Group transport is performed in many natural systems and has become a canonical task for studying cooperation in robotics. We simulate a system of simple, insect-like robots that can move autonomously and grasp object...
详细信息
Group transport is performed in many natural systems and has become a canonical task for studying cooperation in robotics. We simulate a system of simple, insect-like robots that can move autonomously and grasp objects as well as each other. We use artificial evolution to produce solitary transport and group transport behaviors. We show that robots, even though not aware of each other, can be effective in group transport. Group transport can even be performed by robots that behave as in solitary transport. Still, robots engaged in group transport can benefit from behaving differently from robots engaged in solitary transport. The best group transport behaviors yielded by half of the evolutions let robots organize into self-assembled structures. This provides evidence that self-assembly can provide adaptive value to individuals that compete in an artificial evolution based on task performance. We conclude the article by discussing potential implications for evolutionary biology and robotics.
Enactivism claims that sensory-motor activity and embodiment are crucial in perceiving the environment and that machine vision could be a much simpler business it considered in this context. However, computational mod...
详细信息
Enactivism claims that sensory-motor activity and embodiment are crucial in perceiving the environment and that machine vision could be a much simpler business it considered in this context. However, computational models of enactive vision are very rare and often rely on handcrafted control systems. In this article, we argue that the apparent complexity of the environment and of the robot brain can be significantly simplified if perception, behavior, and learning are allowed to co-develop on the same timescale. In doing so, robots become sensitive to, and actively exploit, characteristics of the environment that they can tackle within their own computational and physical constraints. We describe the application of this methodology in three sets of experiments: shape discrimination, car driving, and wheeled robot navigation. A further set of experiments, where the visual system can develop the receptive fields by means of unsupervised Hebbian learning, demonstrates that the receptive fields are consistently and significantly affected by the behavior of the system and differ from those predicted by most computational models of the visual cortex. Finally, we show that our robots can also replicate the performance deficiencies observed in experiments of motor deprivation with kittens.
A new approach to the design of a neural network (NN) based navigator is proposed in which the mobile robot travels to a pre-defined goal position safely and efficiently without any prior map of the environment. This ...
详细信息
A new approach to the design of a neural network (NN) based navigator is proposed in which the mobile robot travels to a pre-defined goal position safely and efficiently without any prior map of the environment. This navigator can be optimized for any user-defined objective function through the use of an evolutionary algorithm. The motivation of this research is to develop an efficient methodology for general goal-directed navigation in generic indoor environments as opposed to learning specialized primitive behaviors in a limited environment. To this end, a modular NN has been employed to achieve the necessary generalization capability across a variety of indoor environments. Herein, each NN module takes charge of navigating in a specialized local environment, which is the result of decomposing the whole path into a sequence of local paths through clustering of all the possible environments. We verify the efficacy of the proposed algorithm over a variety of both simulated and real unstructured indoor environments using our autonomous mobile robot platform.
The interaction of brain, body, and environment can result in complex behavior with rich dynamics, even for relatively simple agents. Such dynamics are, however, often difficult to analyze. In this article, we explore...
详细信息
The interaction of brain, body, and environment can result in complex behavior with rich dynamics, even for relatively simple agents. Such dynamics are, however, often difficult to analyze. In this article, we explore the case of a simple simulated robotic agent, equipped with a reactive neurocontroller and an energy level, which the agent has been evolved to recharge. A dynamical systems analysis shows that a non-neural internal state (energy level), despite its simplicity, dynamically modulates the behavioral attractors of the agent-environment system, such that the robot's behavioral repertoire is continually adapted to its current situation and energy level. What emerges is a dynamic, non-deterministic, and highly self-organized action selection mechanism, originating from the dynamical coupling of four systems (non-neural internal states, neurocontroller, body, and environment) operating at very different timescales.
Recent work in the evolutionary computation field suggests that the implementation of the principles of modularity (functional localization of functions), repetition (multiple use of the same sub-structure) and hierar...
详细信息
Recent work in the evolutionary computation field suggests that the implementation of the principles of modularity (functional localization of functions), repetition (multiple use of the same sub-structure) and hierarchy (recursive composition of sub-structures) could improve the evolvability of complex systems. The generation of neural networks through evolutionary algorithms should in particular benefit from an adapted use of these notions. We have consequently developed modular encoding for neural networks based on attribute grammars (MENNAG), a new encoding designed to generate the structure of neural networks and parameters with evolutionary algorithms, while explicitly enabling these three above-mentioned principles. We expressed this encoding in the formalism of attribute grammars in order to facilitate understanding and future modifications. It has been tested on two preliminary benchmark problems: cart-pole control and robotic arm control, the latter being specifically designed to evaluate the repetition capabilities of an encoding. We compared MENNAG to a direct encoding, ModNet, NEAT, a multilayer perceptron with a fixed structure and to reference controllers. Results show that MENNAG performs better than comparable encodings on both problems, suggesting a promising potential for future applications.
