaction, etc. Meanwhile, robots are mobile and usually have tight energy constraints, integrating these services onto an embedded platform with around 10 W of power consumption is critical to the proliferation of mobile robots. In this paper, we present a case study on integrating real-time localization, vision, and speech recognition services on a mobile SoC, Nvidia Jetson TX1, within about 10 W of power envelope. In addition, we explore whether offloading some of the services to cloud platform can lead to further energy efficiency while meeting the real-time requirements