A Cloud-based Robot System for Long-term Interaction: Principles, Implementation, Lessons Learned

Making the transition to long-term interaction with social-robot systems has been identified as one of the main challenges in human-robot interaction. This article identifies four design principles to address this challenge and applies them in a real-world implementation: cloud-based robot control, a modular design, one common knowledge base for all applications, and hybrid artificial intelligence for decision making and reasoning. The control architecture for this robot includes a common Knowledge-base (ontologies), Data-base, “Hybrid Artificial Brain” (dialogue manager, action selection and explainable AI), Activities Centre (Timeline, Quiz, Break and Sort, Memory, Tip of the Day, \ldots ), Embodied Conversational Agent (ECA, i.e., robot and avatar), and Dashboards (for authoring and monitoring the interaction). Further, the ECA is integrated with an expandable set of (mobile) health applications. The resulting system is a Personal Assistant for a healthy Lifestyle (PAL), which supports diabetic children with self-management and educates them on health-related issues (48 children, aged 6–14, recruited via hospitals in the Netherlands and in Italy). It is capable of autonomous interaction “in the wild” for prolonged periods of time without the need for a “Wizard-of-Oz” (up until 6 months online). PAL is an exemplary system that provides personalised, stable and diverse, long-term human-robot interaction.

IMPROBED: Multiple Problem-Solving Brain via Evolved Developmental Programs

Artificial neural networks (ANNs) were originally inspired by the brain; however, very few models use evolution and development, both of which are fundamental to the construction of the brain. We describe a simple neural model, called IMPROBED, in which two neural programs construct an artificial brain that can simultaneously solve multiple computational problems. One program represents the neuron soma and the other the dendrite. The soma program decides whether neurons move, change, die, or replicate. The dendrite program decides whether dendrites extend, change, die, or replicate. Since developmental programs build networks that change over time, it is necessary to define new problem classes that are suitable to evaluate such approaches. We show that the pair of evolved programs can build a single network from which multiple conventional ANNs can be extracted, each of which can solve a different computational problem. Our approach is quite general and it could be applied to a much wider variety of problems.

Practical experience in the technical systems creating with the artificial intelligence elements

The practical experience of solving scientific tasks using artificial intelligence technologies is presented. The authors offered their understanding of the term "artificial intelligence". Describes the development of the dept. №265 of Mathematical Problems of Applied Informatics V.M. Glushkov Institute of Cybernetics of the NAS of Ukraine in the creation of technical systems with elements of AI mainly to work in extreme environments. The purpose of the authors is to provide useful information to develop a strategy for the development of AI in the Ukraine. Some of these studies: monitoring the territory and management of land use technologies using remote sensing technologies from aircraft, spacecraft, unmanned aerial vehicles; monitoring the technical equipment of the underwater environment (technical means of searching for a sunken object of the submarine type for emergency operations are being developed); mine safety control (risk research during mining, creating robotic systems with elements of artificial intelligence for studying the conditions of work in the mine, warning accidents and emergency rescue work). The next direction is the diagnosis and treatment of addictive patients using the principles of therapeutic methods BiofeedBack. Attention is paid to the development of robotic technical systems with AI for servicing cosmic long missions. For this, theoretical studies have been conducted on the creation of a live brain mathematical model for its use in the development of the "artificial brain" of robots. The authors gave a list of tasks that can solve AI in programs for long-term space flights, technologies and systems that should develop in the first place to implement these tasks

Neuroscience-Inspired Parameter Selection of Spiking Neuron Using Hodgkin Huxley Model

Spiking neural networks (SNN) are currently being researched to design an artificial brain to teach it how to think, perform, and learn like a human brain. This paper focuses on exploring optimal values of parameters of biological spiking neurons for the Hodgkin Huxley (HH) model. The HH model exhibits maximum number of neurocomputational properties as compared to other spiking models, as per previous research. This paper investigates the HH model parameters of Class 1, Class 2, phasic spiking, and integrator neurocomputational properties. For the simulation of spiking neurons, the NEURON simulator is used since it is easy to understand and code.

