• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.3
• /
• pp.1241-1246
• /
• 2014

Take-out robots used for handling of the plastic parts manufactured with the injection mold are usually the gantry type that consists of long and thin links. In this study, we want to evaluate the safety of the take-out Robot structure through finite element analysis. The take-out Robot is automated robot to transport from one location to another in the molded article. The take-out Robot structure has a 380 kilogram weight, a 1300mm width, a 670.5mm depth and a 670mm height. It confirms the equivalent stress and the deformation of the load and its own weight through weight analysis. It looks for the natural frequency of the take-out robot through modal analysis. It confirms the acceleration, the normal stress and the deformation about the natural frequency of the take-out robot through response analysis. Also It repeats the analysis by changing the structure of the take-out robot, to confirm the results and it is determined whether the safety of the structure. These analysis results are effectively used to reduce the vibration of the take-out robot.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.92-95
• /
• 2004

This study proposes an industrial rehabilitation robot system which can exercise two joints in 3 dimensional spaces. The robot kinematics analysis and the results of studies on each joint for the rehabilitation robot could verify possibility of rehabilitation motion to exercise a joint. The force and torques sensor not only measures a rehabilitation performance of subjects between the abnormal limb and the manipulator, but also carries out an important function of safety device to prevent accidents. Also, limit sensors and emergency stop switch are used for high safety in this system. In this real test, the possibility of rehabilitation robot system is evaluated by C&R ARM I which is similar to upper-limb.

• The Journal of Korea Robotics Society
• /
• v.5 no.1
• /
• pp.77-84
• /
• 2010

This paper proposes a bridge inspection system using a robot to manage the safety status of bridges. A conventional bridge inspection has a lot of problems because inspection is conducted manually by human. As an alternative, we are to develop a robot system having machine vision and this robot system is mounted on an end linkage of specially designed car having seven DOF (Degrees Of Freedom) to inspect cracks beneath bridge. This system is able to check a status of the bridge and record its changes every other year. As a result, the developed robot system offers us the inspection result of quality and reliability about the bridge inspection status. Also, we have tested the effectiveness of the suggested system through outdoor experiments.

• Proceedings of the KIEE Conference
• /
• 1990.07a
• /
• pp.492-495
• /
• 1990

This paper introduces a path planning technique for a mobile robot in the presence of obstacles. In the technique, workspace is described by regional graph and represented obstacles by the three-layer neural network. And performance cost is defined under consideration both the traveling distance and the safety of a mobile robot. Then a collision-free path is obtained using the neural optimization technique.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2013.05a
• /
• pp.429-430
• /
• 2013

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2011.06a
• /
• pp.337-338
• /
• 2011

• The Journal of Korea Robotics Society
• /
• v.18 no.2
• /
• pp.225-232
• /
• 2023

With the recent increase of multiple robots cooperating in smart manufacturing logistics environments, it has become very important how to predict the safety and efficiency of the individual tasks and dynamically assign them to the best one of available robots. In this paper, we propose a novel task policy learner based on deep relational reinforcement learning for predicting the safety and efficiency of tasks in a multi-robot manufacturing logistics environment. To reduce learning complexity, the proposed system divides the entire safety/efficiency prediction process into two distinct steps: the policy parameter estimation and the rule-based policy inference. It also makes full use of domain-specific knowledge for policy rule learning. Through experiments conducted with virtual dynamic manufacturing logistics environments using NVIDIA's Isaac simulator, we show the effectiveness and superiority of the proposed system.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.33 no.8
• /
• pp.849-857
• /
• 2009

To guarantee the safety and reliability of obsolete thermal power plants, on site routine patrol in their facilities has been done by human workers. Due to their poor working environments, however, a patrol robot system has been gradually required instead of the human workers from the viewpoint of the workers' safety and work efficiency. For this purpose, this paper presents a patrol robot, controllers, and its control scheme. Especially, this robot system uses a line tracing algorithm, which uses a vision camera instead of IR sensors, and an RFID system for its patrol operation. We confirmed its effectiveness through experiments.

• International Journal of Safety
• /
• v.6 no.1
• /
• pp.11-15
• /
• 2007

In many cases, rescue robots work under harsh conditions such as the presence of various obstacles, high temperature, and limited visibility, etc. These robots are required to have tough mechanical structure, good sensing and control capability, and reliable communication capability for receiving operator's command and sending information on the state of the robot and environment. In this study, a rescue robot that can investigate hazardous or disastrous sites with these capabilities is designed and implemented. The performance of the proposed rescue robot is tested under simulated disastrous environment.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.368-371
• /
• 2003

A new accurate and reliable human-in-the-loop control by artificial neural network (ANN) for human assistance robot was proposed in this paper. The principle of human-in-the-loop control by ANN was explained including the system architecture of human assistance robot control the design of the controller the control process as well as the switching of the different control patterns. Based on the proposed method, the control of meal assistance robot was implemented. In the controller of meal assistance robote a feedforward ANN controller was designed for the accurate position control. For safety a feedback ANN forcefree control was installed in the meal assistance robot. Both controllers have taken fully into account the influence of human arm upon the meal assistance robote and they can be switched smoothly based on the external force induced by the challenged person arm. By the experimental and simulation work of this method for an actual meal assistance robote the effectiveness of the proposed method was verified.