Pioneering Technology for Intelligent Environmental Sensing Using Unmanned Mobile Robot

JI Laboratory
Associate Professor：JI Yonghoon

E-mail：
［Research areas］
Robotics, sensor data processing
［Keywords］
Mobile robot, robot vision, environmental sensing, SLAM (simultaneous localization and mapping)

Skills and background we are looking for in prospective students

To have basic knowledge of mathematics such as linear algebra and probability theory, and the general concepts of robotics, instrumentation engineering, and machine learning would be desirable. Highly motivated students with curiosity are welcome. In order to implement ideas on robotic systems, it is advantageous if students are accustomed to creating simple hardware and programming languages, especially C⁺⁺ or Python.

What you can expect to learn in this laboratory

Robotics is a special field in which various areas such as mechanical, electronic, computer, control, and instrumentation engineering are seamlessly integrated. Thus, SI (system integration) technology is very important. Depending on the specific research theme, students will be able to acquire a wide range of engineering knowledge. In addition, since we are actively conducting research that is applicable to real sites, students can learn the ability to apply state-of-the-art technology to various problems in our society.

【Job category of graduates】 Manufacturing industry, IT industry, academia, etc.

Research outline

We conduct various research required for real-world applications through robot technology. Specifically, we analyze data from the various sensors mounted on the unmanned mobile robot and extract shape information or physical properties distributed in the environment such as material information to utilize them to solve various problems in our society.

1. Semantic Map Building by Exploration Robot in Disaster Area

We develop a semi-autonomous mobile robot system that builds a wide-area survey map including semantic information to carry out damage monitoring in disaster areas. To this end, sensor fusion technology is developed for multiple types of sensors mounted on the robot to build map information including various physical properties of the environment. Each elemental technology as shown in Fig. 1 is developed in cooperation with other universities. The semantic survey map can be used for the prevention of secondary disasters and recovery plans.

2. Underwater Sensing Using Acoustic Camera

Recently, as shown in Fig. 2, the development of acoustic cameras, which can generate high-resolution images in 3D space, even in turbid water, has facilitated our understanding of underwater situations. This type of sonar sensors is relatively small and can easily be mounted on an underwater robot. Moreover, it can analyze the properties of the material distributed in the environment based on measured data. This research focuses on generating a 3D material distribution map using the acoustic camera under a waterfront development environment where human cannot directly access, such as construction and reclamation projects related to airports, ports, and submarine tunnels, etc. Providing the underwater map information to the relevant decision-making organizations, it is expected to be utilized for the future plan of the waterfront development.

3. Autonomous Mobile Robot Navigation

Navigation technology for autonomous mobile robots has been intensively studied in recent decades, and many technologies have already been put into practical use. Our goal is to improve the navigation performance of autonomous mobile robots based on measurement data from various next-generation sensors.

Key publications

1. Y. Wang, Y. Ji, H. Woo, Y. Tamura, H. Tsuchiya, A. Yamashita, and H. Asama, "Acoustic Camera-based Pose Graph SLAM for Dense 3-D Mapping in Underwater Environments," IEEE Journal of Oceanic Engineering, 46(3), PP. 829-847, 2021.
2. Y. Ji, Y. Tanaka, Y. Tamura, M. Kimura, A. Umemura, Y. Kaneshima, H. Murakami, A. Yamashita, and H. Asama, “Adaptive Motion Planning Based on Vehicle Characteristics and Regulations for Off-Road UGVs,” IEEE Transection on Industrial Informatics, 15(1), pp. 599-611, 2019.
3. Y. Ji, A. Yamashita, and H. Asama, “Automatic Calibration of Camera Sensor Network Based on 3D Texture Map Information,” Robotics and Autonomous Systems, 87(1), pp. 313-328, 2017.

Equipment

Wheeled and crawler type mobile robots
Sensors for environmental measurement, such as LiDAR, range sensor, optical camera, thermography, acoustic camera, etc.