Visual Perception Framework for an Intelligent Mobile Robot

Lee, Chung-Yeon; Lee, Hyundo; Hwang, In‐June; Zhang, Byoung-Tak

doi:10.1109/ur49135.2020.9144932

Cited by 12 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study by [35] described the current representation of perception as one of the AMR applications drawbacks. Perception is essential when studying mobile robots [7].…”

Section: Perceptionmentioning

confidence: 99%

A review on object detection for autonomous mobile robot

Abdul-Khalil

Abdul-Rahman²,

Mutalib³

et al. 2023

IJ-AI

View full text Add to dashboard Cite

The advancement of autonomous mobile robots (AMR) is vastly being discovered and applied to several industries. AMR contributes to the development of artificial intelligence (AI), which focuses on the growth of human-interaction systems. However, it is safe to understand that mobile robots work closely in real-time and under changing surroundings. Similarly, some limitations may affect the efficiency of mobile robots. Thus, to improve the system's efficiency and accuracy, mobile robots should adopt the ability to detect incoming obstacles accurately. This paper presents the findings of a brief technology review aimed at identifying the current state of the art and future needs for AMR in object detection. This review paper is presented in the form of a narrative-literature review. Review articles were collected from 2015 until 2022 from journals or conference papers from well-known sources like IEEE Xplore, Science Direct, Scopus, and Web of Science (WOS). The analysis of the articles was discussed in four main topics, AI, object detection, AMR, and deep learning.

show abstract

“…The study by [35] described the current representation of perception as one of the AMR applications drawbacks. Perception is essential when studying mobile robots [7].…”

Section: Perceptionmentioning

confidence: 99%

A review on object detection for autonomous mobile robot

Abdul-Khalil

Abdul-Rahman²,

Mutalib³

et al. 2023

IJ-AI

View full text Add to dashboard Cite

show abstract

“…Particularly, this idea is becoming key in the development of mobile robots. 632,633 The TEM cannot be considered a mobile robot, although the constantly changing interaction with the environment (i.e., changing magnification and sample position) is comparable and could surely benefit from perceptual preprocessing. Even the holder handling and loading could be directly tackled with the mobile robot perspective!…”

Section: Artificial Human-like Systems: the Path Towards Automation?mentioning

confidence: 99%

Machine learning in electron microscopy for advanced nanocharacterization: current developments, available tools and future outlook

2022

View full text Add to dashboard Cite

show abstract

“…In the field of robot recognition, Lee et al [2] proposed a visual perception framework integrating multiple deep neural networks, which made the distributed application development of intelligent mobile robots more accessible and successfully recognized people, objects and human posture. In order to quickly and accurately detect the captured object and overcome the influence of complex interference in the environment, Song et al [3] proposed a new three-mode image fusion strategy, namely the visible depth-heat significance object detection.…”

Section: Introductionmentioning

confidence: 99%

Research on object classification based on visual-tactile fusion

Zhang

Bai

Shan

2023

Eighth International Conference on Electronic Technology and Information Science (ICETIS 2023)

View full text Add to dashboard Cite

As two modes of direct contact between robots and external environment, visual and tactile play a critical role in improving robot perception ability. In the real environment, it is difficult for the robot to achieve high accuracy when classifying objects only by a single mode (visual or tactile). In order to improve the classification accuracy of robots, a novel visual-tactile fusion method is proposed in this paper. Firstly, the ResNet18 is selected as the backbone network to extract visual features. To improve the accuracy of object localization and recognition in the visual network, the Position-Channel Attention Mechanism (PCAM) block is added after conv3 and conv4 of ResNet18. Then, the four-layer one-dimensional convolutional neural network is used to extract tactile features, and the extracted tactile features are fused with visual features at the feature layer. Finally, the experimental results demonstrate that compared with the existing methods, on the self-made dataset VHAC-52, the proposed method has improved the AUC and ACC by 1.60% and 1.47%, respectively.

show abstract

Visual Perception Framework for an Intelligent Mobile Robot

Cited by 12 publications

References 10 publications

A review on object detection for autonomous mobile robot

A review on object detection for autonomous mobile robot

Machine learning in electron microscopy for advanced nanocharacterization: current developments, available tools and future outlook

Research on object classification based on visual-tactile fusion

Contact Info

Product

Resources

About