Nav2CAN: Achieving Context Aware Navigation in ROS2 Using Nav2 and RGB-D sensing

Tristan Schwörer; Jonathan Eichild Schmidt; Dimitrios Chrysostomou

doi:10.1109/IST59124.2023.10355731

Nav2CAN: Achieving Context Aware Navigation in ROS2 Using Nav2 and RGB-D sensing

Tristan Schwörer, Jonathan Eichild Schmidt, Dimitrios Chrysostomou^*

^*Corresponding author for this work

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

2 Citations (Scopus)

277 Downloads (Pure)

Abstract

This paper presents a real-time human interaction detection system using RGB-D cameras to enable context-aware navigation for mobile robots. The system employs a convolutional neural network (CNN) architecture optimized for efficient inference on embedded GPUs. Using a keypoint detection based human detector on RGB-D images, interactions are localized in the 3D scene using object detection of humans. The detected human interaction zones are integrated into the robot’s navigation costmaps to modify planned paths accounting for social spaces. The system is validated through simulated and real-world tests showing reliable interaction detection at over 10 Hz. The modular system, called Nav2CAN, can be added to mobile robots operating in ROS2 (Robot Operating System 2) and achieve easy integration and compatibility with other packages. By combining deep learning-based perception with semantic navigation costmaps, socially-aware robot navigation in human environments is achieved.

Original language	English
Title of host publication	IST 2023 - IEEE International Conference on Imaging Systems and Techniques, Proceedings
Publisher	IEEE Signal Processing Society
Publication date	20 Dec 2023
ISBN (Print)	979-8-3503-3084-7
ISBN (Electronic)	9798350330830
DOIs	https://doi.org/10.1109/IST59124.2023.10355731
Publication status	Published - 20 Dec 2023
Event	2023 IEEE International Conference on Imaging Systems and Techniques, IST 2023 - Copenhagen, Denmark Duration: 17 Oct 2023 → 19 Oct 2023

Conference

Conference	2023 IEEE International Conference on Imaging Systems and Techniques, IST 2023
Country/Territory	Denmark
City	Copenhagen
Period	17/10/2023 → 19/10/2023
Sponsor	IEEE, IEEE Instrumentation and Measurement Society

Series	IST 2023 - IEEE International Conference on Imaging Systems and Techniques, Proceedings

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

ROS2
context-aware navigation
human robot collaboration
human robot interaction
mobile robotics
proxemics
robotics

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/IST59124.2023.10355731

IST2023_Nav2CANAccepted author manuscript, 6.37 MBLicence: CC BY 4.0

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

Schwörer, Tristan ; Schmidt, Jonathan Eichild ; Chrysostomou, Dimitrios. / Nav2CAN: Achieving Context Aware Navigation in ROS2 Using Nav2 and RGB-D sensing. IST 2023 - IEEE International Conference on Imaging Systems and Techniques, Proceedings. IEEE Signal Processing Society, 2023. (IST 2023 - IEEE International Conference on Imaging Systems and Techniques, Proceedings).

@inproceedings{1bac70c1822e4f1186071a5a9062d0e9,

title = "Nav2CAN: Achieving Context Aware Navigation in ROS2 Using Nav2 and RGB-D sensing",

abstract = "This paper presents a real-time human interaction detection system using RGB-D cameras to enable context-aware navigation for mobile robots. The system employs a convolutional neural network (CNN) architecture optimized for efficient inference on embedded GPUs. Using a keypoint detection based human detector on RGB-D images, interactions are localized in the 3D scene using object detection of humans. The detected human interaction zones are integrated into the robot{\textquoteright}s navigation costmaps to modify planned paths accounting for social spaces. The system is validated through simulated and real-world tests showing reliable interaction detection at over 10 Hz. The modular system, called Nav2CAN, can be added to mobile robots operating in ROS2 (Robot Operating System 2) and achieve easy integration and compatibility with other packages. By combining deep learning-based perception with semantic navigation costmaps, socially-aware robot navigation in human environments is achieved. ",

keywords = "ROS2, context-aware navigation, human robot collaboration, human robot interaction, mobile robotics, proxemics, robotics",

author = "Tristan Schw{\"o}rer and Schmidt, {Jonathan Eichild} and Dimitrios Chrysostomou",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE International Conference on Imaging Systems and Techniques, IST 2023 ; Conference date: 17-10-2023 Through 19-10-2023",

year = "2023",

month = dec,

day = "20",

doi = "10.1109/IST59124.2023.10355731",

language = "English",

isbn = "979-8-3503-3084-7",

series = "IST 2023 - IEEE International Conference on Imaging Systems and Techniques, Proceedings",

booktitle = "IST 2023 - IEEE International Conference on Imaging Systems and Techniques, Proceedings",

publisher = "IEEE Signal Processing Society",

address = "United States",

}

Schwörer, T, Schmidt, JE & Chrysostomou, D 2023, Nav2CAN: Achieving Context Aware Navigation in ROS2 Using Nav2 and RGB-D sensing. in IST 2023 - IEEE International Conference on Imaging Systems and Techniques, Proceedings. IEEE Signal Processing Society, IST 2023 - IEEE International Conference on Imaging Systems and Techniques, Proceedings, 2023 IEEE International Conference on Imaging Systems and Techniques, IST 2023, Copenhagen, Denmark, 17/10/2023. https://doi.org/10.1109/IST59124.2023.10355731

