• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.5
• /
• pp.619-627
• /
• 2024

As AI technology advances, interest in performing multi-robot autonomous missions for manned-unmanned teaming (MUM-T) is increasing. In order to develop autonomous mission performance technology for multiple robots, simulation technology that reflects the characteristics of real robots and can flexibly apply various missions is needed. Additionally, in order to solve complex non-linear tasks, an API must be provided to apply multi-robot reinforcement learning technology, which is currently under active research. In this study, we propose the campaign model to flexibly simulate the missions of multiple robots. We then discuss the results of developing a simulation environment that can be edited and run and provides a reinforcement learning API including acceleration performance. The proposed simulated control module and simulated environment were verified using an enemy infiltration scenario, and parallel processing performance for efficient reinforcement learning was confirmed through experiments.

• The Journal of the Korea Contents Association
• /
• v.18 no.7
• /
• pp.536-550
• /
• 2018

This paper examine how acceptance of AI robots can be achieved according to occupational groups when the discourse on human labor and occupation changes due to the new industrial revolution is spreading steadily. Previous research on the acceptance of new technologies and products has predicted use behavior through subjective beliefs and values that do not change well over the short term. Therefore, this study compares the beliefs, values, and use intention of AI robots according to occupation. As a result, the subjective belief factor for AI robots was classified into belief in rationality(reason) and belief in benevolence(emotion). The value factors were divided into acceptance value(role performance, communication, social comparison) and avoidance value(risk, complexity). There was a significant difference in the effect of these on the use intention of AI robot by occupation and employment types. This result suggests that there are gaps in the occupation group at the rate of technology acceptance, as opposed to the existing prediction that AI robots will be rapidly expanded by professionals.

• Journal of Service Research and Studies
• /
• v.13 no.4
• /
• pp.206-223
• /
• 2023

The introduction of Smart technologies such as Artificial Intelligence(AI) systems are have a powerful impact in a variety of industry fields. Some experts predict that smart technology will completely change people's daily life and work styles, causing technological innovation, productivity improvement, and discovery and emergence of new fields. On the one hand, this vision cannot ignore negative views and concerns. Despite many social debates about employment, such as job loss and rising unemployment, there have not been many studies based on employee experience that provide a fundamental solution to the conflict between AI and employment. Therefore, this study finds out the effects and related factors of AI concierge robots for hotel employees, focusing on the hotel industry, and how employees' perceptions of AI concierge robots affect user resistance and turnover intention. This study, conducted a questionnaire survey of 322 hotel employees who had experience working with AI concierge robots in China, and used SPSS and SmartPLS statistical analysis programs to draw conclusions. We found that hotel employees' perceptions of AI concierge robots were significantly related to user resistance and turnover intention, and this association was related to employee self-efficacy, perceived organizational support, quality of AI services and new tasks. In addition, it was found that the quality of AI concierge robots directly or indirectly had the greatest influence on user resistance and turnover intention. The findings of this study provide theoretical implications for academia and practical implications for industry practitioners.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.3
• /
• pp.909-914
• /
• 2024

This study suggests a quantitative evaluation of transfer learning, which is widely used in various AI fields, including image recognition for robot vision. Quantitative and qualitative analyses of results applying transfer learning are presented, but transfer learning itself is not discussed. Therefore, this study proposes a quantitative evaluation of transfer learning itself based on MNIST, a handwritten digit database. For the reference network, the change in recognition accuracy according to the depth of the transfer learning frozen layer and the ratio of transfer learning data and pre-training data is tracked. It is observed that when freezing up to the first layer and the ratio of transfer learning data is more than 3%, the recognition accuracy of more than 90% can be stably maintained. The transfer learning quantitative evaluation method of this study can be used to implement transfer learning optimized according to the network structure and type of data in the future, and will expand the scope of the use of robot vision and image analysis AI in various environments.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.8
• /
• pp.733-739
• /
• 2008

This article proposes algorithms for the automatic initiation of the tracks of maneuvering targets in cluttered environments. These track initiation algorithms consist of IPDA-AI(Integrated Probabilistic Data Association-Amplitude Information) and MPDA(Most Probable Data Association) in an Interacting Multiple Model(IMM) configuration, and they are referred to as the IMM-IPDAF-AI and IMM-MPDA respectively. The IMM portion consists of several filters based on different dynamical models to handle target maneuvers. Each of the filters utilizes an IPDA-AI(or MPDA) algorithm to deal with the problem of track existence in the presence of clutter. Although the primary purpose of this study is to deal with the track initiation problem, the IMM-IPDAF-AI and IMM-MPDA can also be used for the maintenance of existing tracks and the termination of tracks for targets when they disappear. For illustrative purposes, simulation is used to compare the performance of the algorithms proposed to other track formation algorithms.