This article extends previous work on evolving learning without synaptic plasticity from discrete tasks to continuous tasks. Continuous-time recurrent neural networks without synaptic plasticity are artificially evolv...
详细信息
This article extends previous work on evolving learning without synaptic plasticity from discrete tasks to continuous tasks. Continuous-time recurrent neural networks without synaptic plasticity are artificially evolved on an associative learning task. The task consists in associating paired stimuli: temperature and food. The temperature to be associated can be either drawn from a discrete set or allowed to range over a continuum of values. We address two questions: Can the learning without synaptic plasticity approach be extended to continuous tasks? And if so, how does learning without synaptic plasticity work in the evolved circuits? Analysis of the most successful circuits to learn discrete stimuli reveal finite state machine (FSM) like internal dynamics. However, when the task is modified to require learning stimuli on the full continuum range, it is not possible to extract a FSM from the internal dynamics. In this case, a continuous state machine is extracted instead.
Continuous-time recurrent neural networks affected by random additive noise are evolved to produce phototactic behaviour in simulated mobile agents. The resulting neurocontrollers are evaluated after evolution against...
详细信息
ISBN:
(纸本)9783540691334
Continuous-time recurrent neural networks affected by random additive noise are evolved to produce phototactic behaviour in simulated mobile agents. The resulting neurocontrollers are evaluated after evolution against perturbations and for different levels of neural noise. Controllers evolved with neural noise are more robust and may still function in the absence of noise. Evidence from behavioural tests indicates that robust controllers do not undergo noise-induced bifurcations or if they do, the transient dynamics remain functional. A general hypothesis is proposed according to which evolution implicitly selects neural systems that operate in noise-resistant landscapes which are hard to bifurcate and/or bifurcate while retaining functionality.
We used an evolutionary robotics methodology to generate pairs of simulated agents capable of reliably establishing and maintaining a coordination pattern under noisy conditions. Unlike previous related work, agents w...
详细信息
ISBN:
(纸本)9783540691334
We used an evolutionary robotics methodology to generate pairs of simulated agents capable of reliably establishing and maintaining a coordination pattern under noisy conditions. Unlike previous related work, agents were only evolved for this ability and not for their capacity to discriminate social contingency (i.e., a live responsive partner) from non-contingent engagements (i.e., a recording). However, when they were made to interact with a recording of their partner made during a successful previous interaction, the coordination pattern could not be established. An analysis of the system's underlying dynamics revealed (i) that stability of the coordination pattern requires ongoing mutuality of interaction, and (ii) that the interaction process is not only constituted by, but also constitutive of, individual behavior. We suggest that this stability of coordination is a general property of a certain class of interactively coupled dynamical systems, and conclude that psychological explanations of an individual's sensitivity to social contingency need to take into account the role of the interaction process.
Co-evolving a robot's sensor morphology and control program increases the potential that it can effectively complete its tasks and provides a means for adapting to changes in the environment. In previous work, we ...
详细信息
ISBN:
(纸本)9781889335384
Co-evolving a robot's sensor morphology and control program increases the potential that it can effectively complete its tasks and provides a means for adapting to changes in the environment. In previous work, we presented a learning system where the angle, range, and type of sensors on a hexapod robot, along with the control program, were evolved. Although three sensor stimuli were detectable by the system, it used only two due to the relative importance of these two stimuli in completing the task. In the research presented in this paper, we used the same system, but reduced the availability of a key stimuli;the most effective solution now required the use of all three stimuli. The learning system still performed well by pacing sensors appropriate for the third stimuli and creating a program that utilized these sensors to successfully solve the problem.
Theory presented by Ashby states that the process of homeostasis is directly related to intelligence and to the ability of an individual in successfully adapting to dynamic environments or disruptions. This paper pres...
详细信息
ISBN:
(纸本)9783540881896
Theory presented by Ashby states that the process of homeostasis is directly related to intelligence and to the ability of an individual in successfully adapting to dynamic environments or disruptions. This paper presents an artificial homeostatic system under evolutionary control, composed of an extended model of the GasNet artificial neural network framework, named NSGasNet, and an artificial endocrine system. Mimicking properties of the neuro-endocrine interaction, the system is shown to be able to properly coordinate the behaviour of a simulated agent that, presents internal dynamics and is devoted to explore the scenario without endangering its essential organization. Moreover, sensorimotor disruptions are applied, impelling the system to adapt in order to maintain some variables within limits, ensuring the agent survival. It is envisaged that the proposed framework is a step towards the design of a generic model for coordinating more complex behaviours, and potentially coping with further severe disruptions.
暂无评论