Renan C. Moioli

Artificial homeostatic system: a novel approach

Many researchers are developing frameworks inspired by natural, especially biological, systems to solve complex real-world problems. This work extends previous work in the field of biologically inspired computing, proposing an artificial endocrine system for autonomous robot navigation. Having intrinsic self-organizing behaviour, the novel artificial endocrine system can be applied to a wide range of problems, particularly those that involve decision making under changing environmental conditions, such as autonomous robot navigation. This work draws on “embodied cognitive science”, including the study of intelligence, adaptivity, homeostasis, and the dynamic aspects of cognition, in order to help lay down fundamental principles and techniques for a novel approach to more biologically plausible artificial homeostatic systems. Results from using the artificial endocrine system to control a simulated robot are presented.

Towards the evolution of an artificial homeostatic system

This paper presents an artificial homeostatic system (AHS) devoted to the autonomous navigation of mobile robots, with emphasis on neuro-endocrine interactions. The AHS is composed of two modules, each one associated with a particular reactive task and both implemented using an extended version of the GasNet neural model, denoted spatially unconstrained GasNet model or simply non-spatial GasNet (NSGasNet). There is a coordination system, which is responsible for the specific role of each NSGasNet at a given operational condition. The switching among the NSGasNets is implemented as an artificial endocrine system (AES), which is based on a system of coupled nonlinear difference equations. The NSGasNets are synthesized by means of an evolutionary algorithm. The obtained neuro-endocrine controller is adopted in simulated and real benchmark applications, and the additional flexibility provided by the use of NSGasNet, together with the existence of an automatic coordination system, guides to convincing levels of performance.

Exploring the Kuramoto model of coupled oscillators in minimally cognitive evolutionary robotics tasks

This work is the first attempt to investigate the neural dynamics of a simulated robotic agent engaged in minimally cognitive tasks by employing evolved instances of the Kuramoto model of coupled oscillators as its nervous system. The main objectives are to shed new light into the role of neuronal synchronisation and phase towards the generation of cognitive behaviours and to initiate an investigation on the efficacy of such systems as practical robot controllers. The first experiment is an active categorical perception task in which the robot has to discriminate between moving circles and squares. In the second task, the robotic agent has to approach moving circles with both normal and inverted vision thus adapting to both scenarios. These tasks were chosen for being considered as benchmarks in the evolutionary robotics and adaptive behaviour communities. The results obtained indicate the feasibility of the framework in the analysis and generation of embodied cognitive behaviours.

Homeostasis and evolution together dealing with novelties and managing disruptions

Purpose ? The purpose of this paper is to present an artificial homeostatic system whose parameters are defined by means of an evolutionary process. The objective is to design a more biologically plausible system inspired by homeostatic regulations observed in nature, which is capable of exploring key issues in the context of robot behaviour adaptation and coordination. Design/methodology/approach ? The proposed system consists of an artificial endocrine system that coordinates two spatially unconstrained GasNet artificial neural network models, called non-spatial GasNets. Both systems are dedicated to the definition of control actions in autonomous navigation tasks via the use of an artificial hormone and a hormone receptor. A series of experiments are performed in a real and simulated scenario in order to investigate the performance of the system and its robustness to novel environmental conditions and internal sensory disruptions. Findings ? The designed system shows to be robust enough to self-adapt to a wider variety of disruptions and novel environments by making full use of its in-built homeostatic mechanisms. The system is also successfully tested on a real robot, indicating the viability of the proposed method for coping with the reality gap, a well-known issue for the evolutionary robotics community. Originality/value ? The proposed framework is inspired by the homeostatic regulations and gaseous neuro-modulation that are intrinsic to the human body. The incorporation of an artificial hormone receptor stands for the novelty of this paper. This hormone receptor proves to be vital to control the networks response to the signalling promoted by the presence of the artificial hormone. It is envisaged that the proposed framework is a step forward in the design of a generic model for coordinating many and more complex behaviours in simulated and real robots, employing multiple hormones and potentially coping with further severe disruptions.

A multiple hormone approach to the homeostatic control of conflicting behaviours in an autonomous mobile robot

This work proposes a biologically inspired system for the coordination of multiple and possible conflicting behaviours in an autonomous mobile robot, devoted to explore novel scenarios while ensuring its internal variables dynamics. The proposed Evolutionary Artificial Homeostatic System, derived from the study of how an organism would self-regulate in order to keep its essential variables within a limited range (homeostasis), is composed of an artificial endocrine system, including two hormones and two hormone receptors, and also three previously evolved NSGasNet artificial neural networks. It is shown that the integration of receptors enhance the system robustness without incorporating to the three evolved NSGasNets more a priori knowledge. The experiments conducted also show that the proposed multi-hormone evolutionary artificial homeostatic system is able to successfully coordinate a multiple and conflicting behaviours task, being also robust enough to cope with internal and external disruptions.

