• Proceedings of the KIEE Conference
• /
• 2001.11c
• /
• pp.428-430
• /
• 2001

다수의 자율이동로봇으로 구성되는 다개체 시스템에서의 협조행동을 위해서 각 개체는 주변환경의 인식뿐만 아니라 환경변화에 적응할 수 있는 추론능력이 요구된다. 이에 본 논문에서는 강화학습을 이용하여 동적으로 변화하는 환경 하에서 개체들이 스스로 학습하고 대처할 수 있는 협조행동 방법을 제시한다. 제안한 방법을 먹이와 포식자 문제에 적용하여 포식자 로봇간의 협조행동을 구현하였다. 여러 대로 구성된 포식자 로봇은 회피가 목적인 먹이로봇을 추적하여 포획하는 것이 임무이며 포식자 로봇들 간의 협조행동을 위해 각 상태에 따른 최적의 행동방식을 찾는데 강화학습을 이용한다.

• Proceedings of the Korean Society of Applied Entomolohy Conference
• /
• 2000.05a
• /
• pp.127-127
• /
• 2000

• Journal of Korea Game Society
• /
• v.13 no.6
• /
• pp.27-34
• /
• 2013

This paper analyzes the behaviour of a prey to avoid the pursuit of a predator at predator-prey relationship to be appeared in the collective behavior of animals. One of the methods to avoid the pursuit of a predator is to rotate quickly when a predator arrives near to it. At that moment, a critical distance and a rotating angular are very important for the prey in order to survive from the pursuit, where the critical distance is the distance between the predator and the prey just before rotation. In order to analyze the critical distance and the rotating angular, this paper introduces the energy for a predator which it has at starting point of the chase and consumes during the chase. Through simulations, we can know that the rotating angle for a prey to survive from the pursuit is increased when the critical distance is shorter and when the ratio of predator's mass and prey's mass is also decreased. The results of simulations are the similar phenomenon in nature and therefore it means that the method to analyze in this paper is correct.

• Korean journal of applied entomology
• /
• v.39 no.2
• /
• pp.59-71
• /
• 2000

The Asian ladybird, Harmonia axyridis, might be distinguished in biological control agents for the several aphid species in the greenhouses as well as in the fields. Therefore, feeding behavior and predacious capability characteristics were observed. When ladybirds are searching for aphids as their preys, they use the maxillary palpus as contact reception. Otherwise, most of aphids escape from walking or chewing ladybird to other place (mainly move to near-by leaf, or fall down to the under-leaf or ground) instead of plant sucking. Consumed time of ladybirds for searching and feeding prey were significantly different and dependent on their development stage. The ladybird adults ate about 120 green peach aphids and 257 cotton aphids per day. The 3rd instar of ladybirds ate 2,420 and 2,750 eggs of greenhouse whitefly on the cucumber and tomato leaf, respectively, as well. However, ladybird instars taken greenhouse whitefly eggs could not continuously develope to adult, on the other hand, ladybirds taken aphids were normal condition.

• Proceedings of the KIEE Conference
• /
• 2000.11d
• /
• pp.809-811
• /
• 2000

협조행동이 요구되는 다수의 자율이동로봇 시스템에서 각 개체는 주변환경의 인식뿐만 아니라 지속적인 환경변화에 적응할 수 있는 고도의 추론능력을 요구하고 있다. 이에 본 논문에서는 강화학습을 이용하여 동적으로 변화하는 환경에서 스스로 학습하여 대처할 수 있는 협조행동 방법을 제시하였다. 강화학습은 동물의 학습방법 연구에서 비롯되었으며, 주어진 목표를 수행하는 과정에서 개체의 행동이 목표를 성취하도록 하였을 때는 그 행동에 보상을 주어 환경의 상태에 따른 최적의 행동방법을 찾아내도록 학습하는 방법이다. 따라서 본 논문에서는 포식자들이 협조행동을 통하여 능동적으로 움직이는 먹이를 잡는 까다로운 문제에 제안한 방법을 적용하여 그 성능을 검증하였다.

