• Journal of Advanced Research in Ocean Engineering
• /
• v.3 no.3
• /
• pp.136-148
• /
• 2017

The paper presents dual arm ROV manipulation using deep reinforcement learning. The purpose of this underwater manipulator is to investigate and excavate natural resources in ocean, finding lost aircraft blackboxes and for performing other extremely dangerous tasks without endangering humans. This research work emphasizes on a self-learning approach using Deep Reinforcement Learning (DRL). DRL technique allows ROV to learn the policy of performing manipulation task directly, from raw image data. Our proposed architecture maps the visual inputs (images) to control actions (output) and get reward after each action, which allows an agent to learn manipulation skill through trial and error method. We have trained our network in simulation. The raw images and rewards are directly provided by our simple Lua simulator. Our simulator achieve accuracy by considering underwater dynamic environmental conditions. Major goal of this research is to provide a smart self-learning way to achieve manipulation in highly dynamic underwater environment. The results showed that a dual robotic arm trained for a 3DOF movement successfully achieved target reaching task in a 2D space by considering real environmental factor.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2001.04a
• /
• pp.249-254
• /
• 2001

Abstract In this paper, we propose a method of cooperative control based on artifical intelligent system in distributed autonomous robotic system. In general, multi-agent behavior algorithm is simple and effective for small number of robots. And multi-robot behavior control is a simple reactive navigation strategy by combining repulsion from obstacles with attraction to a goal. However when the number of robot goes on increasing, this becomes difficult to be realized because multi-robot behavior algorithm provide on multiple constraints and goals in mobile robot navigation problems. As the solution of above problem, we propose an architecture of fuzzy system for each multi-robot speed control and fuzzy-neural network for obstacle avoidance. Here, we propose an architecture of fuzzy system for each multi-robot speed control and fuzzy-neural network for their direction to avoid obstacle. Our focus is on system of cooperative autonomous robots in environment with obstacle. For simulation, we divide experiment into two method. One method is motor schema-based formation control in previous and the other method is proposed by this paper. Simulation results are given in an obstacle environment and in an dynamic environment.

• The Journal of Korea Robotics Society
• /
• v.3 no.1
• /
• pp.23-32
• /
• 2008

This paper presents a task planning system for a steward robot, which has been developed as an interactive intermediate agent between an end-user and a complex smart home environment called the ISH (Intelligent Sweet Home) at KAIST (Korea Advanced Institute of Science and Technology). The ISH is a large-scale robotic environment with various assistive robots and home appliances for independent living of the elderly and the people with disabilities. In particular, as an approach for achieving human-friendly human-robot interaction, we aim at 'simplification of task commands' by the user. In this sense, a task planning system has been proposed to generate a sequence of actions effectively for coordinating subtasks of the target subsystems from the given high-level task command. Basically, the task planning is performed under the framework of STRIPS (Stanford Research Institute Problem Solver) representation and the split planning method. In addition, we applied a state-partitioning technique to the backward split planning method to reduce computational time. By analyzing the obtained graph, the planning system decomposes an original planning problem into several independent sub-problems, and then, the planning system generates a proper sequence of actions. To show the effectiveness of the proposed system, we deal with a scenario of a planning problem in the ISH.

• Journal of Institute of Control, Robotics and Systems
• /
• v.12 no.1
• /
• pp.66-71
• /
• 2006

Recently, there are lots of concerning on ubiquitous environment of robots and URC (Ubiquitous Robotic Companion). In this paper, a practical ubiquitous interface system far controlling mobile robots in indoor environments was proposed. The interface system was designed as a manager-agent model including a PC manager, a mobile manager, and robot agents for being able to be accessed by any network. In the system, the PC manager has a 3D virtual environment and shows real images for a human-friendly interface, and share the computation load of the robot such as path planning and managing geographical information. It also contains Hybrid Format Manager(HFM) working for transforming the image, position, and control data and interchanging them between the robots and the managers. Mobile manager working in the minimized computing condition of handsets has a mobile interface environment displaying the real images and the position of the robot and being able to control the robots by pressing keys. Experimental results showed the proposed system was able to control robots rising wired and wireless LAN and mobile Internet.

• Science of Emotion and Sensibility
• /
• v.24 no.3
• /
• pp.115-124
• /
• 2021

Non-verbal communication is important in human interaction. It provides a layer of information that complements the message being transmitted. This type of information is not limited to human speakers. In human-robot communication, increasing the animacy of the robotic agent-by using non-verbal cues-can aid the expression of abstract concepts such as emotions. Considering the physical limitations of artificial agents, robots can use light and movement to express equivalent emotional feedback. This study analyzes the effects of LED and motion animation of a spherical robot on the emotion being expressed by the robot. A within-subjects experiment was conducted at the University of Tsukuba where participants were asked to rate 28 video samples of a robot interacting with a person. The robot displayed different motions with and without light animations. The results indicated that adding LED animations changes the emotional impression of the robot for valence, arousal, and dominance dimensions. Furthermore, people associated various situations according to the robot's behavior. These stimuli can be used to modulate the intensity of the emotion being expressed and enhance the interaction experience. This paper facilitates the possibility of designing more affective robots in the future, using simple feedback.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.2
• /
• pp.55-72
• /
• 2017

Autonomous Vehicles(AV) are considered as an alternative to solve various social problems. Many researches which are related to developing technologies and AV operations have been conducted vastly and on-going. However, there seem to be little studies on various influences of AI algorithm on driving installed in AV. This study aims to examine the impacts of the ethical decisions made by Utilitarianism-based AI in AV when the oncoming car crossed over the central line. It establishes scenarios about situation of encroaching a central line and analyzes traffic impacts of ethical decision made by AV. According to the results of the analyses, as th accident occurs, overall speed of traffic decrease. There is a negative impact on the traffic flow when AV made an Utilitarian-based ethical decision by changing the lane. However, when AV choose to collide head-on, there is a positive effect to relieve traffic flow with an assistance of CACC, equipped.

• Journal of Information Processing Systems
• /
• v.11 no.3
• /
• pp.370-388
• /
• 2015

The localization of multi-agents, such as people, animals, or robots, is a requirement to accomplish several tasks. Especially in the case of multi-robotic applications, localization is the process for determining the positions of robots and targets in an unknown environment. Many sensors like GPS, lasers, and cameras are utilized in the localization process. However, these sensors produce a large amount of computational resources to process complex algorithms, because the process requires environmental mapping. Currently, combination multi-robots or swarm robots and sensor networks, as mobile sensor nodes have been widely available in indoor and outdoor environments. They allow for a type of efficient global localization that demands a relatively low amount of computational resources and for the independence of specific environmental features. However, the inherent instability in the wireless signal does not allow for it to be directly used for very accurate position estimations and making difficulty associated with conducting the localization processes of swarm robotics system. Furthermore, these swarm systems are usually highly decentralized, which makes it hard to synthesize and access global maps, it can be decrease its flexibility. In this paper, a simple pyramid RAM-based Neural Network architecture is proposed to improve the localization process of mobile sensor nodes in indoor environments. Our approach uses the capabilities of learning and generalization to reduce the effect of incorrect information and increases the accuracy of the agent's position. The results show that by using simple pyramid RAM-base Neural Network approach, produces low computational resources, a fast response for processing every changing in environmental situation and mobile sensor nodes have the ability to finish several tasks especially in localization processes in real time.