A Lightweight Operation Mode Decision Method for Cleaning Robots Driven by Garbage Attributes Perception
The intelligent operation mode decision scheme has been proved to be a promising solution for enhancing the cleaning performance of cleaning robots. In this paper, we propose a lightweight operation mode decision method for cleaning robots, driven by garbage attributes perception. The method aims to...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2024-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10412059/ |
_version_ | 1797335503410823168 |
---|---|
author | Zhigang Zhou Dongbo Zhang Jiang Zhu Hongzhong Tang |
author_facet | Zhigang Zhou Dongbo Zhang Jiang Zhu Hongzhong Tang |
author_sort | Zhigang Zhou |
collection | DOAJ |
description | The intelligent operation mode decision scheme has been proved to be a promising solution for enhancing the cleaning performance of cleaning robots. In this paper, we propose a lightweight operation mode decision method for cleaning robots, driven by garbage attributes perception. The method aims to enable cleaning robots to intelligently select the most appropriate operation mode when dealing with different types of garbage, thereby improving their cleaning efficiency. Specifically, we propose a lightweight garbage attributes extraction network (LGAE-Net) based on inverted residuals, which adopts the proposed deep dynamic attention convolution (DDA-Conv) as its basic structure and adaptively extracts share features of attributes while reducing computational complexity. Then, the network adopts a multi-label architecture to predict multiple attributes, and a dynamic weighting joint learning strategy is introduced to alleviate the problem of imbalanced difficulty in attribute learning. Finally, based on the extraction of attributes, a decision module for operation mode is constructed. This module enables fast decision from the perception of attributes to the selection of an operation mode. Our proposed method achieves 94.26% decision accuracy on the test dataset, and the single-sheet recognition rate is only 1.63 msec. In addition, it maintains a parameter count (Params(M)) of approximately 2.97M and floating-point operations (FLOPs(M)) of only 94.91M, which reflects the excellent balance of accuracy and efficiency of the method, and can meet the real-time requirements of cleaning robots. |
first_indexed | 2024-03-08T08:39:09Z |
format | Article |
id | doaj.art-48522612a18847f3a12e43815ca66cd6 |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-03-08T08:39:09Z |
publishDate | 2024-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-48522612a18847f3a12e43815ca66cd62024-02-02T00:03:42ZengIEEEIEEE Access2169-35362024-01-0112153081532010.1109/ACCESS.2024.335778110412059A Lightweight Operation Mode Decision Method for Cleaning Robots Driven by Garbage Attributes PerceptionZhigang Zhou0https://orcid.org/0009-0004-0228-3785Dongbo Zhang1https://orcid.org/0000-0003-3776-3426Jiang Zhu2https://orcid.org/0000-0003-3570-7594Hongzhong Tang3College of Automation and Electronics Information, Xiangtan University, Xiangtan, ChinaCollege of Automation and Electronics Information, Xiangtan University, Xiangtan, ChinaCollege of Automation and Electronics Information, Xiangtan University, Xiangtan, ChinaCollege of Automation and Electronics Information, Xiangtan University, Xiangtan, ChinaThe intelligent operation mode decision scheme has been proved to be a promising solution for enhancing the cleaning performance of cleaning robots. In this paper, we propose a lightweight operation mode decision method for cleaning robots, driven by garbage attributes perception. The method aims to enable cleaning robots to intelligently select the most appropriate operation mode when dealing with different types of garbage, thereby improving their cleaning efficiency. Specifically, we propose a lightweight garbage attributes extraction network (LGAE-Net) based on inverted residuals, which adopts the proposed deep dynamic attention convolution (DDA-Conv) as its basic structure and adaptively extracts share features of attributes while reducing computational complexity. Then, the network adopts a multi-label architecture to predict multiple attributes, and a dynamic weighting joint learning strategy is introduced to alleviate the problem of imbalanced difficulty in attribute learning. Finally, based on the extraction of attributes, a decision module for operation mode is constructed. This module enables fast decision from the perception of attributes to the selection of an operation mode. Our proposed method achieves 94.26% decision accuracy on the test dataset, and the single-sheet recognition rate is only 1.63 msec. In addition, it maintains a parameter count (Params(M)) of approximately 2.97M and floating-point operations (FLOPs(M)) of only 94.91M, which reflects the excellent balance of accuracy and efficiency of the method, and can meet the real-time requirements of cleaning robots.https://ieeexplore.ieee.org/document/10412059/Attribute learningcleaning robotslightweight networkmultiple modes decision |
spellingShingle | Zhigang Zhou Dongbo Zhang Jiang Zhu Hongzhong Tang A Lightweight Operation Mode Decision Method for Cleaning Robots Driven by Garbage Attributes Perception IEEE Access Attribute learning cleaning robots lightweight network multiple modes decision |
title | A Lightweight Operation Mode Decision Method for Cleaning Robots Driven by Garbage Attributes Perception |
title_full | A Lightweight Operation Mode Decision Method for Cleaning Robots Driven by Garbage Attributes Perception |
title_fullStr | A Lightweight Operation Mode Decision Method for Cleaning Robots Driven by Garbage Attributes Perception |
title_full_unstemmed | A Lightweight Operation Mode Decision Method for Cleaning Robots Driven by Garbage Attributes Perception |
title_short | A Lightweight Operation Mode Decision Method for Cleaning Robots Driven by Garbage Attributes Perception |
title_sort | lightweight operation mode decision method for cleaning robots driven by garbage attributes perception |
topic | Attribute learning cleaning robots lightweight network multiple modes decision |
url | https://ieeexplore.ieee.org/document/10412059/ |
work_keys_str_mv | AT zhigangzhou alightweightoperationmodedecisionmethodforcleaningrobotsdrivenbygarbageattributesperception AT dongbozhang alightweightoperationmodedecisionmethodforcleaningrobotsdrivenbygarbageattributesperception AT jiangzhu alightweightoperationmodedecisionmethodforcleaningrobotsdrivenbygarbageattributesperception AT hongzhongtang alightweightoperationmodedecisionmethodforcleaningrobotsdrivenbygarbageattributesperception AT zhigangzhou lightweightoperationmodedecisionmethodforcleaningrobotsdrivenbygarbageattributesperception AT dongbozhang lightweightoperationmodedecisionmethodforcleaningrobotsdrivenbygarbageattributesperception AT jiangzhu lightweightoperationmodedecisionmethodforcleaningrobotsdrivenbygarbageattributesperception AT hongzhongtang lightweightoperationmodedecisionmethodforcleaningrobotsdrivenbygarbageattributesperception |