A Proxy-based Cloud Infrastructure for Home
Service Robots
Gaofeng Li
∗†
, Hongpeng Wang
∗†
, Xin Ying
‡
and Jingtai Liu
∗†
∗
Institute of Robotics and Automatic Information System, NanKai University, Tianjin, 300071
†
Tianjin Key Laboratory of Intelligent Robotics, Tianjin, 300071
‡
Tianjin LingJie Technology Co.,Ltd., Tianjin, 300384
Abstract—With the emerging of cloud computing, a growing
body of work is focused on cloud robotics. In this paper, robots
and the other devices in home are regarded as service supplier
or service consumer and are packaged as RaaS (Robot as a
Service) units. We design the RaaS Unit Module and propose
a proxy-based cloud infrastructure for the home service robots.
In addition, by modeling the disconnection times as a Poisson
Process, a simple offloading strategy about whether it is suitable
to offload a task to cloud is analyzed. To verify the feasibility of
this infrastructure, a specific instruction set is developed to call
cloud robot’s service via Lua Programming Language. By using
iFLY voice cloud which is a third application, speech recognition
is implemented to allow users to call robot service by voice input,
which illustrates that this cloud robot can utilize cloud resources.
Keywords—Cloud Robotics, Proxy-based Model, RaaS U-
nit Module, Offloading Strategy, Lua Programming Language,
Speech Recognition, XiaoNan Home Service Robot
I. INTRODUCTION
With the development of wireless networking and rapidly
expanding Internet resources, robots and automation systems
are no more limited by onboard computation and memory. In
2010, James Kuffner introduced the term “Cloud Robotics”
[1]. According to Kuffner, Cloud robots can improve the
robot’s performance on 5 aspects: 1) Big Data. 2) Cloud
Computing. 3) Collective Robot Learning. 4) Open-Source and
Open-Access. 5) Crowdsourcing and Call Centers [2].
The benefits of cloud robotics are clear. By offloading the
task to the cloud, it would be possible to build smaller, more
battery effective robots while the memory and computing
capability can be nearly infinite by utilizing cloud resources
[3].
Though the research on cloud robotics has just begun in the
last several years, it has achieved great success. J. Kuffner built
a cloud-based robot grasping system by utilizing Google’s
proprietary object recognition engine for object recognition,
the Point Cloud Library for pose estimation, Columbia Univer-
sity’s GraspIt! toolkit and OpenRAVE for 3D grasping [4]. E.
Guizzo proposed that cloud robots should have a remote brain
in cloud to share the infinite information and resources [5].
This work is supported by National High-tech R&D Program of Chi-
na (863 Program) under Grant 2012AA041403, National Natural Sci-
ence Foundation of China (Grant No. 61375087, 61105096). Email:
gaofengli@mail.nankai.edu.cn; hpwang@nankai.edu.cn; xying@ljrobot.com;
liujt@nankai.edu.cn. Jingtai Liu is the corresponding author.
Willow Garage developed a Robot Operating System (ROS)
which is an open source software framework [6]. Another
standalone, large scale, open project hosted by Willow Garage
is Point Cloud Library (PCL), which is for effective 2D/3D
image point cloud processing [7]. Google bought 9 robot
companies in half years and is devising a self-driving car by
utilizing its advantages in image recognition and navigation.
Google has been a big supporter of cloud robotics, aiming to
become a leader in this domain [8]. RoboEarth is a European
project led by the Eindhoven University of Technology, in
the Netherlands, to develop a “World Wide Web for robots”
[9]. Researchers in Singapore’s ASORO (A-Star Robotics
Laboratory) have built a cloud-computing infrastructure that
allows robots to generate 3-D maps of their environments
much faster than they could with their onboard computers [10].
These are excellent paradigms to show what they can
provide for robots and how robots can use cloud resource.
However, based on RaaS, cloud robots are not only expected
to “get” resource from cloud, but also expected to provide
themselves as services to users.
Y. Chen in Arizona State University has designed and im-
plemented a RaaS unit which is a cloud computing unit in [11].
M. Narita proposed a Robot Service Network Protocol (RSNP)
[12] to integrate robot services with Internet services and
adopted RSNP to realize reliable cloud-based robot services
[13]. F. Z. Errounda sketched an overall business model and
proposed an overlay-based architecture to handle the cloud
interaction aspects of the business model [14]. They also
applied this model to a wild fire suppression scenario which
needs three robots with different abilities to cooperate with
each other [15].
In this paper, we introduce a proxy-based model and design
a RaaS Unit Module in section II. Based on RaaS units, a
proxy-based cloud infrastructure is implemented for the home
service robot prototype in section III. Aiming to solve the
disconnection problem in cloud robots, we also analyze the
offloading strategy in section IV. Finally, a specific instruction
set is developed to call the cloud robot’s services via off-line
program to verify the feasibility of this infrastructure. By using
voice cloud which is a third application, speech recognition is
also implemented to illustrate that the cloud robot can utilize
cloud resources.
5718
978-1-4799-7016-2/15/$31.00
c
2015 IEEE