Bruno Lara

Robot Control and the Evolution of Modular Neurodynamics

Summary A modular approach to neural behavior control of autonomous robots is presented. It is based on the assumption that complex internal dynamics of recurrent neural networks can efficiently solve complex behavior tasks. For the development of appropriate neural control structures an evolutionary algorithm is introduced, which is able to generate neuromodules with specific functional properties, as well as the connectivity structure for a modular synthesis of such modules. This so called ENS 3 -algorithm does not use genetic coding. It is primarily designed to develop size and connectivity structure of neuro-controllers. But at the same time it optimizes also parameters of individual networks like synaptic weights and bias terms. For demonstration, evolved networks for the control of miniature Khepera robots are presented. The aim is to develop robust controllers in the sense that neuro-controllers evolved in a simulator show comparably good behavior when loaded to a real robot acting in a physical environment. Discussed examples of such controllers generate obstacle avoidance and phototropic behaviors in non-trivial environments.

Parameter Estimation of Some Epidemic Models. The Case of Recurrent Epidemics Caused by Respiratory Syncytial Virus

The research presented in this paper addresses the problem of fitting a mathematical model to epidemic data. We propose an implementation of the Landweber iteration to solve locally the arising parameter estimation problem. The epidemic models considered consist of suitable systems of ordinary differential equations. The results presented suggest that the inverse problem approach is a reliable method to solve the fitting problem. The predictive capabilities of this approach are demonstrated by comparing simulations based on estimation of parameters against real data sets for the case of recurrent epidemics caused by the respiratory syncytial virus in children.

Automated failure classification for assembly with self-tapping threaded fastenings using artificial neural networks

This paper presents a new strategy for the automated monitoring and classification of self-tapping threaded fastenings, based on artificial neural networks. Threaded fastenings represent one of the most common assembly methods making the automation of this task highly desirable. It has been shown that the torque versus insertion depth signature signals measured on-line can be used for monitoring threaded insertions. However, the research to date provides only a binary successful/unsuccessful type of classification. In practice when a fault occurs it is useful to know the causes leading to it. Extending earlier work by the authors, a radial basis neural network is used to classify insertion signals, differentiating successful insertions from failed insertions and categorizing different types of insertion failures. The neural network is first tested using a computer simulation study based on a mathematical model of the process. The network is then validated using experimental torque signature signals obtained from an electric screwdriver equipped with an optical shaft encoder and a rotary torque sensor. Test results are presented proving that this novel approach allows failure detection and classification in a reliable and robust way. The key advantages of the proposed method, when compared to existing methods, are improved and automated set-up procedures and its generalization capabilities in the presence of noise and component discrepancies due to tolerances.

Internal simulations for behaviour selection and recognition

In this paper, we present internal simulations as a methodology for human behaviour recognition and understanding. The internal simulations consist of pairs of inverse forward models representing sensorimotor actions. The main advantage of this method is that it both serves for action selection and prediction as well as recognition. We present several human-robot interaction experiments where the robot can recognize the behaviour of the human reaching for objects.

Automated robot-based screw insertion system

This paper introduces an automated robot-based system for the insertion of self-tapping screws into unthreaded holes. The system consists of three main components: a manipulator-guided screwdriver, a camera and a system which controls and monitors the overall process. The focus of this paper is on the key stages of the insertion procedure: (a) detection of the insertion location by means of a camera, (b) positioning of the electrical screwdriver employing a manipulator, and (c) appropriately monitored insertion of a screw. Experiments were carried out in order to identify the requirements needed for a fully automated insertion system. Results are presented.

Exploration Behaviors, Body Representations, and Simulation Processes for the Development of Cognition in Artificial Agents

Sensorimotor control and learning are fundamental prerequisites for cognitive development in humans and animals. Evidence from behavioural sciences and neuroscience suggests that motor and brain development are strongly intertwined with the experiential process of \textit{exploration}, where internal body representations are formed and maintained over time. In order to guide our movements, our brain must hold an internal model of our body and constantly monitor its configuration state. How can sensorimotor control using such low-level body representations enable the development of more complex cognitive and motor capabilities? Although a clear answer has still not been found for this question, several studies suggest that processes of mental simulation of action-perception loops are likely to be executed in our brain and are dependent on internal body representations. Therefore, the capability to re-enact sensorimotor experience might represent a key mechanism behind the implementation of higher cognitive capabilities, such as behaviour recognition, arbitration and imitation, sense of agency and self-other distinction. Addressed mainly to researchers on autonomous motor and mental development in artificial agents, this work aims at gathering the latest development in the study on exploration behaviours, on internal body representations, on internal models, and on mechanisms for internal sensorimotor simulations. Relevant studies in human and animal sciences are discussed and a parallel to similar investigations in robotics is presented.

Coupled inverse-forward models for action execution leading to tool-use in a humanoid robot

We propose a computational model based on inverse-forward model pairs for the simulation and execution of actions. The models are implemented on a humanoid robot and are used to control reaching actions with the arms. In the experimental setup a tool has been attached to the left arm of the robot extending its covered action space. The preliminary investigations carried out aim at studying how the use of tools modifies the body scheme of the robot. The system performs action simulations before the actual executions. For each of the arms, predicted end-effector positions are compared with the desired one and the internal pair presenting the lowest error is selected for action execution. This allows the robot to decide on performing an action either with its hand alone or with the one with the attached tool.

Robot Positioning Using Camera-Space Manipulation With a Linear Camera Model

This paper presents a new version of the camera-space-manipulation method (CSM). The set of nonlinear view parameters of the classic CSM is replaced with a linear model. Simulations and experiments show a similar precision error for the two methods. However, the new approach is simpler to implement and is faster.

Evolving Brain Structures for Robot Control

To study the relevance of recurrent neural network structures for the behavior of autonomous agents a series of experiments with miniature robots is performed. A special evolutionary algorithm is used to generate netw orks of different sizes and architectures. Solutions for obstacle a voidance and phototropic behavior are presented. Netw orks are evolved with the help of simulated robots, and the results are validated with the use of physical robots.

Anticipation by multi-modal association through an artificial mental imagery process

Mental imagery has become a central issue in research laboratories seeking to emulate basic cognitive abilities in artificial agents. In this work, we propose a computational model to produce an anticipatory behaviour by means of a multi-modal off-line hebbian association. Unlike the current state of the art, we propose to apply hebbian learning during an internal sensorimotor simulation, emulating a process of mental imagery. We associate visual and tactile stimuli re-enacted by a long-term predictive simulation chain motivated by covert actions. As a result, we obtain a neural network which provides a robot with a mechanism to produce a visually conditioned obstacle avoidance behaviour. We developed our system in a physical Pioneer 3-DX robot and realised two experiments. In the first experiment we test our model on one individual navigating in two different mazes. In the second experiment we assess the robustness of the model by testing in a single environment five individuals trained under different conditions. We believe that our work offers an underpinning mechanism in cognitive robotics for the study of motor control strategies based on internal simulations. These strategies can be seen analogous to the mental imagery process known in humans, opening thus interesting pathways to the construction of upper-level grounded cognitive abilities.