• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.38 no.4
• /
• pp.352-362
• /
• 2010

The simultaneous operation of multiple UAV's makes it possible to enhance the mission accomplishment efficiency. In order to achieve this, easily scalable control algorithms are required, and swarm intelligence having such characteristics as flexibility, robustness, decentralized control, and self-organization based on behavioral model comes into the spotlight as a practical substitute. Recently, evolutionary robotics is applied to the control of UAV's to overcome the weakness of difficulties in the logical design of behavioral rules. In this paper, a neural network controller evolved by evolutionary robotics is applied to the control of multiple UAV's which have the mission of searching limited area. Several numerical demonstrations show the proposed algorithm has superior results to those of behavior based neural network controller which is designed by intuition.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.11a
• /
• pp.129-130
• /
• 2009

산불 진화작업은 초기진화의 중요성과 동시에 종단에는 마지막 잔불정리까지 소방서에서 담당하게 되며 특히나 잔불정리 작업은 반드시 지상인력이 하여야 한다. 그러나 마지막 작업이라 하여 소홀히 하게 된다면 더 큰 피해를 일으킬 수 있다. 이러한 중요성에도 불구하고 많은 인력, 시간, 비용 소모로 인해 빠른 대처를 하지 못하는 상황이다. 본 논문은 더 큰 피해로 이어 질 수 있는 잔불을 로봇을 통하여 진화하는 잔불 진화 로봇 시스템을 제안한다. 또한, 제안된 시스템을 통해 잔불 진화의 실패로 인한 대형 산불 재해를 막기 위한 시간, 인력 및 비용의 절감을 가져 올 것이며, 더욱이 예외 상황에서의 인명피해 방지효과를 예상한다.

• ICROS
• /
• v.22 no.3
• /
• pp.43-57
• /
• 2016

미래 농업은 생산, 유통, 소비 등의 모든 시스템이 연결되고 여기에 ICT 로봇 나노(NT) 바이오(BT)의 첨단기술을 결합해 자율적으로 운영되는 신성장동력 산업으로 진화될 것으로 예상된다. 이에 따라 농업은 정밀농업기술, 자동화 및 농업용 스마트 로봇 등의 다양한 공학기술의 접목과 함께 발달되고 있다. 최근에는 농업에 적용이 어려울 것이라고 예상되던 마이크로 나노 바이오공학의 접목도 시도되고 있으며 이에 따른 미래 농업의 전망은 아주 밝다고 볼 수 있다. 본 논문에서는 미래 농업을 위한 바이오시스템공학에 대해 자동화, 로봇화, 마이크로 나노농업공학 및 농업생명가공공학을 중점으로 주요기술들을 설명하고 국내 외 연구개발 동향을 살펴보고자 한다.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.4 no.2
• /
• pp.90-96
• /
• 2009

In the original model-based paradigm in the field of motion planning of robots, robots had to play the focal role of considering all situations under which they made decisions and operate. Such paradigm makes it difficult to respond efficiently to the dynamically shifting environment such as disaster area. In order to handle such a situation that may be changed dynamically, a technology that allows a dynamic execution of data transmission and physical/network connection between multiple robots based on scenarios is required. In this paper, we deal with evolutionary robots that adapt to any given environment and execute scenarios, specially focused on the development of a simulator to test the evolutionary process of cooperated multiple robots.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.37 no.3
• /
• pp.27-38
• /
• 2000

This paper proposes how the recurrent neural network controller for a Khepera mobile robot with an obstacle avoiding ability can be determined by co-adaptation of the evolution and learning, The proposed co-adaptation scheme consists of two folds： a population of NN controllers are evolved by the genetic algorithm so that the degree of obstacle avoidance might be reduced through the global searching and each NN controller is trained by CRBP learning so that the running behavior is adapted to its outer environment through the local searching. Experimental results shows that the NN controller coadapted by evolution and learning outperforms its non-learning equivalent evolved by only genetic algorithm in both the ability of obstacle avoidance and the convergence speed reaching to the required running behavior.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.6
• /
• pp.587-593
• /
• 2017

