• The Journal of Korea Robotics Society
• /
• v.18 no.2
• /
• pp.143-154
• /
• 2023

In this study, a fast motion planning method for the swing motion of a 6x6 wheel-legged robot to traverse large obstacles and gaps is proposed. The motion planning method presented in the previous paper, which was based on trajectory optimization, took up to tens of seconds and was limited to two-dimensional, structured vertical obstacles and trenches. A deep neural network based on one-dimensional Convolutional Neural Network (CNN) is introduced to generate keyframes, which are then used to represent smooth reference commands for the six leg angles along the robot's path. The network is initially trained using the behavioral cloning method with a dataset gathered from previous simulation results of the trajectory optimization. Its performance is then improved through reinforcement learning, using a one-step REINFORCE algorithm. The trained model has increased the speed of motion planning by up to 820 times and improved the success rates of obstacle crossing under harsh conditions, such as low friction and high roughness.

• Journal of Christian Education in Korea
• /
• v.73
• /
• pp.7-19
• /
• 2023

In education, the educere aspect makes itself felt - moving from an original situation to something higher, something better. Moreover, the formative character of educare can be recognised in the German concept Bildung, which focuses on human beings in their wholeness, on their attitude within society and their worldview. What shape has been given in the Netherlands to these different aspects of education over the centuries? Without creating the impression that a linear development in thinking about - and acting in - education has taken place throughout history, and without the ambition to be comprehensive, we look at what took place between adults and children in previous centuries in the Netherlands. Will our investigation yield historical constants or differences? We let ourselves be surprised.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.261-263
• /
• 2022

The National Program for Excellence in SW is underway to innovate the software education system and cultivate software professionals with creative convergence thinking in response to the demand for software manpower. This program was started by selecting 8 universities in 2015, and in September 2022, 44 universities are participating. The Wonkwang University's National Program for Excellence in SW, which was selected for this project in 2018, adopted the SW competency certification system to strengthen SW competency and many students actively participated. In this paper, the SW competency certification system program was examined, and lecture evaluation in related subjects and the performance of the certification system were analyzed in detail. Through the analysis results, the performance of the SW competency certification system was identified.

• 한국벤처창업학회:학술대회논문집
• /
• 2022.11a
• /
• pp.175-180
• /
• 2022

최근 몇 년간 COVID19로 인한 팬데믹 상황과 전세계적으로 유례없는 인플레이션을 겪으면서 각종 산업 분야의 경기 불황으로 어려움을 겪고 있다. 미용 산업 분야도 예외가 아니다. 그 중에서도 특히 피부미용 업종은 실물 경기의 영향에 민감하게 반응하는 서비스산업 분야다. 고객을 직접 만나야만 이루어지는 피부미용업은 COVID19가 가져온 비대면 사회화 과정에 대책없이 충격을 받은 산업 분야라고 볼 수 있다. 불황 속에서도 산업이 성장하려면 지속적인 성장 강화 교육과 제도적 차원이 지원이 필요하다. 피부미용업 분야로 진출하는 여성의 대부분 생계를 위한 목적을 가지고 있지만 실제로 성공한 사례들은 보면 내재된 기업가 정신들을 함유하고 있을 것으로 보고 이에 대한 분석과 긍정심리자본 요소가 창업 성과를 높이고 지속할 수 있는지 알아보고 부족하다면 구성원들의 학습역량을 높이기 위한 다양한 노력이 필요하다. 따라서 본 연구에서는 피부미용업 창업자에게 기업가 정신이 미치는 영향을 파악해보고 긍정심리자본 요소가 창업성과에 미치는 영향이 어느 정도 되는지 파악하는데 목적을 두고 있다. 연구대상의 피부미용업에 종사하는 창업자들로 기업가정신이 기업가정신이 긍정심리자본을 조절변수로 두었을 때 창업 성과에 영향을 미칠 것이라는 인과적 경로를 검증하고 이를 통한 피부미용업의 창업자들에게 창업과 성장을 위해서 필요한 교육이나 준비사항을 제안하고자 한다.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.149-154
• /
• 2023

본고는 한국어 생성 모델의 독성 텍스트 저항 능력을 검증하기 위해 'CVALUE' 데이터셋에서 추출한 고난도 독성 질문-대답 100쌍을 바탕으로 한국어 생성 모델을 위한 '100 K-Poison' 데이터셋을 시범적으로 구축했다. 이 데이터셋을 토대로 4가지 대표적인 한국어 생성 모델 'ZeroShot TextClassifcation'과 'Text Generation7 실험을 진행함으로써 현재 한국어 생성 모델의 독성 텍스트 식별 및 응답 능력을 종합적으로 고찰했고, 모델 간의 독성 텍스트 저항력 격차 현상을 분석했으며, 앞으로 한국어 생성 모델의 독성 텍스트 식별 및 웅대 성능을 한층 더 강화하기 위한 '이독공독(以毒攻毒)' 학습 전략을 새로 제안하였다.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.945-946
• /
• 2023