Artificial Brain for the Humanoid-Nurse Robots of the Future: Integrating PsyNACS© and Artificial Intelligence

Robots in healthcare are being developed rapidly, as they offer wide-ranging medical applications and care solutions. However, it is quite challenging to develop high-quality, patient-centered, communication-efficient robots. This can be attributed to a multitude of barriers such as technology maturity, diverse healthcare practices, and humanizing innovations. In order to engineer an ideal Humanoid-Nurse Robots (HNRs), a profound integration of artificial intelligence (AI) and information system like nursing assessment databases for a better nursing care delivery model is required. As a specialized nursing database in psychiatric hospitals, the Psychiatric Nursing Assessment Classification System and Care Planning System (PsyNACS©) has been developed by Ito et al., to augment quality and safe nursing care delivery of psychiatric health services. This chapter describes the nursing landscape in Japan, PsyNACS© as a specialized nursing database, the HNRs of the future, and the future artificial brain for HNRs linking PsyNACS© with AI through deep learning and Natural Language Processing (NLP).

The Model-less Neuromimetic Chip and its Normalization of Neuroscience and Artificial Intelligence

<p></p><p>The conceptual basis of a novel neuromimetic chip is described. Based on an existing computational bioelectrodynamics study and adaptive brain signaling biophysics knowledge from neuroscience, the chip is, in effect, a form of inorganic artificial brain tissue. This ‘physics replication’ approach involves no abstract models of brain tissue physics or function. Instead of the physics of a general-purpose computer or the physics of abstract models of the brain on the chip (analogue or digital), this neuromimetic chip has an inorganic version of natural adaptive brain signaling physics. As a result of using the native brain physics, the chip has functionally relevant endogenous quasistatic electric and magnetic field systems of the form known to be expressed by excitable cell tissue. Fully developed at macroscopic scales it can be expected to produce an EEG/MEG-like electromagnetic signature. This article does an extended analysis to understand an observed generalized lack of the physics-replication approach and its implications for the neuroscience of natural and artificial intelligence. This is achieved through a technical comparison with the neuromimetic chip’s closest relative, the neuromorphic chip (of the class of general-purpose computers). The results indicate that the physics-replication approach is a possible but neglected option. It also reveals that the neuromimetic chip contributes empirical science, in contrast to the theoretical science conducted using general-purpose computers. Because of the chip’s novelty and proximity to foundational issues, the article contributes necessary background information in anticipation of the arrival of the first prototyping results over the coming years.<b></b></p><br><p></p>

Long- and Short-Term Conductance Control of Artificial Polymer Wire Synapses

Networks in the human brain are extremely complex and sophisticated. The abstract model of the human brain has been used in software development, specifically in artificial intelligence. Despite the remarkable outcomes achieved using artificial intelligence, the approach consumes a huge amount of computational resources. A possible solution to this issue is the development of processing circuits that physically resemble an artificial brain, which can offer low-energy loss and high-speed processing. This study demonstrated the synaptic functions of conductive polymer wires linking arbitrary electrodes in solution. By controlling the conductance of the wires, synaptic functions such as long-term potentiation and short-term plasticity were achieved, which are similar to the manner in which a synapse changes the strength of its connections. This novel organic artificial synapse can be used to construct information-processing circuits by wiring from scratch and learning efficiently in response to external stimuli.

The Model-less Neuromimetic Chip and its Normalization of Neuroscience and Artificial Intelligence

<p></p><p>The conceptual basis of a novel neuromimetic chip is described. Based on an existing computational bioelectrodynamics study and adaptive brain signaling biophysics knowledge from neuroscience, the chip is, in effect, a form of inorganic artificial brain tissue. This ‘physics replication’ approach involves no abstract models of brain tissue physics or function. Instead of the physics of a general-purpose computer or the physics of abstract models of the brain on the chip (analogue or digital), this neuromimetic chip has an inorganic version of natural adaptive brain signaling physics. As a result of using the native brain physics, the chip has functionally relevant endogenous quasistatic electric and magnetic field systems of the form known to be expressed by excitable cell tissue. Fully developed at macroscopic scales it can be expected to produce an EEG/MEG-like electromagnetic signature. This article does an extended analysis to understand an observed generalized lack of the physics-replication approach and its implications for the neuroscience of natural and artificial intelligence. This is achieved through a technical comparison with the neuromimetic chip’s closest relative, the neuromorphic chip (of the class of general-purpose computers). The results indicate that the physics-replication approach is a possible but neglected option. It also reveals that the neuromimetic chip contributes empirical science, in contrast to the theoretical science conducted using general-purpose computers. Because of the chip’s novelty and proximity to foundational issues, the article contributes necessary background information in anticipation of the arrival of the first prototyping results over the coming years.<b></b></p><br><p></p>