• Korean journal of applied entomology
• /
• v.40 no.2
• /
• pp.125-129
• /
• 2001

Some wingless species have evolved take-off behaviors that enable them to become airborne. We examined aerodynamic attributes of dispersal relative to the body size and standing vs. walking postures for three phytoseiids that were suspected to have different take-off behaviors and dispersal abilities, Phytoseiulus persimilis Athias-Henriot, Neoseiulus fallacis (Carman) and N. californicus (McGregor). The average vertical profile of Pp in the walking position was significantly higher than those of Nf and Nc when in walking position. The body height of Nf in the standing posture was significantly greater than the body height of Pp when in the walking position. Cross-section areas also showed similar patterns of difference. Nf in the standing posture would have more than twice the drag force than in walking posture because of more fluid momentum in the wind boundary layer However, Pp in the walking position would have similar drag to Nf in the standing posture because of a higher vertical profile and larger size. Thus we add the scientific evidence of presence and absence of take-off behavior of some phytoseiid mites and evolutionary aspects of aerial dispersal are further discussed.

• Journal of Wetlands Research
• /
• v.20 no.3
• /
• pp.272-280
• /
• 2018

Existing toxicity assessment researches were rarely studied on assessment of the abnormal behavior that affecting survival. Therefore, the study used anti-predator response of amphibians larvae, based on behavioral understanding, to assess toxicity in fullerene nanowhisker(FNW) and fullerene nanowhisker-silver nanoparticle composites(FNW-Ag). The experiment was conducted by dividing the groups not exposed to nanomaterials and exposed to nanomaterials at five concentrations(FNW: $10{\mu}g/ml$, FNW: $100{\mu}g/ml$, FNW: $500{\mu}g/ml$ FNW-Ag: $10{\mu}g/ml$, FNW: $50{\mu}g/ml$). As a result, there were no differences in normal activity except those exposed to concentrations of FNW-Ag $50{\mu}g/ml$, but there were statistically significant differences in anti-predator response except those exposed to concentrations of FNW $10{\mu}g/ml$. That is, exposed of nanomaterials does not affect ordinary movements, but analyses based on behavioral understandings have shown that it has an influence on the anti-predator response. It is therefore considered necessary to have animal behavioral analysis method performed in the assessment of eco-toxic experiment.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2660-2662
• /
• 2001

Q-학습은 최근에 연구되는 강화학습으로서 환경에 대한 정의가 필요 없어 자율이동로봇의 행동학습에 적합한 방법이다. 그러나 다개체 시스템의 학습처럼 환경이 복잡해짐에 따라 개체의 입출력 변수는 늘어나게 되고 Q함수의 계산량은 기하급수적으로 증가하게 된다. 따라서 이러한 문제를 해결하기 위해 다개체 시스템의 Q-학습에 적합한 연속적인 Q-학습 알고리즘을 제안하였다. 연속적인 Q-학습 알고리즘은 개체가 가질 수 있는 모든 상태-행동 쌍을 하나의 Q함수에 표현하는 방법으로서 계산량 및 복잡성을 줄임으로써 동적으로 변하는 환경에 능동적으로 대처하도록 하였다. 제안한 연속적인 Q-학습 알고리즘을 벽으로 막힌 공간에서 두 포식자와 한 먹이로 구성되는 먹이-포식자 문제에 적용하여 먹이개체의 효율적인 회피능력을 검증하였다.

• Proceedings of the Zoological Society Korea Conference
• /
• 2000.10a
• /
• pp.121.3-122
• /
• 2000

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.9
• /
• pp.27-35
• /
• 2021

Artificial life is used in various fields of applied science by evaluating natural life-related systems, their processes, and evolution. Research has been actively conducted to evolve physical body design and behavioral control strategies for the dynamic activities of these artificial life forms. However, since co-evolution of shapes and neural networks is difficult, artificial life with optimized movements has only one movement in one form and most do not consider the environmental conditions around it. In this paper, artificial life that co-evolve bodies and neural networks using predator-prey models have environmental adaptive movements. The predator-prey hierarchy is then extended to the top-level predator, medium predator, prey three stages to determine the stability of the simulation according to initial population density and correlate between body evolution and population dynamics.