In this article, the concept of a cellular robot that is capable of reconfiguring itself is reviewed. This "self-reconfigurable (SR) robot" exemplifies a new trend in robotics, indeed, we can now build vario...
详细信息
In this article, the concept of a cellular robot that is capable of reconfiguring itself is reviewed. This "self-reconfigurable (SR) robot" exemplifies a new trend in robotics, indeed, we can now build various kinds of SR robots with off-the-shelf technologies of processors, actuators, and sensors. These SR robots, based on modern mechatronics, are still not as adaptable as the liquid metal robot in The Terminator 2 but are just as flexible as any conventional robots
Robots operating in everyday life environments are often required to switch between different tasks. While learning and evolution have been effectively applied to single task performance, multiple task performance sti...
详细信息
Robots operating in everyday life environments are often required to switch between different tasks. While learning and evolution have been effectively applied to single task performance, multiple task performance still lacks methods that have been demonstrated to be both reliable and efficient. This paper introduces a new method for multiple task performance based on multiobjective evolutionary algorithms, where each task is considered as a separate objective function. In order to verify the effectiveness, the proposed method is applied to evolve neural controllers for the Cyber Rodent (CR) robot that has to switch properly between two distinctly different tasks: 1) protecting another moving robot by following it closely and 2) collecting objects scattered in the environment. Furthermore, the tasks and neural complexity are analyzed by including the neural structure as a separate objective function. The simulation and experimental results using the CR robot show that the multiobjective-based evolutionary method can be applied effectively for generating neural networks that enable the robot-to perform multiple tasks simultaneously.
A preference is not located anywhere in the agent's cognitive architecture, but it is rather a constraining of behavior which is in turn shaped by behavior. Based on this idea, a minimal model of behavioral prefer...
详细信息
A preference is not located anywhere in the agent's cognitive architecture, but it is rather a constraining of behavior which is in turn shaped by behavior. Based on this idea, a minimal model of behavioral preference is proposed. A simulated mobile agent is modeled with a plastic neurocontroller, which holds two separate high dimensional homeostatic boxes in the space of neural dynamics. An evolutionary algorithm is used for creating a link between the boxes and the performance of two different phototactic behaviors. After evolution, the agent's performance exhibits some important aspects of behavioral preferences such as durability and transitions. This article demonstrates (1) the logical consistency of the multi-causal view by producing a case study of its viability and providing insights into its dynamical basis and (2) how durability and transitions arise through the mutual constraining of internal and external dynamics in the flow of alternating high and low susceptibility to environmental variations. Implications for modeling autonomy are discussed.
In this article, we evolve and analyze continuous-time recurrent neural networks capable of associating the smells of different foods with edibility or inedibility in different environments. First, we present an in-de...
详细信息
In this article, we evolve and analyze continuous-time recurrent neural networks capable of associating the smells of different foods with edibility or inedibility in different environments. First, we present an in-depth analysis of this task, highlighting the evolutionary challenges it poses and how these challenges informed our experimental design. Next, we describe the evolution of nonplastic neural circuits that can solve this food edibility learning problem. We then show that the dynamics of the best evolved nonplastic circuits instantiate finite state machines that capture the combinatorial structure of this task. Finally, we demonstrate that successful circuits with Hebbian synaptic plasticity can also be evolved, but that such circuits do not utilize their synaptic plasticity in a traditional way.
Intrinsically Motivated Reinforcement Learning (IMRL) has been proposed as a framework within which agents exploit "internal reinforcement" to acquire general-purpose building-block behaviors ("skills&q...
详细信息
ISBN:
(纸本)9781424411153
Intrinsically Motivated Reinforcement Learning (IMRL) has been proposed as a framework within which agents exploit "internal reinforcement" to acquire general-purpose building-block behaviors ("skills") which can be later combined for solving several specific tasks. The architectures so far proposed within this framework are limited in that: (1) they use hardwired "salient events" to form and train skills, and this limits agents' autonomy;(2) they are applicable only to problems with abstract states and actions, as grid-world problems. This paper proposes solutions to these problems in the form of a hierarchical reinforcement-learning architecture that: (1) exploits evolutionary robotics techniques so to allow the system to autonomously discover "salient events";(2) uses neural networks so to allow the system to cope with continuous states and noisy environments. The viability of the proposed approach is demonstrated with a simulated robotic scenario.
