ISSN:0954-0091    

DOI:10.1080/095400999116223

出版商:Taylor & Francis Group    

年代:1999

数据来源: Taylor

摘要:

This article describes how the SGOCE paradigm has been used within the context of a 'minimal simulation' strategy to evolve neural networks controlling locomotion and obstacle avoidance in a six-legged robot. A standard genetic algorithm has been used to evolve developmental programs according to which recurrent networks of leaky-integrator neurons were grown in a user-provided developmental substrate and were connected to the robot's sensors and actuators. Specific grammars have been used to limit the complexity of the developmental programs and of the corresponding neural controllers. Such controllers were first evolved through simulation and then successfully downloaded on the real robot.

ISSN:0954-0091    

DOI:10.1080/095400999116232

出版商:Taylor & Francis Group    

年代:1999

数据来源: Taylor

摘要:

This paper introduces a hybrid system for modeling, learning and recognition of sequences of 'states' in indoor robot navigation. States are broadly defined as local relevant situations (in the real world) in which the robot happens to be during the navigation. The hybrid is based on parallel recurrent neural networks trained to perform a posteriori state probability estimates of an underlying hidden Markov model (HMM) given a sequence of sensory (e.g. sonar) observations. Discriminative training is accomplished in a supervised manner, using gradient-descent. Recognition is carried out either in a dynamic programming framework, i.e. searching the maximum a posteriori probability of state-posteriors along paths of the HMM, or in real time. The approach is suitable for navigation and for map learning. Experiments of learning and recognition of noisy sequences acquired by a mobile robot equipped with 16 sonars are presented.

ISSN:0954-0091    

DOI:10.1080/095400999116241

出版商:Taylor & Francis Group    

年代:1999

数据来源: Taylor

摘要:

During the last decade, numerous contributions have been made to the use of reinforcement learning in the robot learning field. They have focused mainly on the generalization, memorization and exploration issues-mandatory for dealing with real robots. However, it is our opinion that the most difficult task today is to obtain the definition of the reinforcement function (RF). A first attempt in this direction was made by introducing a method-the update parameters algorithm (UPA)-for tuning a RF in such a way that it would be optimal during the exploration phase. The only requirement is to conform to a particular expression of RF. In this article, we propose Dynamic-UPA, an algorithm able to tune the RF parameters during the whole learning phase (exploration and exploitation). It allows one to undertake the so-called exploration versus exploitation dilemma through careful computation of the RF parameter values by controlling the ratio between positive and negative reinforcement during learning. Experiments with the mobile robot Khepera in tasks of synthesis of obstacle avoidance and wall-following behaviors validate our proposals.

ISSN:0954-0091    

DOI:10.1080/095400999116250

出版商:Taylor & Francis Group    

年代:1999

数据来源: Taylor

摘要:

This paper presents a two-stage neural system to determine the contact points between a three-fingered gripper and an object of arbitrary shape. In the first stage, a CCD camera captures the image of the object and such an image is transformed into a two-dimensional outline through a nearest neighbour algorithm. In the second phase, two neural networks, functioning in cascade, select three contact points in the outline. A competitive Hopfield neural network defines an approximate polygon considering a reduced number of boundary points of the original outline. Then, a supervised neural network, either a multi-layer perceptron or a radial basis function (RBF) network, find the contact points. The experiments suggest that the RBF network trained by the global ridge regression method is suitable for on-line applications and presents the best overall performance in terms of accuracy and robustness to noise. Moreover, this method is able to find correctly the contact points for objects of arbitrary shapes.

