This paper explores current developments in evolutionary and bio-inspired approaches to autonomous robotics, concentrating on research from our group at the University of Sussex. These developments ...are discussed in the context of advances in the wider fields of adaptive and evolutionary approaches to AI and robotics, focusing on the exploitation of embodied dynamics to create behaviour. Four case studies highlight various aspects of such exploitation. The first exploits the dynamical properties of a physical electronic substrate, demonstrating for the first time how component-level analog electronic circuits can be evolved directly in hardware to act as robot controllers. The second develops novel, effective and highly parsimonious navigation methods inspired by the way insects exploit the embodied dynamics of innate behaviours. Combining biological experiments with robotic modeling, it is shown how rapid route learning can be achieved with the aid of navigation-specific visual information that is provided and exploited by the innate behaviours. The third study focuses on the exploitation of neuromechanical chaos in the generation of robust motor behaviours. It is demonstrated how chaotic dynamics can be exploited to power a goal-driven search for desired motor behaviours in embodied systems using a particular control architecture based around neural oscillators. The dynamics are shown to be chaotic at all levels in the system, from the neural to the embodied mechanical. The final study explores the exploitation of the dynamics of brain-body-environment interactions for efficient, agile flapping winged flight. It is shown how a multi-objective evolutionary algorithm can be used to evolved dynamical neural controllers for a simulated flapping wing robot with feathered wings. Results demonstrate robust, stable, agile flight is achieved in the face of random wind gusts by exploiting complex asymmetric dynamics partly enabled by continually changing wing and tail morphologies.
We propose a biologically plausible architecture for unsupervised ensemble learning in a population of spiking neural network classifiers. A mixture of experts type organisation is shown to be ...effective, with the individual classifier outputs combined via a gating network whose operation is driven by input timing dependent plasticity (ITDP). The ITDP gating mechanism is based on recent experimental findings. An abstract, analytically tractable model of the ITDP driven ensemble architecture is derived from a logical model based on the probabilities of neural firing events. A detailed analysis of this model provides insights that allow it to be extended into a full, biologically plausible, computational implementation of the architecture which is demonstrated on a visual classification task. The extended model makes use of a style of spiking network, first introduced as a model of cortical microcircuits, that is capable of Bayesian inference, effectively performing expectation maximization. The unsupervised ensemble learning mechanism, based around such spiking expectation maximization (SEM) networks whose combined outputs are mediated by ITDP, is shown to perform the visual classification task well and to generalize to unseen data. The combined ensemble performance is significantly better than that of the individual classifiers, validating the ensemble architecture and learning mechanisms. The properties of the full model are analysed in the light of extensive experiments with the classification task, including an investigation into the influence of different input feature selection schemes and a comparison with a hierarchical STDP based ensemble architecture.
We present a general and fully dynamic neural system, which exploits intrinsic chaotic dynamics, for the real-time goal-directed exploration and learning of the possible locomotion patterns of an ...articulated robot of an arbitrary morphology in an unknown environment. The controller is modeled as a network of neural oscillators that are initially coupled only through physical embodiment, and goal-directed exploration of coordinated motor patterns is achieved by chaotic search using adaptive bifurcation. The phase space of the indirectly coupled neural-body-environment system contains multiple transient or permanent self-organized dynamics, each of which is a candidate for a locomotion behavior. The adaptive bifurcation enables the system orbit to wander through various phase-coordinated states, using its intrinsic chaotic dynamics as a driving force, and stabilizes on to one of the states matching the given goal criteria. In order to improve the sustainability of useful transient patterns, sensory homeostasis has been introduced, which results in an increased diversity of motor outputs, thus achieving multiscale exploration. A rhythmic pattern discovered by this process is memorized and sustained by changing the wiring between initially disconnected oscillators using an adaptive synchronization method. Our results show that the novel neurorobotic system is able to create and learn multiple locomotion behaviors for a wide range of body configurations and physical environments and can readapt in realtime after sustaining damage.
Modern technology offers many ways to enhance teaching and learning that in turn promote the development of tools for educational activities both inside and outside the classroom. Many educational ...programs using the augmented reality (AR) technology are being widely used to provide supplementary learning materials for students.
This paper describes the potential and challenges of using GeoGebra AR in mathematical studies, whereby students can view 3D geometric objects for a better understanding of their structure, and verifies the feasibility of its use based on experimental results. The GeoGebra software can be used to draw geometric objects, and 3D geometric objects can be viewed using AR software or AR applications on mobile phones or computer tablets. These could provide some of the required materials for mathematical education at high schools or universities. The use of the GeoGebra application for education in Laos will be particularly discussed in this paper.
In this short article, we present a detailed analysis of the dynamics of a system of two coupled Fitzhugh–Nagumo neuron equations with tonic descending command signals, suitable for modelling ...circuits underlying the generation of motor behaviours. We conduct a search of possible attractors and calculate dynamical quantities, such as the largest Lyapunov exponents (LLEs), at a fine resolution over the areas of parameter space where complex and chaotic dynamics are most likely, to build a more detailed picture of the dynamical regimes of the system, focusing on the most complex solutions. By building a precise LLE map, we identify a narrow region of parameter space of particular interest, rich with chaotic and multistable dynamics, and show that it is on the border of criticality. This allows us to draw conclusions about possible neural mechanisms underlying the generation of chaotic dynamics. We illustrate the detailed ecology of multiple attractors in the system by listing, characterising and grouping all the stable attractors in the parameter range of interest. This allows us to pinpoint the regions with complex multistability. The greater understanding thus provided is intended to help future studies on the roles of chaotic dynamics in biological motor control, and their application in robotics, particularly by giving a deeper insight into how input signals and control parameters shape the system’s dynamics which can be exploited in chaos-driven adaptation.
