Autonomous learning in humanoid robotics through mental imagery

Neurorobotic Models of Neurological Disorders: A Mini Review

Modeling is widely used in biomedical research to gain insights into pathophysiology and treatment of neurological disorders but existing models, such as animal models and computational models, are limited in generalizability to humans and are restricted in the scope of possible experiments. Robotics offers a potential complementary modeling platform, with advantages such as embodiment and physical environmental interaction yet with easily monitored and adjustable parameters. In this review, we discuss the different types of models used in biomedical research and summarize the existing neurorobotics models of neurological disorders. We detail the pertinent findings of these robot models which would not have been possible through other modeling platforms. We also highlight the existing limitations in a wider uptake of robot models for neurological disorders and suggest future directions for the field.

A Database for Learning Numbers by Visual Finger Recognition in Developmental Neuro-Robotics

Numerical cognition is a fundamental component of human intelligence that has not been fully understood yet. Indeed, it is a subject of research in many disciplines, e.g., neuroscience, education, cognitive and developmental psychology, philosophy of mathematics, linguistics. In Artificial Intelligence, aspects of numerical cognition have been modelled through neural networks to replicate and analytically study children behaviours. However, artificial models need to incorporate realistic sensory-motor information from the body to fully mimic the children's learning behaviours, e.g., the use of fingers to learn and manipulate numbers. To this end, this article presents a database of images, focused on number representation with fingers using both human and robot hands, which can constitute the base for building new realistic models of numerical cognition in humanoid robots, enabling a grounded learning approach in developmental autonomous agents. The article provides a benchmark analysis of the datasets in the database that are used to train, validate, and test five state-of-the art deep neural networks, which are compared for classification accuracy together with an analysis of the computational requirements of each network. The discussion highlights the trade-off between speed and precision in the detection, which is required for realistic applications in robotics.

A comprehensive survey on humanoid robot development

The development of a versatile, fully-capable humanoid robot as envisioned in science fiction books is one of the most challenging but interesting issues in the robotic field. Currently, existing humanoid robots are designed with different purposes and applications in mind. In humanoid robot development process, each robot is designed with various characteristics, abilities, and equipment, which influence the general structure, cost, and difficulty of development. Even though humanoid robot development is very popular, a few review papers are focusing on the design and development process of humanoid robots. Motivated by this, we present this review paper to show variations in the requirements, design, and development process and also propose a taxonomy of existing humanoid robots. It aims at demonstrating a general perspective of existing humanoid robots’ characteristics and applications. This paper includes state-of-the-art and successfully reported existing humanoid robot designs along with different robots used in various robot competitions.

Path optimization for navigation of a humanoid robot using hybridized fuzzy-genetic algorithm

Purpose

Humanoids have become the center of attraction for many researchers dealing with robotics investigations by their ability to replace human efforts in critical interventions. As a result, navigation and path planning has emerged as one of the most promising area of research for humanoid models. In this paper, a fuzzy logic controller hybridized with genetic algorithm (GA) has been proposed for path planning of a humanoid robot to avoid obstacles present in a cluttered environment and reach the target location successfully. The paper aims to discuss these issues.

Design/methodology/approach

Here, sensor outputs for nearest obstacle distances and bearing angle of the humanoid are first fed as inputs to the fuzzy logic controller, and first turning angle (TA) is obtained as an intermediate output. In the second step, the first TA derived from the fuzzy logic controller is again supplied to the GA controller along with other inputs and second TA is obtained as the final output. The developed hybrid controller has been tested in a V-REP simulation platform, and the simulation results are verified in an experimental setup.

Findings

By implementation of the proposed hybrid controller, the humanoid has reached its defined target position successfully by avoiding the obstacles present in the arena both in simulation and experimental platforms. The results obtained from simulation and experimental platforms are compared in terms of path length and time taken with each other, and close agreements have been observed with minimal percentage of errors.

Originality/value

Humanoids are considered more efficient than their wheeled robotic forms by their ability to mimic human behavior. The current research deals with the development of a novel hybrid controller considering fuzzy logic and GA for navigational analysis of a humanoid robot. The developed control scheme has been tested in both simulation and real-time environments and proper agreements have been found between the results obtained from them. The proposed approach can also be applied to other humanoid forms and the technique can serve as a pioneer art in humanoid navigation.

The Representation of Motor (Inter)action, States of Action, and Learning: Three Perspectives on Motor Learning by Way of Imagery and Execution

Learning in intelligent systems is a result of direct and indirect interaction with the environment. While humans can learn by way of different states of (inter)action such as the execution or the imagery of an action, their unique potential to induce brain- and mind-related changes in the motor action system is still being debated. The systematic repetition of different states of action (e.g., physical and/or mental practice) and their contribution to the learning of complex motor actions has traditionally been approached by way of performance improvements. More recently, approaches highlighting the role of action representation in the learning of complex motor actions have evolved and may provide additional insight into the learning process. In the present perspective paper, we build on brain-related findings and sketch recent research on learning by way of imagery and execution from a hierarchical, perceptual-cognitive approach to motor control and learning. These findings provide insights into the learning of intelligent systems from a perceptual-cognitive, representation-based perspective and as such add to our current understanding of action representation in memory and its changes with practice. Future research should build bridges between approaches in order to more thoroughly understand functional changes throughout the learning process and to facilitate motor learning, which may have particular importance for cognitive systems research in robotics, rehabilitation, and sports.

