Cloud Robotics Experimentation Testbeds: a Cloud-Based Navigation Case Study

Cloud robotics is expected to play an important role in Industry 4.0 automation processes. Nevertheless, cloud robotics research still lacks comprehensive analysis on implementation issues and standardization. Experimentation testbeds designed for cloud robotics may accelerate research by providing a range of solutions while relieving researchers from implementing the whole cloud robotics stack. In this work, we present a case study over a cloud robotics testbed infrastructure in which we implement a cloud-based real-time autonomous navigation service for autonomous unmanned ground vehicles (UGVs). An UGV located 4600 km away from the cloud platform makes use of such service to navigate throughout its environment, delegating to the cloud almost all computation. Results indicate the feasibility of real world cloud robotics implementations and we discuss the challenges and benefits of such approach.

[1]  Robert Bogue,et al.  Cloud robotics: a review of technologies, developments and applications , 2017, Ind. Robot.

[2]  Raffaello D'Andrea,et al.  Rapyuta: A Cloud Robotics Platform , 2015, IEEE Transactions on Automation Science and Engineering.

[3]  Marco Pavone,et al.  Network offloading policies for cloud robotics: a learning-based approach , 2019, Autonomous Robots.

[4]  Daniel F. Macedo,et al.  Enabling experimental research through converged orchestration of optical , wireless , and cloud domains , 2018 .

[5]  Peter Gulden,et al.  Steady Delivery: Wireless Local Positioning Systems for Tracking and Autonomous Navigation of Transport Vehicles and Mobile Robots , 2017, IEEE Microwave Magazine.

[6]  Fernando Díaz del Río,et al.  A Tradeoff Analysis of a Cloud-Based Robot Navigation Assistant Using Stereo Image Processing , 2015, IEEE Transactions on Automation Science and Engineering.

[7]  Siti Nurmaini,et al.  Intelligent Robotics Navigation System: Problems, Methods, and Algorithm , 2017 .

[8]  Lorenzo Sabattini,et al.  Cooperative cloud robotics architecture for the coordination of multi-AGV systems in industrial warehouses , 2017 .

[9]  Max Q.-H. Meng,et al.  Autonomous mobile robot navigation in uneven and unstructured indoor environments , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[10]  Moisés R. N. Ribeiro,et al.  On Human-in-the-Loop CPS in Healthcare: A Cloud-Enabled Mobility Assistance Service , 2019, Robotica.

[11]  Moises R. N. Ribeiro 5G Research and Testbeds in Brazil , 2019, 2019 Optical Fiber Communications Conference and Exhibition (OFC).

[12]  Valerio Frascolla,et al.  Ultra Reliable Communication for Robot Mobility enabled by SDN Splitting of WiFi Functions , 2018, 2018 IEEE Symposium on Computers and Communications (ISCC).

[13]  Zhichao Li,et al.  VC-bots: a vehicular cloud computing testbed with mobile robots , 2016, IoV-VoI '16.

[14]  Athanasios V. Vasilakos,et al.  Cloud robotics: Current status and open issues , 2016, IEEE Access.

[15]  Koji Zettsu,et al.  Rospeex: A cloud robotics platform for human-robot spoken dialogues , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[16]  Roberta Lima Gomes,et al.  How can emerging applications benefit from EaaS in open programmable infrastructures? , 2017, 2017 IEEE First Summer School on Smart Cities (S3C).

[17]  Moisés R. N. Ribeiro,et al.  Towards a New Generation of Smart Devices for Mobility Assistance : CloudWalker , a Cloud-Enabled Cyber-Physical System , 2018 .

[18]  Paolo Dario,et al.  Enabling Global Robot Navigation Based on a Cloud Robotics Approach , 2016, Int. J. Soc. Robotics.

[19]  Hongtai Cheng,et al.  Design of a CloudROS enabled Mobile Robot , 2018, 2018 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[20]  Moisés R. N. Ribeiro,et al.  Towards a New Generation of Smart Devices for Mobility Assistance: CloudWalker, a Cloud-Enabled Cyber-Pbysical System , 2018, 2018 7th IEEE International Conference on Biomedical Robotics and Biomechatronics (Biorob).