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. 인공생명체 연구는 자연 생명과 관련된 시스템이나 그 과정들, 진화 등을 평가해 다양한 응용과학 분야에 활용된다. 이러한 인공생명체의 원활한 활동을 위해 물리적 신체 설계와 행동 제어전략을 진화시키는 연구가 활발히 진행되었다. 그러나 형태와 신경망을 공진화시키는 것은 어렵기에 최적화된 움직임을 가진 인공생명체는 한 가지 형태에 한 가지 움직임만을 가지며 주변 환경 상황은 고려하지 않는 것이 대부분이다. 본 논문에서는 포식자-피식자 모델을 이용하여 형태와 신경망을 공진화하는 인공생명체가 환경적응형 움직임을 갖게 한다. 그런 다음 포식자-피식자 계층 구조를 최상위 포식자-중간 포식자-최하위 피식자 3단계로 확장하여 초기 개체군 밀도에 따라 시뮬레이션의 안정성을 판별하며 형태 진화와 개체군 역학 간의 상관관계를 분석한다.
•Present a modified particle-based branching method for automatically generating a shrubbery pattern that conforms to the input surface curvature that is applied directly to the 3D input mesh without ...requiring any basic tree element from existing sources.•Branching patterns can be controlled by the user’s brush on a partial area of input mesh, where the branch shapes reflects the brush trajectory.•Controllability for both global and local tree-branch shape by providing a set of parameters for particle-based growth algorithm.
Display omitted
We propose a new method to automatically generate a shrub-branch-style shell (also called a hollow-branch sculpture) decorative pattern for an arbitrary 3D model along its surface curvature. Our method generates the branching pattern by using a particle-based model without requiring any basic tree-shape elements to be extracted from existing 2D images or 3D models. We modify the particle method by constraining the direction vectors for particle motion onto a given mesh surface so the branch structure grows along the surface to form a shell of the input object. The global and local branch shapes are changed by adjusting the growth space and growth factors, providing better controllability and diversity of the resulting patterns. In addition, the growth space for the branching pattern can be interactively assigned by a user’s brush to an arbitrary area of the mesh surface where the trajectory of the brush stroke is reflected in the branch-growth directions. The following control options are also considered: merging multiple branch clusters having different root locations, biasing the generation of strong main branches, and creating a windowed growth space for thin shapes. The versatility and effectiveness of our approach are demonstrated by generating various arborsculpture-inspired shapes.
Modern technology offers many ways to enhance teaching and learning that in turn promote the development of tools for educational activities both inside and outside the classroom. Many educational ...programs using the augmented reality (AR) technology are being widely used to provide supplementary learning materials for students. This paper describes the potential and challenges of using GeoGebra AR in mathematical studies, whereby students can view 3D geometric objects for a better understanding of their structure, and verifies the feasibility of its use based on experimental results. The GeoGebra software can be used to draw geometric objects, and 3D geometric objects can be viewed using AR software or AR applications on mobile phones or computer tablets. These could provide some of the required materials for mathematical education at high schools or universities. The use of the GeoGebra application for education in Laos will be particularly discussed in this paper. Keywords: GeoGebra, Geometry, Mathematic, Learning Media, Augmented Reality
We present an efficient packet transmission strategy for massively multiplayer online first-person shooter (MMOFPS) games using movement-adaptive packet transmission interval. The player motion in ...FPS games shows a wide spectrum of movement variability both in speed and orientation, where there is room for reducing the number of packets to be transmitted to the server depending on the predictability of the character's movement. In this work, the degree of variability (nonlinearity) of the player movements is measured at every packet transmission to calculate the next transmission time, which implements the adaptive transmission frequency according to the amount of movement change. Server-side prediction with a few auxiliary heuristics is performed in concert with the incoming packets to ensure reliability for synchronizing the connected clients. The comparison of our method with the previous fixed-interval transmission scheme is presented by demonstrating them using a test game environment. 본 논문은 클라이언트-서버 방식을 사용하는 대규모 1인칭 온라인 슈터 게임(MMOFPS)에서의 네트워크 부하를 줄이기 위한 효율적인 적응적 패킷전송 주기 방법을 제안한다. 플레이어 움직임에 있어서 빠르고 지속적인 변화와 정적이고 선형적인 상태가 다양하게 공존하는 FPS 게임의 특성상 변화의 정도에 따라 서버로의 패킷 전송량을 절약할 수 있는 지점들이 존재하는데, 이를 위해 본 논문에서는 클라이언트가 매 패킷을 전송할 때마다 플레이어의 위치 및 움직임 변수들의 변화량을 측정하여 이를 기반으로 다음번 패킷이 전송되어야 할 시간 간격을 계산한다. 서버 측에서는 받은 패킷의 정보들을 사용하여 다음 패킷이 도착할 때까지의 공백을 메우기 위해 위치 예측을 수행하여 모든 클라이언트에게 브로드캐스팅을 하게 된다. 긴 패킷 전송 간격으로 인한 예측 오차를 줄이기 위하여 전송 간격 최대한계치와 이중 패킷전송 등의 추가적 작업을 수행한다. 결과의 효율성을 보이기 위해 테스트 게임 환경을 구축하여 기존의 고정된 패킷전송 주기 시스템과의 비교분석을 수행하였다.
PDF