In this paper, we propose a method to solve the difficulties in constructing an environment capable of practical training on the theoretical contents of robot control field. We make a two-wheeled mobile robot with Segway structure using LEGO block. In order to demonstrate the validity of using the developed robot as a practical application of advanced control theory of robotics education such as dynamic system and nonlinear system, the robot takes a stable posture while balancing the change of gravity during running. The results of the experiment are shown. By presenting the results, the robots made using the LEGO block are used for practical training of advanced control theory of robotics. It can be used as a tool.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.12
• /
• pp.595-602
• /
• 2021

The robot is developing into a software-oriented shape that recognizes the surrounding situation and is given a task. Cloud Robotics Platform is a method to support Service Oriented Architecture shape for robots, and it is a cloud-based method to provide necessary tasks and motion controllers depending on the situation. As it evolves into a humanoid robot, the robot will be used to help humans in generalized daily life according to the three robot principles. Therefore, in addition to robots for specific individuals, robots as public goods that can help all humans depending on the situation will be universal. Therefore, the importance of information security in the Cloud Robotics Computing environment is analyzed to be composed of people, robots, service applications on the cloud that give intelligence to robots, and a cloud bridge that connects robots and clouds. It will become an indispensable element for In this paper, we propose a Security Scheme that can provide security for communication between people, robots, cloud bridges, and cloud systems in the Cloud Robotics Computing environment for intelligent robots, enabling robot services that are safe from hacking and protect personal information.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.5
• /
• pp.610-616
• /
• 2004

In the research of biomechanical engineering, robotics and neurophysiology, to clarify the mechanism of human bipedal walking is of major interest. It serves as a basis of developing several applications such as rehabilitation tools and humanoid robots. Nevertheless, because of complexity of the neuronal system that interacts with the body dynamics system to make walking movements, much is left unknown about the details of locomotion mechanism. Researchers were looking for the optimal model of the neuronal system by trials and errors. In this paper, we applied Genetic Programming to induce the model of the nervous system automatically and showed its effectiveness by simulating a human bipedal walking with the obtained model.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.12
• /
• pp.10-19
• /
• 1999

Cellular Automata Neural Systems(CANS) are neural networks based on biological development and evolution. Each neuron of CANS has local connection and acts as a form of pulse according to the dynamics of the chaotic neuron. CANS are generated from initial cells according to the CA rule. In the previous study, to obtain the useful ability of CANS, we make the pattern of initial cells evolve. However, it is impossible to represent all solution space, so we propose an evolving method of CA rule to overcome this defect in this paper. DNA coding has the redundancy and overlapping of gene and is apt for the representation of the rule. In this paper, we show the general expression of CA rule and propose translation method from DNA code to CA rule. The effectiveness of the proposed scheme was verified by applying it to the navigation problem of autonomous mobile robot.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.1
• /
• pp.29-37
• /
• 1999

In general, the information processing capability of a neural network is determined by its architecture and efficient training patterns. However, there is no systematic method for designing neural network and selecting effective training patterns. Evolutionary Algorithms(EAs) are referred to as the methods of population-based optimization. Therefore, EAs are considered as very efficient methods of optimal system design because they can provide much opportunity for obtaining the global optimal solution. In this paper, we propose a new method for finding the optimal structure of neural networks based on competitive co-evolution, which has two different populations. Each population is called the primary population and the secondary population respectively. The former is composed of the architecture of neural network and the latter is composed of training patterns. These two populations co-evolve competitively each other, that is, the training patterns will evolve to become more difficult for learning of neural networks and the architecture of neural networks will evolve to learn this patterns. This method prevents the system from the limitation of the performance by random design of neural networks and inadequate selection of training patterns. In co-evolutionary method, it is difficult to monitor the progress of co-evolution because the fitness of individuals varies dynamically. So, we also introduce the measurement method. The validity and effectiveness of the proposed method are inspected by applying it to the visual servoing of robot manipulators.