• 제어로봇시스템학회:학술대회논문집
• /
• 1990.10b
• /
• pp.1240-1245
• /
• 1990

Intelligent Control is an extended paradigm that subsumes both control and AI paradigms, each of which is limited by its own abstractions. Autonomy, as a design goal, offers an arena where both control and AI paradigms must be applied -and a challenge to the viability of both as independent entities. We discuss hierarchical event-based control architectures in which AI and Control paradigms can be integrated within a model-based approach. In a niodel-based system, knowledge is encapsulated in the form of models at the various layers to support the predefined system objectives. Concepts are illustrated with a robotmanaged space-borne chemical laboratory.

• The Journal of the Korea Contents Association
• /
• v.18 no.9
• /
• pp.116-124
• /
• 2018

This study aimed to interpreting the view of current media by artificial intelligence(AI) with the case of a TV show Person of Interest, which was broadcasted until 2016 in US. In this study, we first attempted to find how AI reflects the three laws of robotics, which often appear in Science Fictions. In addition, we paid attention to how the society looks according to the change of the manipulator of the AI, and as a result we derived the distinguishes of the show from other content dealing with robots or AI in terms of narrative. Through this study, we classified the messages in accordance of AI into three categories- importance of data sovereignty, potential of intelligence explosion, and blind faith in high technology. This study suggested that the show emphasizes the consciousness and attitude that should be possessed as a citizen who meets the era of AI prior to raising issue of 'what artificial intelligence is should be developed for our convenience?'

• The Journal of Korea Robotics Society
• /
• v.1 no.2
• /
• pp.203-211
• /
• 2006

In this research, a comprehensive study is performed upon the design of a quadruped walking robot. In advance, the walking posture and skeletal configuration of the vertebrate are analyzed to understand quadrupedal locomotion, and the roles of limbs during walking are investigated. From these, it is known that the forelimbs just play the role of supporting their body and help vault forward, while most of the propulsive force is generated by hind limbs. In addition, with the study of the stances on walking and energy efficiency, design criteria and control method for a quadruped walking robot are derived. The proposed controller, though it is simple, provides a useful framework for controlling a quadruped walking robot. In particular, introduciton of a new rhythmic pattern generator relieves the heavy computational burden because it does not need any computation on kinematics. Finally, the proposed method is validated via dynamic simulations and implementing in a quadruped walking robot, called AiDIN(Artificial Digitigrade for Natural Environment).

• Annual Conference of KIPS
• /
• 2021.11a
• /
• pp.841-844
• /
• 2021

보행 환경 인지 기술은 보행 보조 로봇의 지능화를 위한 핵심 기술 중 하나다. 이 논문은 국내 보행 환경에 대한 보행 보조 로봇의 인지 지능을 고도화하는 방법으로 심층 학습 기반의 의미론적 영상 분할 기법을 고려한다. 이 논문은 국내 보행 환경에 대한 기존 영상 분할 기법의 성능을 비교 분석하고, 국내 보행 환경에 적합한 영상 분할 기술의 개발 방향과 인지 센서의 구성 및 배치에 대해 논한다.

• Annual Conference of KIPS
• /
• 2024.05a
• /
• pp.737-738
• /
• 2024

본 연구는 사용자의 감정을 인식하고, 개인화된 행동을 학습하는 AI 반려동물 시스템을 제안한다. DQN 을 이용한 강화학습을 통해 사용자의 피드백에 따라 행동을 변화시키며, 보다 자연스럽고 흥미로운 상호작용을 가능하게 한다. 이를 통해 기존의 정형화된 로봇 반려동물의 한계를 극복하고 사용자에게 맞춤형 경험을 제공하는 AI 반려동물 개발에 기여하고자 한다.