Object-Based Reliable Visual Navigation for Mobile Robot

Wang, Fan; Zhang, Chaofan; Zhang, Wen; Fang, Cuiyun; Xia, Yingwei; Liu, Yong; Dong, Hao

doi:10.3390/s22062387

Cited by 14 publications

(9 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers have enhanced the visual reasoning ability by introducing semantic features [ 56 ], and improving the understanding of images can likewise generate more accurate questions. The question-and-answer-based interactive system can also be deployed on robots [ 57 , 58 ] to respond to complex and changing environments by increasing the flexibility of decision-making.…”

Section: Discussionmentioning

confidence: 99%

Diversity Learning Based on Multi-Latent Space for Medical Image Visual Question Generation

Zhu

Togo

Ogawa

et al. 2023

Sensors

View full text Add to dashboard Cite

Auxiliary clinical diagnosis has been researched to solve unevenly and insufficiently distributed clinical resources. However, auxiliary diagnosis is still dominated by human physicians, and how to make intelligent systems more involved in the diagnosis process is gradually becoming a concern. An interactive automated clinical diagnosis with a question-answering system and a question generation system can capture a patient’s conditions from multiple perspectives with less physician involvement by asking different questions to drive and guide the diagnosis. This clinical diagnosis process requires diverse information to evaluate a patient from different perspectives to obtain an accurate diagnosis. Recently proposed medical question generation systems have not considered diversity. Thus, we propose a diversity learning-based visual question generation model using a multi-latent space to generate informative question sets from medical images. The proposed method generates various questions by embedding visual and language information in different latent spaces, whose diversity is trained by our newly proposed loss. We have also added control over the categories of generated questions, making the generated questions directional. Furthermore, we use a new metric named similarity to accurately evaluate the proposed model’s performance. The experimental results on the Slake and VQA-RAD datasets demonstrate that the proposed method can generate questions with diverse information. Our model works with an answering model for interactive automated clinical diagnosis and generates datasets to replace the process of annotation that incurs huge labor costs.

show abstract

Section: Discussionmentioning

confidence: 99%

Diversity Learning Based on Multi-Latent Space for Medical Image Visual Question Generation

Zhu

Togo

Ogawa

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…This type of map allows robots to operate and maintain the semantic information of each entity on the map. So it is more conducive for robots to understand the environment and interact with entities in the environment, improving the practicality of the map [247]. Reference [45] proposed a voxel-based semantic visual SLAM system based on mask-RCNN and KinectFusion algorithm.…”

Section: For Sencementioning

confidence: 99%

An Overview on Visual SLAM: From Tradition to Semantic

et al. 2022

View full text Add to dashboard Cite

Visual SLAM (VSLAM) has been developing rapidly due to its advantages of low-cost sensors, the easy fusion of other sensors, and richer environmental information. Traditional visionbased SLAM research has made many achievements, but it may fail to achieve wished results in challenging environments. Deep learning has promoted the development of computer vision, and the combination of deep learning and SLAM has attracted more and more attention. Semantic information, as high-level environmental information, can enable robots to better understand the surrounding environment. This paper introduces the development of VSLAM technology from two aspects: traditional VSLAM and semantic VSLAM combined with deep learning. For traditional VSLAM, we summarize the advantages and disadvantages of indirect and direct methods in detail and give some classical VSLAM open-source algorithms. In addition, we focus on the development of semantic VSLAM based on deep learning. Starting with typical neural networks CNN and RNN, we summarize the improvement of neural networks for the VSLAM system in detail. Later, we focus on the help of target detection and semantic segmentation for VSLAM semantic information introduction. We believe that the development of the future intelligent era cannot be without the help of semantic technology. Introducing deep learning into the VSLAM system to provide semantic information can help robots better perceive the surrounding environment and provide people with higher-level help.

show abstract

“…Mobile robots are one of the platforms that are often used for robotics education [ 6 ]. Related discussions include multi-sensor fusion [ 7 ], localization [ 8 ], navigation [ 9 ], and simultaneous localization and mapping [ 10 ]. Meanwhile, many educational institutions are developing practical robotics experiments.…”

Section: Introductionmentioning

confidence: 99%

A Robotics Experimental Design Method Based on PDCA: A Case Study of Wall-Following Robots

Wong,

Pu,

Wong

2024

Sensors

View full text Add to dashboard Cite

There is a lack of research that proposes a complete and interoperable robotics experimental design method to improve students’ learning outcomes. Therefore, this study proposes a student-oriented method based on the plan-do-check-act (PDCA) concept to design robotics experiments. The proposed method is based on our teaching experience and multiple practical experiences of allowing students to do hands-on experiments. It consists of eight steps, mainly including experimental goals, experimental activities, robot assembly, robot control, in-class evaluation criteria, and after-class report requirements. The after-class report requirements designed in the proposed method can help students improve their report-writing abilities. A wall-following robotics experiment designed using the PDCA method is proposed, and some students’ learning outcomes and after-class reports in this experiment are presented to illustrate the effectiveness of the proposed method. This experiment also helps students to understand the fundamental application of multi-sensor fusion technology in designing an autonomous mobile robot. We can see that the proposed reference examples allow students to quickly assemble two-wheeled mobile robots with four different sensors and to design programs to control these assembled robots. In addition, the proposed in-class evaluation criteria stimulate students’ creativity in assembling different wall-following robots or designing different programs to achieve this experiment. We present the learning outcomes of three stages of the wall-following robotics experiment. Three groups of 42, 37, and 44 students participated in the experiment in these three stages, respectively. The ratios of the time required for the robots designed by students to complete the wall-following experiment, less than that of the teaching example, are 3/42 = 7.14%, 26/37 = 70.27%, and 44/44 = 100%, respectively. From the comparison of learning outcomes in the three stages, it can be seen that the proposed PDCA-based design method can indeed improve students’ learning outcomes and stimulate their active learning and creativity.

show abstract

Object-Based Reliable Visual Navigation for Mobile Robot

Cited by 14 publications

References 59 publications

Diversity Learning Based on Multi-Latent Space for Medical Image Visual Question Generation

Diversity Learning Based on Multi-Latent Space for Medical Image Visual Question Generation

An Overview on Visual SLAM: From Tradition to Semantic

A Robotics Experimental Design Method Based on PDCA: A Case Study of Wall-Following Robots

Contact Info

Product

Resources

About