Imagery May Arise from Associations Formed through Sensory Experience: A Network of Spiking Neurons Controlling a Robot Learns Visual Sequences in Order to Perform a Mental Rotation Task

Mental imagery occurs “when a representation of the type created during the initial phases of perception is present but the stimulus is not actually being perceived.” How does the capability to perform mental imagery arise? Extending the idea that imagery arises from learned associations, we propose that mental rotation, a specific form of imagery, could arise through the mechanism of sequence learning–that is, by learning to regenerate the sequence of mental images perceived while passively observing a rotating object. To demonstrate the feasibility of this proposal, we constructed a simulated nervous system and embedded it within a behaving humanoid robot. By observing a rotating object, the system learns the sequence of neural activity patterns generated by the visual system in response to the object. After learning, it can internally regenerate a similar sequence of neural activations upon briefly viewing the static object. This system learns to perform a mental rotation task in which the subject must determine whether two objects are identical despite differences in orientation. As with human subjects, the time taken to respond is proportional to the angular difference between the two stimuli. Moreover, as reported in humans, the system fills in intermediate angles during the task, and this putative mental rotation activates the same pathways that are activated when the system views physical rotation. This work supports the proposal that mental rotation arises through sequence learning and the idea that mental imagery aids perception through learned associations, and suggests testable predictions for biological experiments.

Explaining unexplained pain to fibromyalgia patients: finding a narrative that is acceptable to patients and provides a rationale for evidence based interventions

As the cause of fibromyalgia is controversial, communicating with patients can be challenging, particularly if the patient adopts the narrative 'I am damaged and so I need a more powerful pain killer'. Research shows that providing patients with alternative narratives can be helpful, but it remains unclear what particular narratives are most acceptable to patients and at the same time provide a rationale for evidence based psychological and exercise interventions. This article described the development of a new narrative and the written comments made about the narrative by fibromyalgia patients. The narrative derives from a complexity theory model and provides an alternative to biogenic and psychogenic models. The model was presented to 15 patients whose comments about comprehensibility led to the final format of the narrative. In the final form, the body is presented as 'a very, very clever computer' where fibromyalgia is caused by a software rather than a hardware problem. The software problem is caused by the body adapting when people have to 'keep going' despite 'stop signals', such as pain and fatigue. The narrative provides a rationale for engaging in psychological and exercise interventions as a way of correcting the body's software. This way of explaining fibromyalgia was evaluated by a further 25 patients attending a 7-week 'body reprogramming' intervention, where the therapy was presented as correcting the body's software, and included both exercise and psychological components. Attendance at the course was 85%. Thematic analysis of written patient feedback collected after each session showed that patients found the model believable and informative, it provided hope and was empowering. Patients also indicated that they had started to implement lifestyle change with perceived benefit. Fibromyalgia patients appear to respond positively to a technology-derived narrative based on the analogy of the body as a computer.

Lateral specialization in unilateral spatial neglect: a cognitive robotics model

In this paper, we present the experimental results of an embodied cognitive robotic approach for modelling the human cognitive deficit known as unilateral spatial neglect (USN). To this end, we introduce an artificial neural network architecture designed and trained to control the spatial attentional focus of the iCub robotic platform. Like the human brain, the architecture is divided into two hemispheres and it incorporates bio-inspired plasticity mechanisms, which allow the development of the phenomenon of the specialization of the right hemisphere for spatial attention. In this study, we validate the model by replicating a previous experiment with human patients affected by the USN and numerical results show that the robot mimics the behaviours previously exhibited by humans. We also simulated recovery after the damage to compare the performance of each of the two hemispheres as additional validation of the model. Finally, we highlight some possible advantages of modelling cognitive dysfunctions of the human brain by means of robotic platforms, which can supplement traditional approaches for studying spatial impairments in humans.

Internal Models, Vestibular Cognition, and Mental Imagery: Conceptual Considerations

Vestibular cognition has recently gained attention. Despite numerous experimental and clinical demonstrations, it is not yet clear what vestibular cognition really is. For future research in vestibular cognition, adopting a computational approach will make it easier to explore the underlying mechanisms. Indeed, most modeling approaches in vestibular science include a top-down or a priori component. We review recent Bayesian optimal observer models, and discuss in detail the conceptual value of prior assumptions, likelihood and posterior estimates for research in vestibular cognition. We then consider forward models in vestibular processing, which are required in order to distinguish between sensory input that is induced by active self-motion, and sensory input that is due to passive self-motion. We suggest that forward models are used not only in the service of estimating sensory states but they can also be drawn upon in an offline mode (e.g., spatial perspective transformations), in which interaction with sensory input is not desired. A computational approach to vestibular cognition will help to discover connections across studies, and it will provide a more coherent framework for investigating vestibular cognition.

Making fingers and words count in a cognitive robot

Evidence from developmental as well as neuroscientific studies suggest that finger counting activity plays an important role in the acquisition of numerical skills in children. It has been claimed that this skill helps in building motor-based representations of number that continue to influence number processing well into adulthood, facilitating the emergence of number concepts from sensorimotor experience through a bottom-up process. The act of counting also involves the acquisition and use of a verbal number system of which number words are the basic building blocks. Using a Cognitive Developmental Robotics paradigm we present results of a modeling experiment on whether finger counting and the association of number words (or tags) to fingers, could serve to bootstrap the representation of number in a cognitive robot, enabling it to perform basic numerical operations such as addition. The cognitive architecture of the robot is based on artificial neural networks, which enable the robot to learn both sensorimotor skills (finger counting) and linguistic skills (using number words). The results obtained in our experiments show that learning the number words in sequence along with finger configurations helps the fast building of the initial representation of number in the robot. Number knowledge, is instead, not as efficiently developed when number words are learned out of sequence without finger counting. Furthermore, the internal representations of the finger configurations themselves, developed by the robot as a result of the experiments, sustain the execution of basic arithmetic operations, something consistent with evidence coming from developmental research with children. The model and experiments demonstrate the importance of sensorimotor skill learning in robots for the acquisition of abstract knowledge such as numbers.