A ROS-based data-driven motion self-recognition system using deep-learning convolutional neural networks in a military unmanned ground vehicle

Fendy Santoso, Anthony Finn

Research output: Book chapter/Published conference paperConference paperpeer-review

Abstract

The ability to recognize motions is an important feature in cutting-edge robotics or autonomous systems, such as self-driving cars, humanoid robots, and human-robot interactions, resulting in improved safety and efficiency. Addressing this critical issue, we introduce a simple framework leveraging the benefits of the normalized real-time network traffic data of the middleware ROS platform formulated in the form of RGB or grayscale images to train the Convolutional Neural Network (CNN) system in order to learn the motion pattern of the robot. For our experimental platform, we employ the GVR-BOT Unmanned Ground Vehicle (UGV), developed by the U.S. Army Combat Capabilities Development Command (CCDC), Ground Vehicle Systems Center (GVSC). We rigorously study the performance of our motion recognition system under several different lengths of data (epochs). In addition, we compare the relative merits of our proposed system with respect to the performance of the well-known ‘Bag-of-Features’ (BoFs) detection algorithm widely implemented in computer vision. Our research indicates the efficacy of the proposed motion recognition system as we can achieve a reasonably high detection accuracy ≥ 0.97 within a minimum detection time of two epochs highlighting its real-time benefits. Overall, our recognition system can also achieve superior detection performance compared to the efficacy of the BoFs algorithm.
Original languageEnglish
Title of host publication2024 International Joint Conference on Neural Networks, IJCNN 2024 - Proceedings
Place of PublicationJapan
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages1-8
ISBN (Electronic)9798350359312
ISBN (Print)9798350359329
DOIs
Publication statusPublished - 30 Jun 2024
EventInternational Joint Conference on Neural Networks (IJCNN) 2024 - PACIFICO Yokohama, Yokohama, Japan
Duration: 30 Jun 202405 Jul 2024
https://2024.ieeewcci.org/
https://confcats-siteplex.s3.us-east-1.amazonaws.com/wcci24/IEEE_WCCI_2024_Program_d597587f62.pdf (Program)
https://ieeexplore.ieee.org/xpl/conhome/10649807/proceeding (Proceedings)
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10650734 (Front matter)

Publication series

NameProceedings of the International Joint Conference on Neural Networks

Conference

ConferenceInternational Joint Conference on Neural Networks (IJCNN) 2024
Country/TerritoryJapan
CityYokohama
Period30/06/2405/07/24
OtherIEEE WCCI 2024 is the world’s largest technical event on computational intelligence, featuring the three flagship conferences of the IEEE Computational Intelligence Society (CIS) under one roof: The International Joint Conference on Neural Networks (IJCNN), the IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) and the IEEE Congress on Evolutionary Computation (IEEE CEC).
Internet address

Fingerprint

Dive into the research topics of 'A ROS-based data-driven motion self-recognition system using deep-learning convolutional neural networks in a military unmanned ground vehicle'. Together they form a unique fingerprint.

Cite this