Sistema de detección de robots humanoides en ambientes semiestructurados basado en visión estereoscópica

Oscar Herrera; Yesenia González; Paola Cortez; Benito Granados

doi:10.36561/ING.21.8

Authors

Oscar Herrera Instituto Politécnico Nacional, México https://orcid.org/0000-0002-7805-3677
Yesenia González Instituto Politécnico Nacional, México https://orcid.org/0000-0003-2370-4660
Paola Cortez Instituto Politécnico Nacional, México https://orcid.org/0000-0003-2338-8581
Benito Granados Instituto Politécnico Nacional, México https://orcid.org/0000-0003-1958-7780

DOI:

https://doi.org/10.36561/ING.21.8

Keywords:

Artificial vision, Stereo video, Convolutional neural network, Humanoid robots

Abstract

This work proposes the design, development and implementation of an artificial vision system based on stereo video, which is executed in an embedded system, to identify humanoid robots within a semi-structured area. The embedded system uses an Intel RealSense camera that, in addition to being able to obtain distances to objects due to its stereo vision, is capable of discriminating information after a distance threshold determined by the user, eliminating objects in the background of the scene and, through Image recognition based on a convolutional neural network recognizes the humanoid robots within it. The application of the system is based on the Robocup Humanoid League contest, where two teams of robots play soccer, so in addition to recognizing humanoid robots at different angles and distances, the system can classify recognized robots as companions or opponents (depending on the recognition of color marks they carry), emulating that, in the future, the proposed system will be mounted on another humanoid robot.

Downloads

Download data is not yet available.

References

«RoboCup Humanoid League» 2020. [En línea]. Available: https://humanoid.robocup.org [Accessed:18 – abril 2021].

«Amazons collaborative robots offer peek into the future» Available: https://www.businesstimes.com.sg/technology/amazons-collaborative-robots-offer-peek-into-the-future Accessed:14 - septiembre - 2021].

«TASKI. The ultimate cleaning machine» [En línea]. Available: https://taski.com/taski-products/swingobot-000/?lang=es [Accessed:14 - septiembre - 2021].

Robocup Federation official website. Available: https://www.robocup.org [Accessed:18 - abril - 2021].

T. Abbas Shangari, S. Sadeghnejad, J. Baltes. «Importance of Humanoid Robot Detection». In: Goswami A., Vadakkepat P. (eds) Humanoid Robotics A Reference. Springer, Dordrecht. 2018: https://doi.org/10.1007/978-94-007-7194-9_141-1

K. Sabe, M. Fukuchi, JS Gutmann, T. Ohashi,K. Kawamoto, T. Yoshigahara. «Obstacle avoidance and path planning for humanoid robots using stereo vision. In obotics and Automation,» 2004. Proceedings. ICRA’04.2004 IEEE International Conference on 2004 Apr (Vol. 1, pp. 592-597). IEEE.

H. Farazi, S. Behnke. «Real-Time Visual Tracking and Identification for a Team of Homogeneous Humanoid Robots,» In Proceedings of 20th RoboCup International Symposium, Leipzig, Germany, July 2016.

TA. Shangari, V. Shams, B. Azari, F. Shamshirdar, J. Baltes, S. Sadeghnejad. «Inter-humanoid robot interaction with emphasis on detection: a comparison study». The Knowledge Engineering Review. 2017 Feb; 32.

J. Mohammad, A. Sina Mokhtardeh, A. Sajjad, S. Saeed, S. Soroush y B. Jacky, «Humanoid Robot Detection using Deep learning: A speed-Acuracy Tradeoff,» Taiwan, 2017.

A. Saxena, S.H. Chung & A. Ng. «3-D Depth Reconstruction from a Single Still Image». Int J ComputVis 76, 53–69 (2008).

I. R. SDK, «pyrealsense2’s documentation,» 2018. [En línea]. Available: https://intelrealsense.github.io/librealsense/python_docs/_generated/pyrealsense2.html.

J. Redmon, S. Divvala, R. Girshick and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 779-788, doi: 10.1109/CVPR.2016.91.

M. Mitchel Tom, Machine Learning, McGraw-Hill, 1997

A. Bochkovskiy, C.-Y. Wang y M. L. Hong-Yuan, «arXiv.orgLogin,» 23 Apr 2020. [En línea]. Available: https://arxiv.org/pdf/2004.10934.pdf. [Último acceso: Mayo 2020].

A. Bochkovskiy, «github,» 2020. [En línea]. Available: https://github.com/AlexeyAB/darknet/releases/download/darknet_yolo_v3_optimal/yolov4.conv.137.

R.C. Gonzalez, R. E. Woods. «Digital Image Processing, » Prentice Hall, 3ª edición, 2006.

Siddharth Misra, Yaokun Wu, «Machine learning assisted segmentation of scanning electron microscopy images of organic-rich shales with feature extraction and feature ranking », Machine Learning for Subsurface Characterization, 2020.