Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Jan 16:10:1323675.
doi: 10.3389/frobt.2023.1323675. eCollection 2023.

Tour guide robot: a 5G-enabled robot museum guide

Stefano Rosa  1 , Marco Randazzo  1 , Ettore Landini  1 , Stefano Bernagozzi  1 , Giancarlo Sacco  2 , Mara Piccinino  2 , Lorenzo Natale  1
Affiliations

Tour guide robot: a 5G-enabled robot museum guide

Stefano Rosa et al. Front Robot AI. .

Abstract

This paper presents and discusses the development and deployment of a tour guide robot as part of the 5 g-TOURS EU research project, aimed at developing applications enabled by 5G technology in different use cases. The objective is the development of an autonomous robotic application where intelligence is off-loaded to a remote machine via 5G network, so as to lift most of the computational load from the robot itself. The application uses components that have been widely studied in robotics, (i.e., localization, mapping, planning, interaction). However, the characteristics of the network and interactions with visitors in the wild introduce specific problems which must be taken into account. The paper discusses in detail such problems, summarizing the main results achieved both from the methodological and the experimental standpoint, and is completed by the description of the general functional architecture of the whole system, including navigation and operational services. The software implementation is also publicly available.

Keywords: 5G; autonomous navigation; humanoids; museum guide robots; service robots.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. The author(s) declared that they were an editorial board member of Frontiers, at the time of submission. This had no impact on the peer review process and the final decision.

Figures

FIGURE 1
FIGURE 1
The R1 humanoid robot in the configuration used in the museum trials.
FIGURE 2
FIGURE 2
High-level overview of the application’s main components and their interfaces. The components are organized by abstraction level and by physical placement. The bottom row represents the navigation level, while the top row contains the application-level components. The main component, Tour Manager, is executed on a remote machine, as well as the Dialogue System, that communicates with Goole APIs on the internet. The Behaviour Tree is run locally on the robot, while the Navigation component is split between the robot and the remote machine. Components in green constitute the navigation system, components in yellow are part of the dialogue system.
FIGURE 3
FIGURE 3
Network configuration for the museum trials. Onboard the robot, all machines are connected to a router. On the remote side, machines are also connected via a router, which is in turn connected to the internet. The robot is connected to a commercial 5G network via a tethered smartphone; the remote side is connected to 5G via an infrastructure of deployed antennas. A VPN tunnel is created between the PC in the robot’s base and a remote machine acting as VPN server.
FIGURE 4
FIGURE 4
Effect of payload size on application level latency for two machines connected via 5G and through a VPN tunnel with a default configuration, using different YARP transport layers.
FIGURE 5
FIGURE 5
Effect of payload size on application level latency for two machines connected via 5G and through a VPN tunnel, after VPN optimization.
FIGURE 6
FIGURE 6
Management of sensor streams over the network via YARP repeaters and data compression via port monitors. Yellow blocks represent YARP network wrapped device drivers; white blocks represent sensors; green blocks represent macro components (either ROS-based or YARP-based). On the remote side, YARP ports are multiplexed to different subscribers via a YARP reperater, to avoid data duplication.
FIGURE 7
FIGURE 7
The behaviour tree for the tour guide robot application. Conditions are shown as green leaves; actions as white leaves. Compositional nodes are shown in blue (fallback) and purple (sequence).
FIGURE 8
FIGURE 8
Location of the points of interest (blue circles) and DOT antennas (red squares) for the GAM museum (A) and Palazzo Madama (B). Environment dimensions are ∼60×20m for the GAM museum and ∼30×12m for Palazzo Madama. Note that the CAD maps are not necessarily accurate to the actual dimensions and layout of the actual environment.
FIGURE 9
FIGURE 9
The localization introspection module. The three localization streams are represented with different colors. For each stream, the consistency checks are divided into independent position and orientation checks. Faults from each stream are accumulated on order to make a decision on the localization state.
FIGURE 10
FIGURE 10
The robot in action during the trials in GAM.
FIGURE 11
FIGURE 11
The robot in action during the trials in Palazzo Madama.
FIGURE 12
FIGURE 12
Robot trajectories for a subset of tours in GAM and Palazzo Madama. It is possible to notice a larger variance in the trajectory along the first part of the tour in both GAM and Palazzo Madama, due to more visitors surrounding the robot as well as a larger number of followers on average.
FIGURE B1
FIGURE B1
Aggregated QoE results for the final trials in GAM and Palazzo Madama.
See this image and copyright information in PMC

References

    1. Abrate F., Bona B., Indri M., Rosa S., Tibaldi F. (2013). Multirobot localization in highly symmetrical environments. J. Intelligent Robotic Syst. 71, 403–421. 10.1007/s10846-012-9790-6 - DOI
    1. Alletto S., Cucchiara R., Del Fiore G., Mainetti L., Mighali V., Patrono L., et al. (2015). An indoor location-aware system for an iot-based smart museum. IEEE Internet Things J. 3, 244–253. 10.1109/jiot.2015.2506258 - DOI
    1. Álvarez M., Galán R., Matía F., Rodríguez-Losada D., Jiménez A. (2010). An emotional model for a guide robot. IEEE Trans. Syst. Man, Cybernetics-Part A Syst. Humans 40, 982–992. 10.1109/tsmca.2010.2046734 - DOI
    1. Antonante P., Spivak D. I., Carlone L. (2021). “Monitoring and diagnosability of perception systems,” in 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 168–175. 10.1109/IROS51168.2021.9636497 - DOI
    1. Bickmore T., Pfeifer L., Schulman D. (2011). “Relational agents improve engagement and learning in science museum visitors,” in International Workshop on Intelligent Virtual Agents (Springer; ), 55–67.

LinkOut - more resources