Richard J. Duro

On the potential contributions of hybrid intelligent approaches to Multicomponent Robotic System development

The area of cognitive or intelligent robotics is moving from the single monolithic robot control and behavior problem to that of controlling robots with multiple components or multiple robots operating together, and even collaborating, in dynamic and unstructured environments. This paper introduces the topic and provides a general overview of the current state of the field of Multicomponent Robotic Systems focusing on providing some insights into where Hybrid Intelligent Systems could provide key contributions to its advancement. Thus, the aim is to identify prospective research areas and to try to delimit the field from the point of view of the following essential problem: how to coordinate multiple robotic elements in order to perform useful tasks.

Multimodule Artificial Neural Network Architectures for Autonomous Robot Control Through Behavior Modulation

In this paper we consider one of the big challenges when constructing modular behavior architectures for the control of real systems, that is, how to decide which module or combination of modules takes control of the actuators in order to implement the behavior the robot must perform when confronted with a perceptual situation. The problem is addressed from the perspective of combinations of ANNs, each implementing a behavior, that interact through the modulation of their outputs. This approach is demonstrated using a three way predator-prey-food problem where the behavior of the individual should change depending on its energetic situation. The behavior architecture is incrementally evolved.

Urban pollution monitoring through opportunistic mobile sensor networks based on public transport

The development of an opportunistic sensor network deployed on regular public transport vehicles with the aim of obtaining a flexible pollution monitoring system over large urban areas is presented. Georeferenced pollution data is acquired by a modular autonomous sensing system placed on vehicles which has been developed and is being currently tested. Short and long range communication systems are used to transmit data from the mobile sources to the central data processing and mapping unit. Within this unit an application to represent the geopositioned pollutant measurements has been implemented based on Google Earth. This provides the user with an interface allowing the study of the evolution of the gas concentrations along a given bus route as well as on the whole urban area.

Towards real-time hyperspectral image processing, a GP-GPU implementation of target identification

In the quest for real time processing of hyperspectral images, this paper presents two artificial intelligence algorithms for target detection specially developed for their implementation over GPU and applied to a search-and-rescue scenario. Both algorithms are based on the application of artificial neural networks to the hyperspectral data. In the first algorithm the neural networks are applied at the level of individual pixels of the image. The second algorithm is a multiresolution based approach to scale invariant target identification using a hierarchical artificial neural network architecture. We have studied the main issues for the efficient implementation of the algorithms in GPU: the exploitation of thousands of threads that are available in this architecture and the adequate use of bandwidth of the device. The tests we have performed show both the effectiveness of detection of the algorithms and the efficiency of the GPU implementation in terms of execution times.

Gaussian synapse ANNs in multi- and hyperspectral image data analysis

A new type of artificial neural network is used to identify different crops and ground elements from hyperspectral remote sensing data sets. These networks incorporate Gaussian synapses and are trained using a specific algorithm called Gaussian synapse back propagation described here. Gaussian synapses present an intrinsic filtering ability that permit concentrating on what is relevant in the spectra and automatically discard what is not. The networks are structurally adapted to the problem complexity as superfluous synapses and/or nodes are implicitly eliminated by the training procedure, thus pruning the network to the required size straight from the training set. The fundamental difference between the present proposal and other ANN topologies using Gaussian functions is that the latter use these functions as activation functions in the nodes, while in our case, they are used as synaptic elements, allowing them to be easily shaped during the training process to produce any type of n-dimensional discriminator. This paper proposes a multi- and hyperspectral image segmenter that results from the parallel and concurrent application of several of these networks providing a probability vector that is processed by a decision module. Depending on the criteria used for the decision module, different perspectives of the same image may be obtained. The resulting structure offers the possibility of resolving mixtures, that is, carrying out a spectral unmixing process in a very straightforward manner.

A comparison of gaussian based ANNs for the classification of multidimensional hyperspectral signals

This paper is concerned with the comparison of three types of Gaussian based Artificial Neural Networks in the very high dimensionality classification problems found in hyperspectral signal processing. In particular, they have been compared for the spectral unmixing problem given the fact that the requirements for this type of classification are very different from other realms in two aspects: there are usually very few training samples leading to networks that are very easily overtrained, and these samples are not usually representative in terms of sampling the whole input-output space. The networks selected for comparison go from the classical Radial Basis Function (RBF) network to the more complex Gaussian Synapse Based Network (GSBN) considering an intermediate type, the Radial Basis Function with Multiple Deviation (RBFMD). The comparisons were carried out when processing a benchmark set of synthetic hyperspectral images containing mixtures of spectra from materials found in the US Geological Service database.

Influence of noise on discrete time backpropagation trained networks

Abstract Noise is a characteristic of real signals that is not often adequately studied when introducing neural networks and training algorithms for signal prediction and reconstruction. In this paper we carry out a study of the effects of training noise, both in the inputs and targets, and test noise on networks with delays in their synapses that are trained with the discrete time backpropagation algorithm. Exhaustive experiments are carried out for networks working under different noise conditions and trained with noise to predict some instants into the future or to reconstruct or generate the signal autonomously once they have learnt it. The results indicate that the main effect of noise is to make the networks learn a simpler signal and thus generalize better in the case of prediction, especially when chaotic signals are considered. This effect is also evidenced for signal reconstruction tasks. We show that the best level of noise for training a network is the level of noise present in the environment in which it will operate, and when this is not known, it is usually better to train with noise than without it unless the level of noise in the environment is almost zero. The article considers the quantitative differences between adding noise to the training inputs and to both the training inputs and training targets, as well as the performance of networks working under different noise conditions.

An integrated system for urban pollution monitoring through a public transportation based opportunistic mobile sensor network

The objective of this paper is to report on new developments in the project we are working on for the development of a mobile sensor based opportunistic urban pollution monitoring network. This work follows from the implementation of a single pollution sensor based sensing node prototype which was used for testing an opportunistic communications network and which was reported elsewhere. Here we concentrate on the extension of the basic sensing system and its modular conversion into a multi pollutant sensing system able to additionally provide temperature, humidity and geo-position information as well as on the software architecture developed around it in order to process the huge amounts of data the system produces. The different prototypes were tested on the public transportation system of the city of Vigo and on multiple test runs around the city of A Coruña in the north-west of Spain producing very promising results.

Induced behavior in a real agent using the multilevel darwinist brain

In this paper we present a strategy for inducing a behavior in a real agent through a learning process with a human teacher. The agent creates internal models extracting information from the consequences of the actions it must carry out, and not just learning the task itself. The mechanism that permits this background learning process is the Multilevel Darwinist Brain, a cognitive mechanism that allows an autonomous agent to decide the actions it must apply in its environment in order to fulfill its motivations. It is a reinforcement based mechanism that uses evolutionary techniques to perform the on line learning of the models.

Complex behaviours through modulation in autonomous robot control

Combining previous experience and knowledge to contemplate tasks of increasing complexity is one of the most interesting problems in autonomous robotics. Here we present an ANN based modular architecture that uses the concept of modulation to increase the possibilities of reusing previously obtained modules. A first approximation to the modulation of the actuators was tested in a previous paper where we showed how it was useful to obtain more complex behaviours that those obtained using only activation / inhibition. In this paper we extend the concept to sensor modulation, which enables the architecture to easily modify the required behaviour for a module, we show how both types of modulation can be used at the same time and how the activation / inhibition can be seen as a particular case of modulation. Some examples in a real robot illustrate the capabilities of the whole architecture.