This paper presents a 6-DOF relocalization using a 3D laser scanner and a monocular camera. A relocalization problem in robotics is to estimate pose of sensor when a robot revisits the area. A deep convolutional neural network (CNN) is designed to regress 6-DOF sensor pose and trained using both RGB image and 3D point cloud information in end-to-end manner. We generate the new input that consists of RGB and range information. After training step, the relocalization system results in the pose of the sensor corresponding to each input when a new input is received. However, most of cases, mobile robot navigation system has successive sensor measurements. In order to improve the localization performance, the output of CNN is used for measurements of the particle filter that smooth the trajectory. We evaluate our relocalization method on real world datasets using a mobile robot platform.

Recently, development of robot technology has been actively investigated that industrial robots are used in various other fields. However, the interface of the industrial robot is limited to the planned and manipulated path according to the target point and reaching time of the robot arm. Thus, it is not easy to create or change the various paths of the robot arm in other applications, and it is not easy to control the robot so that the robot arm passes the specific point precisely at the desired time during the course of the path. In order to overcome these limitations, this paper proposes a new-media content management platform that can manipulate 6 DOF industrial robot arm using 3D game engine. In this platform, the user can directly generate the motion of the robot arm in the UI based on the 3D game engine, and can drive the robot in real time with the generated motion. The proposed platform was verified using 3D game engine Unity3D and KUKA KR-120 robot.

Static balance of an articulated robot arm at various configurations requires a torque compensating for the gravitational torque of each joint due to the robot mass. Such compensation torque can be provided by a spring-based counterbalance mechanism. However, simple installation of a counterbalance mechanism at each pitch joint does not work because the gravitational torque at each joint is dependent on other joints. In this paper, a 6 DOF industrial robot arm based on the parallelogram for multi-DOF counterbalancing is proposed to cope with this problem. Two passive counterbalance mechanisms are applied to pitch joints, which reduces the required torque at each joint by compensating the gravitational torque. The performance of this mechanism is evaluated experimentally.

In general, the attitude of a high-speed planning boat changes following a speed change. Since the hydrodynamic forces acting on a ship differ according to the change of its underwater shape, it is difficult to estimate its hydrodynamic force compared to that of a large commercial ship. In this paper, 6 Degrees Of Freedom (DOF) equations of motion that express the maneuvering motion of a planning boat are modeled by analyzing its motion characteristics based on various sea trial tests. Finally, a maneuvering simulation is carried out and a validation of the equations of motion is confirmed with the results of sea trial tests.