In the late 1950's Gordon Pask constructed several electrochemical devices having emergent sensory capabilities. These control systems possessed the ability to adaptively construct their own sensors, thereby choos...
详细信息
In the late 1950's Gordon Pask constructed several electrochemical devices having emergent sensory capabilities. These control systems possessed the ability to adaptively construct their own sensors, thereby choosing the relationship between their internal states and the world at large. Devices were built that evolved de novo sensitivity to sound or magnetic fields. Pask's devices have far-reaching implications for artificial intelligence, self-constructing devices, theories of observers and epistemically-autonomous agents, theories of functional emergence, machine creativity, and the limits of contemporary machine learning paradigms.
In this paper an evolutionary algorithm is used for evolving gaits in a walking biped robot controller. The focus is fast learning in a real-time environment. An incremental approach combining a genetic algorithm (GA)...
详细信息
ISBN:
(纸本)9781595931863
In this paper an evolutionary algorithm is used for evolving gaits in a walking biped robot controller. The focus is fast learning in a real-time environment. An incremental approach combining a genetic algorithm (GA) with hill climbing is proposed. This combination interacts in an efficient way to generate precise walking patterns in less than 15 generations. Our proposal is compared to various versions of GA and stochastic search, and finally tested on a pneumatic biped walking robot.
This paper introduces the evolvable functional circle hypothesis. This hypothesis states that if it is assumed that von Uexkull's concept of functional circles exists in robots and that the models used in evolutio...
详细信息
This paper introduces the evolvable functional circle hypothesis. This hypothesis states that if it is assumed that von Uexkull's concept of functional circles exists in robots and that the models used in evolutionary robotics are altered accordingly, then practitioners of evolutionary robotics will benefit in two ways. The first way is that by promoting the evolution of functional circles rather than sensorimotor loops, it allows evolved robots to select their own stimuli and therefore find their own meaning from environmental information. The second way is that it makes it easier for evolved robots to derive multiple meanings from the signal produced by a sensor. The paper goes on to demonstrate a method to alter our models in evolutionary robotics to promote the evolution of functional circles.
In evolutionary robotics role allocation studies, it is common that the role assumed by each robot is strongly associated with specific local conditions, which may compromise scalability and robustness because of the ...
详细信息
ISBN:
(纸本)9783030039288;9783030039271
In evolutionary robotics role allocation studies, it is common that the role assumed by each robot is strongly associated with specific local conditions, which may compromise scalability and robustness because of the dependency on those conditions. To increase scalability, communication has been proposed as a means for robots to exchange signals that represent roles. This idea was successfully applied to evolve communication-based role allocation for a two-role task. However, it was necessary to reward signal differentiation in the fitness function, which is a serious limitation as it does not generalize to tasks where the number of roles is unknown a priori. In this paper, we show that rewarding signal differentiation is not necessary to evolve communication-based role allocation strategies for the given task, and we improve reported scalability, while requiring less a priori knowledge. Our approach puts fewer constrains on the evolutionary process and enhances the potential of evolving communication-based role allocation for more complex tasks.
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.
The purpose of this paper is to present a method of combining neural networks and genetic algorithms to create an efficient control system for a simulated autonomous robot in a 3D environment. The experiments concern ...
详细信息
ISBN:
(纸本)9780889865952
The purpose of this paper is to present a method of combining neural networks and genetic algorithms to create an efficient control system for a simulated autonomous robot in a 3D environment. The experiments concern the emergence of behaviours like obstacle avoidance, tar-et hitting and shortest path finding using a simple yet robust architecture. The evolutionary process takes place inside a dedicated, flexible framework that allows further development and testing.
This paper presents a study investigating the generalization characteristics of two neuro-controllers underpinning decision-making mechanisms in a swarm of robots engaged in a collective perception task. The neuro-con...
详细信息
ISBN:
(纸本)9783031574290;9783031574306
This paper presents a study investigating the generalization characteristics of two neuro-controllers underpinning decision-making mechanisms in a swarm of robots engaged in a collective perception task. The neuro-controllers are both designed-using evolutionary computation-to operate in a randomly distributed cues environment, but under different conditions for what concerns the length of the communication range characterising the robots interactions. For one neuro-controller, the communication range during the design phase is 30 cm, while for the other is 50 cm. The aim of the study is to explore the robustness and the limitations of the two distinct neuro-controllers across a range of different conditions and to establish the optimal bounds on the swarm communication range for this collective perception task. To examine the performance of the two neuro-controllers we conduct a series of post-evaluations in 45 distinct environments, given by nine different distributions of the perceptual cues, and five different communication ranges (i.e., 10, 20, 30, 40, and 50 cm). The results demonstrate that the neuro-controller evolved with a swarm communication range of 30 cm generalizes better and exceeds the performance of the other neuro-controller evolved with 50 cm communication range in a vast majority of the post-evaluation conditions. However, the swarm performance degrades in conditions with patchily distributed perceptual cues and/or very short communication range.
This paper presents a proof of concept demonstration of a novel evolutionary robotic system where robots can self-reproduce. We construct and investigate a strongly embodied evolutionary system, where not only the con...
详细信息
ISBN:
(纸本)9781479944798
This paper presents a proof of concept demonstration of a novel evolutionary robotic system where robots can self-reproduce. We construct and investigate a strongly embodied evolutionary system, where not only the controllers, but also the morphologies undergo evolution in an on-line fashion. Forced by the lack of available hardware we build this system in simulation. However, we use a high quality simulator (Webots) and an existing hardware platform (Roombots) which makes the system, in principle, constructible. Our system can be perceived as an Artificial Life habitat, where robots with evolvable bodies and minds live in an arena and actively induce an evolutionary process 'from within', without a central evolutionary agency or a user-defined synthetic fitness function.
We investigate an evolvable robot system where the body provides proprioceptive sensory signals to the controller (brain) about the positions of the joints. The key aspect we consider is whether all joints should be s...
详细信息
ISBN:
(纸本)9783031700705;9783031700712
We investigate an evolvable robot system where the body provides proprioceptive sensory signals to the controller (brain) about the positions of the joints. The key aspect we consider is whether all joints should be sensed or if sensing fewer joints would be better. We research this matter based on a test suite of twenty-two robots with various shapes and sizes and implement a system where the controller and the sensory signal system evolve together. Experiments with this system show that the evolved solutions use signals only from a fraction of the joints (25-51%) and perform better than the baseline, where all signals are used. This effect was observed across the majority of the test suite.
In this paper, we are interested in ad hoc autonomous agent team composition using cooperative co-evolutionary algorithms (CCEA). In order to accurately capture the individual contribution of team agents, we propose t...
详细信息
ISBN:
(数字)9783031020568
ISBN:
(纸本)9783031020568;9783031020551
In this paper, we are interested in ad hoc autonomous agent team composition using cooperative co-evolutionary algorithms (CCEA). In order to accurately capture the individual contribution of team agents, we propose to limit the number of agents which are updated in-between team evaluations. However, this raises two important problems with respect to (1) the cost of accurately estimating the marginal contribution of agents with respect to the team learning speed and (2) completing tasks where improving team performance requires multiple agents to update their policies in a synchronized manner. We introduce a CCEA algorithm that is capable of learning how to update just the right amount of agents' policies for the task at hand. We use a variation of the El Farol Bar problem, formulated as a multi-robot resource selection problem, to provide an experimental validation of the algorithms proposed.
暂无评论