ISSN:0954-0091    

DOI:10.1080/095400999116269

出版商:Taylor & Francis Group    

年代:1999

数据来源: Taylor

摘要:

A genetic algorithm is used to search for the rhythmical control of eight joints in a quadruped robot. The search is used to find a fixed number of Fourier coefficients for each joint. Each set of coefficients is considered to be a controller for the robot, and it is evaluated using a simulator of the dynamics of the walking pattern generated by the controller. The fitness of a controller is higher if it generates more stable and faster walking. Effective controllers are further evaluated using a purpose-built robot that is physically modeled in the simulator. We present initial results from this simulation system, and show good correspondence between the simulator-generated dynamics and the movement of the robot under control of the same set of coefficients. The results presented here suggest that stable limit cycles may exist in the dynamics of quadruped walking.

ISSN:0954-0091    

DOI:10.1080/095400999116278

出版商:Taylor & Francis Group    

年代:1999

数据来源: Taylor

摘要:

Existing visually guided walking machines have difficulty traversing terrain cluttered with obstacles. These walking machines use computationally intense approaches that require construction of a geometrically correct model of both the environment and the robot. However, most terrestrial vertebrates accomplish this task easily, suggesting that better strategies exist. We present a model inspired by recent research in cats and humans. In our model, perception and action are tightly coupled. The mapping is adaptive and based on experience. The goal of the adaptation is to use distance measurements to smoothly modulate a central pattern generator (CPG) controlling gait. A key element in our model is the use of a temporal gating hypothesis. This hypothesis simplifies the learning problem and is consistent with biological observations. Our approach does not require that a geometric representation of the environment be created or updated based on new observations. This is in strong contrast to current practice in machine vision and robotics of surface reconstruction as a prerequisite to planning. Our simulation results indicate that the desired mapping can be learned quickly with few mistakes before perfect performance is achieved. The resulting gait modulation is smooth and coordinated with the phase of the CPG controlling the robot.

ISSN:0954-0091    

DOI:10.1080/095400999116287

出版商:Taylor & Francis Group    

年代:1999

数据来源: Taylor

摘要:

The task of providing robust vision for autonomous mobile robots is a complex signal processing problem which cannot be solved using traditional deterministic computing techniques. In this article we investigate four unsupervised neural learning algorithms, known collectively as competitive learning, in order to assess both their theoretical operation and their ability to learn to represent a basic robotic vision task. This task involves the ability of a modest robotic system to identify the components of basic motion and to generalize upon that learned knowledge to classify correctly novel visual experiences. This investigation shows that standard competitive learning and the DeSieno version of frequency-sensitive competitive learning (FSCL) are unsuitable for solving this problem. Soft competitive learning, while capable of producing an appropriate solution, is too computationally expensive in its present form to be used under the constraints of this application. However, the Krishnamurthy version of FSCL is found to be both computationally efficient and capable of reliably learning a suitable solution to the motion identification problem both in simulated tests and in actual hardware-based experiments.

ISSN:0954-0091    

DOI:10.1080/095400999116296

出版商:Taylor & Francis Group    

年代:1999

数据来源: Taylor

摘要:

This paper presents an experiment in collective robotics which investigates the influence of communication, of learning and of the number of robots in a specific task, namely learning the topography of an environment whose features change frequently. We propose a theoretical framework based on probabilistic modeling to describe the system's dynamics. The adaptive multi-robot system and its dynamic environment are modeled through a set of probabilistic equations which give an explicit description of the influence of the different variables of the system on the data-collecting performance of the group. Further, we implement the multi-robot system in experiments with a group of Khepera robots and in simulation using Webots, a three-dimensional simulator of Khepera robots. The robots are controlled by a distributed architecture with an associative-memory type of learning algorithm. Results show that the algorithm allows a group of robots to keep an up-to-date account of the environmental state when this changes regularly. Finally, the results of the simulated and physical experiments are compared with the predictions of the probabilistic model. It is found that the model shows both a good qualitative and a good quantitative correspondence to these results. This suggests that a probabilistic model can be a good first approximation of a multi-robot system.

ISSN:0954-0091    

DOI:10.1080/095400999116304

出版商:Taylor & Francis Group    

年代:1999

数据来源: Taylor