Through series of experiments this work compares effects of different types of genetic algorithms on evolution of a neural network that is used to control a robot. Genetic algorithms using binary and real coded indivi...
详细信息
Through series of experiments this work compares effects of different types of genetic algorithms on evolution of a neural network that is used to control a robot. Genetic algorithms using binary and real coded individuals, algorithms using basic and advanced mutations and crossovers and algorithms using fixed and variable population size are compared on three tasks of evoltionary robotics. The goal is to determine wether usage of advanced genetic algorithms leads to faster convergence or to better solution than usage of basic genetic algorithm. Experiments are performed in an easily extendable simulator developed for purposes of this work.
Constructing musculoskeletal models of extinct vertebrates requires subjective assumptions about soft tissue parameters rarely preserved in the fossil record. Despite these necessary assumptions about fundamental inpu...
详细信息
Constructing musculoskeletal models of extinct vertebrates requires subjective assumptions about soft tissue parameters rarely preserved in the fossil record. Despite these necessary assumptions about fundamental input values, paleobiologists rarely perform objective tests of best-estimate models before reaching conclusions based on predicted results. The extent to which lack of knowledge on soft tissue anatomy limits the accuracy of running speed estimates of extinct dinosaurs is therefore poorly understood. In this study, a sensitivity analysis is performed on an evolutionary robotics model of the non-avian theropod dinosaur Allosaurus, used previously to estimate maximum running speed in this extinct animal. A range of muscle parameters were varied over the range observed in extant vertebrates, whereas mass-related parameters were altered across the range of published estimates for Allosaurus. Muscle parameters have a linear relationship with maximum running speed, whereas surprisingly total body mass and torso center of mass have little effect. Muscle force values produced the greatest range in predicted running speeds (4.5-10.7 m/s) and stride lengths (4-5.8 m) in the sensitivity analysis, equating to 65.9% and 30.7% variation about the original 'best-estimate' prediction, a relatively high potential margin of error. These results highlight the importance of sensitivity analyses in biomechanical modeling of extinct taxa, particularly where values for soft tissues parameters are not tightly constrained. The current range in plausible values for soft tissue properties makes a robust quantitative assessment of behavioral ecology and species interactions in dinosaurian communities extremely difficult.
Active perception refers to a theoretical approach to the study of perception grounded on the idea that perceiving is a way of acting, rather than a process whereby the brain constructs an internal representation of t...
详细信息
Active perception refers to a theoretical approach to the study of perception grounded on the idea that perceiving is a way of acting, rather than a process whereby the brain constructs an internal representation of the world. The operational principles of active perception can be effectively tested by building robot-based models in which the relationship between perceptual categories and the body-environment interactions can be experimentally manipulated. In this paper, we study the mechanisms of tactile perception in a task in which a neuro-controlled anthropomorphic robotic arm, equipped with coarse-grained tactile sensors, is required to perceptually categorize spherical and ellipsoid objects. We show that best individuals, synthesized by artificial evolution techniques, develop a close to optimal ability to discriminate the shape of the objects as well as an ability to generalize their skill in new circumstances. The results show that the agents solve the categorization task in an effective and robust way by self-selecting the required information through action and by integrating experienced sensory-motor states over time.
This paper presents a software system that integrates different computational paradigms to solve cognitive tasks of different levels. The system has been employed to empower research on very different platforms rangin...
详细信息
This paper presents a software system that integrates different computational paradigms to solve cognitive tasks of different levels. The system has been employed to empower research on very different platforms ranging from simple two-wheeled structures with only a few cheap sensors, to complex two-legged humanoid robots, with many actuators, degrees of freedom and sensors. It is flexible and adjustable enough to be used in part or as a whole, to target different research domains projects and questions, including evolutionary robotics, RoboCup and Artificial Language Evolution on Autonomous Robots (ALEAR, an EU funded cognitive systems project). In contrast to many other frameworks, the system is such that researchers can quickly adjust the system to different problems and platforms, while allowing maximum reuse of components and abstractions, separation of concerns and extensibility. (C) 2009 Elsevier Ltd. All rights reserved.
A comparison of behavior-based and planning approaches of robot control is presented in this paper. We focus on miniature mobile robotic agents with limited sensory abilities. Two reactive control mechanisms for an ag...
详细信息
A comparison of behavior-based and planning approaches of robot control is presented in this paper. We focus on miniature mobile robotic agents with limited sensory abilities. Two reactive control mechanisms for an agent are considered a radial basis function neural network trained by evolutionary algorithm and a traditional reinforcement learning algorithm over a finite agent state space. The control architecture based on localization and planning is compared to the former method. (C) 2010 Elsevier Ltd. All rights reserved.
The gallop is the preferred high-speed gait for dynamic locomotion in most cursorial mammals. Due to the lack of good analytical models and proven control strategies, however, the gallop remains an elusive goal in the...