In previous work [8] a computational framework was demonstrated that allows a mobile robot to autonomously evolve models its own body for the purposes of adaptive behavior generation or recovery from damage. Conceivab...
详细信息
ISBN:
(纸本)9781595936974
In previous work [8] a computational framework was demonstrated that allows a mobile robot to autonomously evolve models its own body for the purposes of adaptive behavior generation or recovery from damage. Conceivably, robots working in tandem could share their experiences such that one robot, when faced with a situation already encountered by another robot, could draw on that experience and adapt more rapidly. A first demonstration of this is given here: multiple robots with the same or similar body plan, but acting independently, combine self-models such that they accelerate modeling. Two approaches are investigated: the robots feed their experiences back into a common modeling engine, or they maintain their own modeling engine but share their best self-models with each other. It was found that the latter approach achieves a, significant improvement in modeling compared to a single robot and compared to the former approach. This finding has implications for how to design autonomous robots acting in concert to achieve large-scale tasks.
This paper presents an elitist evolving strategy, which allows obtaining a controller, based on a neural network capable of commanding an autonomous robot. In order to reduce the detrimental crossover effect, we propo...
详细信息
ISBN:
(纸本)9789537138097
This paper presents an elitist evolving strategy, which allows obtaining a controller, based on a neural network capable of commanding an autonomous robot. In order to reduce the detrimental crossover effect, we propose to use a strategy to create several children for each parent pair, selecting properly the way of making the replacement. The results obtained show that, though the number of children is high, the quantity of fitness tests carried out is actually lower than that of a conventional evolving algorithm. In this way, we propose an alternative that reduces the computational cost of the process, reaching at a suitable response for the problem resolution.
Real organisms live in a world full of uncertain situations and have evolved cognitive mechanisms to cope with problems based on actions and perceptions which are not always reliable. One aspect could be related with ...
详细信息
ISBN:
(纸本)9783540749127
Real organisms live in a world full of uncertain situations and have evolved cognitive mechanisms to cope with problems based on actions and perceptions which are not always reliable. One aspect could be related with the following questions: could neural uncertainty be beneficial from an evolutionary robotics perspective? Is uncertainty a possible mechanism for obtaining more robust artificial systems? Using the minimal cognition approach, we show that moderate levels of uncertainty in the dynamics of continuous-time recurrent networks correlates positively with behavioral robustness of the system. This correlation is possible through internal neural changes depending on the uncertainty level. We also find that controllers evolved with moderate neural uncertainty remain robust to disruptions even when uncertainty is removed during tests, suggesting that uncertainty helps evolution find regions of higher robustness in parameter space.
Several different controller representations are compared oil a non-trivial problem in simulated car racing, with respect to learning speed and final Fitness. The controller representations are based either on Neural ...
详细信息
ISBN:
(纸本)9781595936974
Several different controller representations are compared oil a non-trivial problem in simulated car racing, with respect to learning speed and final Fitness. The controller representations are based either on Neural Networks or Genetic Programming, and also differ in regards to whether they allow for stateful controllers or just reactive ones. Evolved GP trees are analysed, and attempts are made at explaining the performance differences observed.
Biologically inspired designs can improve the design of artificial agents. In this paper we explain and explore the role of directional light sensors from an evolutionary robotics perspective using a dynamical systems...
详细信息
ISBN:
(纸本)9781595936974
Biologically inspired designs can improve the design of artificial agents. In this paper we explain and explore the role of directional light sensors from an evolutionary robotics perspective using a dynamical systems approach. It was found that by using directionally specific sensors in the agent, there was a simplification of the neural controller employed. This simplification helped not only with the analysis of this type of controller but also improved the behavioural performance of the agents, thereby showing a good example of the ecological balance principle.
暂无评论