Evolving an Artificial Homeostatic System

Theory presented by Ashby states that the process of homeostasis is directly related to intelligence and to the ability of an individual in successfully adapting to dynamic environments or disruptions. This paper presents an artificial homeostatic system under evolutionary control, composed of an extended model of the GasNet artificial neural network framework, named NSGasNet, and an artificial endocrine system. Mimicking properties of the neuro-endocrine interaction, the system is shown to be able to properly coordinate the behaviour of a simulated agent that presents internal dynamics and is devoted to explore the scenario without endangering its essential organization. Moreover, sensorimotor disruptions are applied, impelling the system to adapt in order to maintain some variables within limits, ensuring the agent survival. It is envisaged that the proposed framework is a step towards the design of a generic model for coordinating more complex behaviours, and potentially coping with further severe disruptions.

Synchronisation effects on the behavioural performance and information dynamics of a simulated minimally cognitive robotic agent

Oscillatory activity is ubiquitous in nervous systems, with solid evidence that synchronisation mechanisms underpin cognitive processes. Nevertheless, its informational content and relationship with behaviour are still to be fully understood. In addition, cognitive systems cannot be properly appreciated without taking into account brain–body– environment interactions. In this paper, we developed a model based on the Kuramoto Model of coupled phase oscillators to explore the role of neural synchronisation in the performance of a simulated robotic agent in two different minimally cognitive tasks. We show that there is a statistically significant difference in performance and evolvability depending on the synchronisation regime of the network. In both tasks, a combination of information flow and dynamical analyses show that networks with a definite, but not too strong, propensity for synchronisation are more able to reconfigure, to organise themselves functionally and to adapt to different behavioural conditions. The results highlight the asymmetry of information flow and its behavioural correspondence. Importantly, it also shows that neural synchronisation dynamics, when suitably flexible and reconfigurable, can generate minimally cognitive embodied behaviour.

Analysing Learning Classifier Systems in Reactive and Non-reactive Robotic Tasks

There are few contributions to robot autonomous navigation applying Learning Classifier Systems (LCS) to date. The primary objective of this work is to analyse the performance of the strength-based LCS and the accuracy-based LCS, named EXtended Learning Classifier System (XCS), when applied to two distinct robotic tasks. The first task is purely reactive, which means that the action to be performed can rely only on the current status of the sensors. The second one is non-reactive, which means that the robot might use some kind of memory to be able to deal with aliasing states. This work presents a rule evolution analysis, giving examples of evolved populations and their peculiarities for both systems. A review of LCS derivatives in robotics is provided together with a discussion of the main findings and an outline of future investigations.

Neuronal assembly dynamics in supervised and unsupervised learning scenarios

The dynamic formation of groups of neurons—neuronal assemblies—is believed to mediate cognitive phenomena at many levels, but their detailed operation and mechanisms of interaction are still to be uncovered. One hypothesis suggests that synchronized oscillations underpin their formation and functioning, with a focus on the temporal structure of neuronal signals. In this context, we investigate neuronal assembly dynamics in two complementary scenarios: the first, a supervised spike pattern classification task, in which noisy variations of a collection of spikes have to be correctly labeled; the second, an unsupervised, minimally cognitive evolutionary robotics tasks, in which an evolved agent has to cope with multiple, possibly conflicting, objectives. In both cases, the more traditional dynamical analysis of the systems variables is paired with information-theoretic techniques in order to get a broader picture of the ongoing interactions with and within the network. The neural network model is inspired by the Kuramoto model of coupled phase oscillators and allows one to fine-tune the network synchronization dynamics and assembly configuration. The experiments explore the computational power, redundancy, and generalization capability of neuronal circuits, demonstrating that performance depends nonlinearly on the number of assemblies and neurons in the network and showing that the framework can be exploited to generate minimally cognitive behaviors, with dynamic assembly formation accounting for varying degrees of stimuli modulation of the sensorimotor interactions.

The dynamics of a neural network of coupled phase oscillators with synaptic plasticity controlling a minimally cognitive agent

This work explores the neuronal synchronisation and phase information dynamics of an enhanced version of the widely used Kuramoto model of phase interacting oscillators. The framework is applied to a simulated robotic agent engaged in a minimally cognitive benchmark task. The outcomes of this research contribute not only to uncover the role of neuronal synchronisation and phase information in the generation of cognitive behaviours but also to the understanding of oscillatory properties in neural networks.