Related Experiment Video
Updated: Nov 20, 2025
13:44
Haptic/Graphic Rehabilitation: Integrating a Robot into a Virtual Environment Library and Applying it to Stroke Therapy
Published on: August 8, 2011
14.3K
Visual SLAM for robot navigation in healthcare facility.
Baofu Fang1,2,3, Gaofei Mei1, Xiaohui Yuan4
1School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, 230009, China.
Pattern Recognition
|January 26, 2021
Summary
This study introduces a new Simultaneous Localization and Mapping (SLAM) technology using semantic descriptors and knowledge graphs to enhance robot navigation in dynamic hospital environments, improving efficiency and reducing infection risks during pandemics.
Area of Science:
- Robotics
- Computer Vision
- Artificial Intelligence
Background:
- The COVID-19 pandemic highlighted the need for efficient and safe hospital operations.
- Existing Simultaneous Localization and Mapping (SLAM) technologies struggle with dynamic environments common in hospitals.
Purpose of the Study:
- To develop a novel SLAM technology for dynamic environments like hospitals.
- To improve robot navigation accuracy, efficiency, and safety in healthcare settings.
- To reduce the risk of cross-infection and aid in pandemic control.
Main Methods:
- Utilized RGB and depth images for SLAM.
- Developed a method incorporating knowledge graphs to handle dynamic objects.
- Constructed rotation-invariant and illumination-robust semantic descriptors based on a knowledge graph.
- Integrated semantic descriptors to eliminate dynamic objects and improve tracking.
Main Results:
- Demonstrated significant improvements in accuracy and robustness compared to state-of-the-art methods in dynamic environments.
- Successfully established semantic maps for robot-assisted medical services in healthcare facilities.
- Achieved competitive computational efficiency.
Conclusions:
- The proposed knowledge graph-based semantic SLAM method effectively addresses challenges in dynamic environments.
- This technology enhances robot positioning and tracking accuracy, crucial for hospital applications.
- The approach offers a promising solution for improving healthcare operations and safety, particularly during health crises.
