Hyongjin Kim

GPU-based real-time RGB-D 3D SLAM

This paper proposes a GPU (graphics processing unit)-based real-time RGB-D (red-green-blue depth) 3D SLAM (simultaneous localization and mapping) system. RGB-D data contain 2D image and per-pixel depth information. First, 6-DOF (degree-of-freedom) visual odometry is obtained through the 3D-RANSAC (three-dimensional random sample consensus) algorithm with image features. And a projective ICP (iterative closest point) algorithm gives an accurate odometry estimation result with depth information. For speed up extraction of features and ICP computation, GPU-based parallel computation is performed. After detecting loop closure, a graph-based SLAM algorithm optimizes trajectory of the sensor and 3D map.

2D Image Feature-Based Real-Time RGB-D 3D SLAM

This paper proposes a real-time RGB-D (red-green-blue depth) 3D SLAM (simultaneous localization and mapping) system. Kinect style sensors give RGB-D data which contains 2D image and per-pixel depth information. 6-DOF (degree-of-freedom) visual odometry is obtained through the 3D-RANSAC (three-dimensional random sample consensus) algorithm with image features and depth information. For speed up extraction of features, parallel computation is performed on a GPU (graphics processing unit) processor. After a feature manager detects loop closure, a graph-based SLAM algorithm optimizes trajectory of the sensor and 3D map. Experimental results show the processing rate over 20 Hz.

Experimental Tests of Autonomous Jellyfish Removal Robot System JEROS

Recently, the increase in population of jellyfish is becoming a great menace to the oceans ecosystem, which leads to drastic damage to the fishery industries. To overcome this problem, a jellyfish removal system with trawl boats equipped with the jellyfish removal net has been suggested by NFRDI. However, the system needs large ships which need to be operated by a lot of human operators. Thus, this paper represents the design and implementation of an autonomous jellyfish removal robot system, called JEROS. The JEROS consists of an autonomous surface vehicle (ASV), a grid for jellyfish removal, and an autonomous navigation system. Once jellyfish are detected using a camera, the jellyfish removal scenario is started with generating efficient path to remove the jellyfish. Finally, the jellyfish is sliced up with the grid installed underneath the JEROS by following the generated path. The prototype of the system was implemented, and its feasibility was demonstrated through outdoor experiments and field tests.

Mobile robot localization by matching 2D image features to 3D point cloud

In this paper we describe a method for solving a mobile robot localization problem using prior data. By matching 2D image features to a 3D point cloud, the robot position is estimated in the prior point cloud. We prove our method by testing at specific locations over the whole point clod data.

Development of jellyfish removal robot system JEROS

This paper represents a novel autonomous jellyfish removal robot system, called JEROS (Jellyfish Elimination RObotic Swarm). The JEROS consists of an autonomous surface vehicle (ASV), a grid for jellyfish removal, and an autonomous navigation system. Once jellyfish are detected using a camera, efficient path to remove the jellyfish is generated. Then, the jellyfish are sliced up with the grid installed underneath the JEROS by following the path. The prototype was implemented, and its feasibility was demonstrated through field tests.

Feature-Based 6-DoF Camera Localization Using Prior Point Cloud and Images

In this paper, we present a new localization algorithm to estimate the localization of a robot based on prior data. Over the past decade, the emergence of numerous ways to utilize various prior data has opened up possibilities for their applications in robotics technologies. However, challenges still remain in estimating a robot’s 6-DoF position by simply analyzing the limited information provided by images from a robot. This paper describes a method of overcoming this technical hurdle by calculating the robot’s 6-DoF location. It only utilizes a current 2D image and prior data, which consists of its corresponding 3D point cloud and images, to calculate the 6-DoF position. Furthermore, we employed the SURF algorithm to find the robot’s position by using the image’s features and the 3D projection method. Experiments were conducted by the loop of 510m trajectory, which is included the prior data. It is expected that our method can be applied to broad areas by using enormous data such as point clouds and street views in the near future.

Image-based localization using prior map database and Monte Carlo Localization

The aim of this paper is to propose an image and map data-based localization method applicable to a variety of environments. For the localization, we use prior map database, image-based localization method, and MCL (Monte Carlo Localization). The results were confirmed by open data set in a variety of environments. The experimental results show the feasibility of the proposed method for the robot localization.

Graph Structure-Based Simultaneous Localization and Mapping with Iterative Closest Point Constraints in Uneven Outdoor Terrain

The purpose of this study is to propose a novel mobile robot localization method applicable to outdoor environments, such as an uneven terrain. In order to solve the robot localization problem, we exploit state of the art graph-based SLAM (Simultaneous Localization and Mapping) algorithm and ICP (Iterative Closest Point) algorithm considering the gyroscopic data as a constraint for a graph structure. We confirm our method by testing actual sensor data acquired from a vehicle in outdoor environments and show that our proposed method is improved and suitable for uneven terrain.

Formation Control Experiment of Autonomous Jellyfish Removal Robot System JEROS

The proliferation of jellyfish is threatening marine ecosystem and has caused severe damage to marine-related industries. An autonomous jellyfish removal robot system, named JEROS (Jellyfish Elimination Robotic Swarm), has been developed to cope with this problem. This paper presents formation control of JEROS and related experimental results through field tests. The JEROS is extended to multi-agent robot system and employs the leader-follower algorithm for formation control. The Theta* path planning algorithm is employed to generate an efficient path. Three prototypes of JEROS are implemented, and the feasibility of their formation control and the performance of jellyfish removal were demonstrated through field tests in Masan Bay located in the southern coast of South Korea.