Nav2CAN: Achieving Context Aware Navigation in ROS2 Using Nav2 and RGB-D sensing. / Schwörer, Tristan; Schmidt, Jonathan Eichild; Chrysostomou, Dimitrios.
IST 2023 - IEEE International Conference on Imaging Systems and Techniques, Proceedings. IEEE Signal Processing Society, 2023. (IST 2023 - IEEE International Conference on Imaging Systems and Techniques, Proceedings).

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - Nav2CAN: Achieving Context Aware Navigation in ROS2 Using Nav2 and RGB-D sensing

AU - Schwörer, Tristan

AU - Schmidt, Jonathan Eichild

AU - Chrysostomou, Dimitrios

PY - 2023/12/20

Y1 - 2023/12/20

N2 - This paper presents a real-time human interaction detection system using RGB-D cameras to enable context-aware navigation for mobile robots. The system employs a convolutional neural network (CNN) architecture optimized for efficient inference on embedded GPUs. Using a keypoint detection based human detector on RGB-D images, interactions are localized in the 3D scene using object detection of humans. The detected human interaction zones are integrated into the robot’s navigation costmaps to modify planned paths accounting for social spaces. The system is validated through simulated and real-world tests showing reliable interaction detection at over 10 Hz. The modular system, called Nav2CAN, can be added to mobile robots operating in ROS2 (Robot Operating System 2) and achieve easy integration and compatibility with other packages. By combining deep learning-based perception with semantic navigation costmaps, socially-aware robot navigation in human environments is achieved.

AB - This paper presents a real-time human interaction detection system using RGB-D cameras to enable context-aware navigation for mobile robots. The system employs a convolutional neural network (CNN) architecture optimized for efficient inference on embedded GPUs. Using a keypoint detection based human detector on RGB-D images, interactions are localized in the 3D scene using object detection of humans. The detected human interaction zones are integrated into the robot’s navigation costmaps to modify planned paths accounting for social spaces. The system is validated through simulated and real-world tests showing reliable interaction detection at over 10 Hz. The modular system, called Nav2CAN, can be added to mobile robots operating in ROS2 (Robot Operating System 2) and achieve easy integration and compatibility with other packages. By combining deep learning-based perception with semantic navigation costmaps, socially-aware robot navigation in human environments is achieved.

KW - ROS2

KW - context-aware navigation

KW - human robot collaboration

KW - human robot interaction

KW - mobile robotics

KW - proxemics

KW - robotics

UR - https://ist2023.ieee-ims.org/

UR - http://www.scopus.com/inward/record.url?scp=85182729749&partnerID=8YFLogxK

U2 - 10.1109/IST59124.2023.10355731

DO - 10.1109/IST59124.2023.10355731

M3 - Article in proceeding

SN - 979-8-3503-3084-7

T3 - IST 2023 - IEEE International Conference on Imaging Systems and Techniques, Proceedings

BT - IST 2023 - IEEE International Conference on Imaging Systems and Techniques, Proceedings

PB - IEEE Signal Processing Society

T2 - 2023 IEEE International Conference on Imaging Systems and Techniques, IST 2023

Y2 - 17 October 2023 through 19 October 2023

ER -

Schwörer T, Schmidt JE, Chrysostomou D. Nav2CAN: Achieving Context Aware Navigation in ROS2 Using Nav2 and RGB-D sensing. In IST 2023 - IEEE International Conference on Imaging Systems and Techniques, Proceedings. IEEE Signal Processing Society. 2023. (IST 2023 - IEEE International Conference on Imaging Systems and Techniques, Proceedings). doi: 10.1109/IST59124.2023.10355731

Nav2CAN: Achieving Context Aware Navigation in ROS2 Using Nav2 and RGB-D sensing

Abstract

Conference

Bibliographical note

Keywords

UN SDGs

Access to Document

AUB Link

Other files and links

Fingerprint

IEEE International Conference on Imaging Systems and Techniques (IST 2023)

Aalborg Robotics Challenge (Organisational unit)

Cite this

Nav2CAN: Achieving Context Aware Navigation in ROS2 Using Nav2 and RGB-D sensing

Abstract

Conference

Bibliographical note

Keywords

UN SDGs

Access to Document

AUB Link

Other files and links

Fingerprint

Activities

IEEE International Conference on Imaging Systems and Techniques (IST 2023)

Aalborg Robotics Challenge (Organisational unit)

Cite this