4차 산업혁명과 코로나19 영향으로 개발자 수요가 급증하며, 노코드 및 로우코드 플랫폼과 자연어 처리 기반 인공지능이 주목받고 있다. 본 연구는 프로그래밍 접근성 향상을 위한 노코드 플랫폼을 탐구하며, 사용자가 UI를 통해 직관적으로 프로젝트를 구축할 수 있는 설계 방식을 제시한다. 본 연구에서는 웹 크롤링과 자연어 처리 모델 학습에 기반한 아키텍처와 방향성을 제시한다. 사용자는 화면을 구성하고 프레임워크 선택 후 프로젝트를 간단하게 구축할 수 있다. 이 연구는 전문 지식 없이도 소프트웨어 개발에 쉽게 접근할 수 있는 방법론을 제시하며, 접근성과 포용성 강화에 기여한다.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.281-282
• /
• 2023

자율주행 자동차 시장 규모 및 기술이 급속도로 성장하고 있음에도 불구하고, 전문가 교육을 위한 높은 하드웨어 비용 때문에 실제로 이 기술을 실험하기 위한 집단 교육 플랫폼의 필요성이 높아졌다. 이에 따라 우리는 자율주행에 사용되는 센서와 액츄에이터, 그리고 자율주행 알고리즘 학습을 위한 1/5 크기의 하드웨어를 포함한 교육 플랫폼을 설계했다. 이 교육 프로그램은 온라인 강의와 실습으로 구성되며, 각각의 모듈은 로봇 운영체제(ROS)를 활용한 C언어로 개발되었다. 이 교육 플랫폼은 언제 어디서나 접근 가능한 온라인 형식으로 제공되므로, 학생들은 이론과 실습을 통해 자율주행 분야의 전문가로 성장할 수 있는 기회를 얻게 되고 혁신과 경쟁력 강화에 기여할 것으로 기대된다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.6
• /
• pp.1033-1042
• /
• 2023

This paper proposes a network intrusion detection system that identifies abnormal flows within the network. The majority of datasets commonly used in research lack time-series information, making it challenging to improve detection rates for attacks with fewer instances due to a scarcity of sample data. However, there is insufficient research regarding detection approaches. In this study, we build upon previous research by using the Artificial neural network(ANN) model and a stack ensemble technique in our approach. To address the aforementioned issues, we incorporate temporal information by leveraging adjacent flows and enhance the learning of samples from sparse attacks, thereby improving both the overall detection rate and the detection rate for sparse attacks.

• The Journal of Korea Robotics Society
• /
• v.19 no.1
• /
• pp.117-129
• /
• 2024

This paper introduces collective navigation through a narrow gap using a curriculum-based deep reinforcement learning algorithm for a swarm of unmanned aerial vehicles (UAVs). Collective navigation in complex environments is essential for various applications such as search and rescue, environment monitoring and military tasks operations. Conventional methods, which are easily interpretable from an engineering perspective, divide the navigation tasks into mapping, planning, and control; however, they struggle with increased latency and unmodeled environmental factors. Recently, learning-based methods have addressed these problems by employing the end-to-end framework with neural networks. Nonetheless, most existing learning-based approaches face challenges in complex scenarios particularly for navigating through a narrow gap or when a leader or informed UAV is unavailable. Our approach uses the information of a certain number of nearest neighboring UAVs and incorporates a task-specific curriculum to reduce learning time and train a robust model. The effectiveness of the proposed algorithm is verified through an ablation study and quantitative metrics. Simulation results demonstrate that our approach outperforms existing methods.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.3
• /
• pp.131-139
• /
• 2024

Crew Transfer Vessels (CTVs) are primarily used for the maintenance of offshore wind farms. Despite being manually operated by professional captains and crew, collisions with other ships and marine structures still occur. To prevent this, the introduction of autonomous navigation systems to CTVs is necessary. In this study, research on the obstacle avoidance system of the autonomous navigation system for CTVs was conducted. In particular, research on obstacle avoidance simulation for CTVs using deep reinforcement learning was carried out, taking into account the currents and wind loads in offshore wind farms. For this purpose, 3 degrees of freedom ship maneuvering modeling for CTVs considering the currents and wind loads in offshore wind farms was performed, and a simulation environment for offshore wind farms was implemented to train and test the deep reinforcement learning agent. Specifically, this study conducted research on obstacle avoidance maneuvers using MATD3 within deep reinforcement learning, and as a result, it was confirmed that the model, which underwent training over 10,000 episodes, could successfully avoid both static and moving obstacles. This confirms the conclusion that the application of the methods proposed in this study can successfully facilitate obstacle avoidance for autonomous navigation CTVs within offshore wind farms.