详细信息
The gallop is the preferred high-speed gait for dynamic locomotion in most cursorial mammals. Due to the lack of good analytical models and proven control strategies, however, the gallop remains an elusive goal in the field of legged robotics. While there have been several attempts at creating a gallop, none have captured all of the important dynamic characteristics of the gait. In this work, we present a practical approach for producing a stable 3D gallop in a quadrupedal model which includes these characteristics. The dynamic model utilizes biologically-based assumptions including articulated legs with nonzero mass, compliance at the knee joints, and a body with an asymmetric mass distribution. Furthermore, the resulting 3D gallop contains the prominent features found in the biological gait: early leg retraction, phase-locked leg motion creating an asymmetric footfall pattern, a significant gathered flight phase, unconstrained spatial dynamics, and a smooth gait. To obtain these results, we employ a multiobjective genetic algorithm with a carefully designed vector fitness function to search for various control parameters. Furthermore, we partition the search space in roughly orthogonal subspaces to find parameters for each sub-controller. A critical component of the controller is an energy control law that ensures a fixed amount of energy in the knee springs during each stride. A characterization of the resulting gait is presented, which highlights biological properties and the visual realism of the solution.
This paper continues efforts to establish a mutually informative dialogue between psychology and evolutionary robotics in order to investigate the dynamics of social interaction. We replicate a recent simulation model...
详细信息
This paper continues efforts to establish a mutually informative dialogue between psychology and evolutionary robotics in order to investigate the dynamics of social interaction. We replicate a recent simulation model of a minimalist experiment in perceptual crossing and confirm the results with significantly simpler artificial agents. A series of psycho-physical tests of their behaviour informs a hypothetical circuit model of their internal operation. However, a detailed study of the actual internal dynamics reveals this circuit model to be unfounded, thereby offering a tale of caution for those hypothesising about sub-personal processes in terms of behavioural observations. In particular, it is shown that the behaviour of the agents largely emerges out of the interaction process itself rather than being an individual achievement alone. We also extend the original simulation model in two novel directions in order to test further the extent to which perceptual crossing between agents can self-organise in a robust manner. These modelling results suggest new hypotheses that can become the basis for further psychological experiments.
In mobile robotics, a solid test for adaptation is the ability of a control system to function not only in a diverse number of physical environments, but also on a number of different robotic platforms. This paper dem...
详细信息
In mobile robotics, a solid test for adaptation is the ability of a control system to function not only in a diverse number of physical environments, but also on a number of different robotic platforms. This paper demonstrates that a set of behaviours evolved in simulation on a miniature robot (epuck) can be transferred to a much larger-scale platform (Pioneer), both in simulation and in the real world. The chosen architecture uses artificial evolution of epuck behaviours to obtain a genetic sequence, which is then employed to seed an idiotypic, artificial immune system (AIS) on the Pioneers. Despite numerous hardware and software differences between the platforms, navigation and target-finding experiments show that the evolved behaviours transfer very well to the larger robot when the idiotypic AIS technique is used. In contrast, transferability is poor when reinforcement learning alone is used, which validates the adaptability of the chosen architecture.
This article rigorously characterizes the structure of the entire fitness space of a simple neuromechanical system consisting of a model leg in closed-loop interaction with a neural controller. Using tools from the th...
详细信息
This article rigorously characterizes the structure of the entire fitness space of a simple neuromechanical system consisting of a model leg in closed-loop interaction with a neural controller. Using tools from the theory of piecewise-smooth dynamical systems, we derive expressions for the location and layout of the region of high-fitness solutions in parameter space, and we show how both the boundary and the internal structure of this region arise from specific neural, mechanical, and neuromechanical properties of the walking system. In addition, we characterize the structure of the map from neural parameters to gaits to fitness.
Embodied artificial intelligence argues that the body and brain play equally important roles in the generation of adaptive behavior. An increasingly common approach therefore is to evolve an agent's morphology alo...
详细信息
Embodied artificial intelligence argues that the body and brain play equally important roles in the generation of adaptive behavior. An increasingly common approach therefore is to evolve an agent's morphology along with its control in the hope that evolution will find a good coupled system. In order for embodied artificial intelligence to gain credibility within the robotics and cognitive science communities, however, it is necessary to amass evidence not only for how to co-optimize morphology and control of adaptive machines, but why. This work provides two new lines of evidence for why this co- optimization is useful: Here we show that for an object manipulation task in which a simulated robot must accomplish one, two, or three objectives simultaneously, subjugating more aspects of the robot's morphology to selective pressure allows for the evolution of better robots as the number of objectives increases. In addition, for robots that successfully evolved to accomplish all of their objectives, those composed of evolved rather than fixed morphologies generalized better to previously unseen environmental conditions.
暂无评论