No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Neurocontroller for Robot Arms Based on Biologically Inspired Visuomotor Coordination Neural Models
Abstract
Introduction Biological Framework of Motor Control Modeling and Robotic Approaches Structure and Functionality of Proposed Neural Model Experimental Results Conclusion Acknowledgments References
... Models of human movement are very useful for robotics, where it is of great interest to develop robust and adaptable systems working in the real, unstructured world. Inverse kinematics is one of the crucial problems in developing robot controllers, and artificial neural networks represent an alternative solution with respect to inverse transform and iterative methods [33], especially when the number of degrees of freedom to be controlled is high, as in the case of redundant robot manipulators [47,53,55]. ...
The tradeoff between speed and accuracy of human movements has been exploited from many different perspectives, such as experimental psychology, workspace design, human–machine interface. This tradeoff is formalized by Fitts’ law, which states a linear relationship between the duration and the difficulty of the movement. The bigger is the required accuracy in reaching a target or farther is the target, the slower has to be the movement. A variety of computational models of neuromusculoskeletal systems have been proposed to pinpoint the neurobiological mechanisms that are involved in human movement. We introduce a neurocomputational model of spinal cord to unveil how the tradeoff between speed and accuracy elicits from the interaction between neural and musculoskeletal systems. Model simulations showed that the speed–accuracy tradeoff is not an intrinsic property of the neuromuscular system, but it is a behavioral trait that emerges from the strategy adopted by the central nervous system for executing faster movements. In particular, results suggest that the velocity of a previous learned movement is regulated by the monosynaptic connection between cortical cells and alpha motoneurons.
... Several architectures have been introduced using the mathematical mechanism of self-organizing maps (SOM), which enable learning of sensorimotor mapping involved in modeling forward and inverse models in robotic control (Kawato and Samejima 2007). Similarly, other neuronal control architectures have implemented hierarchical controllers acting in parallel and are based on sensorimotor transformation in cortical motor areas to solve a wide range of problems, such as inverse kinematics, reactive behaviours and autonomous navigation (García-Córdova 2007;Bullock et al. 1999;Ajemian et al. 2000;Laschi et al. 2008;Guglielmelli et al. 2007). ...
This paper describes the BUSCAMOS-Oil monitoring system, which is a robotic platform consisting of an autonomous surface vessel combined with an underwater vehicle. The system has been designed for the long-term monitoring of oil spills, including the search for the spill, and transmitting information on its location, extent, direction and speed. Both vehicles are controlled by two different types of bio-inspired neural networks: a Self-Organization Direction Mapping Network for trajectory generation and a Neural Network for Avoidance Behaviour for avoiding obstacles. The systems’ resilient capabilities are provided by bio-inspired algorithms implemented in a modular software architecture and controlled by redundant devices to give the necessary robustness to operate in the difficult conditions typically found in long-term oil-spill operations. The efficacy of the vehicles’ adaptive navigation system and long-term mission capabilities are shown in the experimental results.
... Complexity and difficulty-to-generalization represent their main deficiencies. Visuo-motor coordination neural models of humans [22] and specific learning ability is another motion principle where Guglielmelli et al. represented a neurocontroller to control a redundant manipulator [23]. With respect to the nature of the learning which occurs within an action-perception cycle, the previously mentioned controller was developed to a model-free learning-based framework to control the pose of the end-effector of a redundant robotic arm [24]. ...
Abstract:
Purpose: In this paper an innovative kinematic control algorithm is proposed for redundant robotic manipulators. The algorithm takes advantage of a bio-inspired approach.
Design/methodology/approach: A simplified 2 DOFs model is presented to handle kinematic redundancy in the x-y plane; an extension to three-dimensional tracking tasks is presented as well. A set of sample trajectories were used to evaluate the performances of the proposed algorithm.
Findings: The results from the simulations confirm the continuity and accuracy of generated joint profiles for given end-effector trajectories as well as algorithm robustness, singularity and self-collision avoidance.
Originality/value: This paper shows how to control a redundant robotic arm by applying human upper arm-inspired concept of inter-joint dependency.
— The production of movement in vertebrate species requisites their nervous system to deal with a high degree of freedom. The strategy that the central nervous system (CNS) recruits to overcome this barrier has been a longstanding question among researchers. A hypothesis that sheds light on this motor control problem is that the CNS uses a modular organization to simplify the task and generate a purposeful movement. In this study, we investigated on this theory by analyzing the time-varying muscle synergy modules. Furthermore, we devised a new plan in the calculation of the relating onset time coefficients by applying K-Means clustering algorithm. We also tested this algorithm in the calculation of time-varying synergy components from the electromyogram (EMG) data we recorded from ten active muscles of four subjects during a hand-reaching movement. The evaluations of the results indicate that a high similarity of synergy components between subjects is evident and this proves the efficiency of the proposed method.
This paper presents a comprehensive overview of modelling, simulation and implementation of neural networks, taking into account that two aims have emerged in this area: the improvement of our understanding of the behaviour of the nervous system and the need to find inspiration from it to build systems with the advantages provided by nature to perform certain relevant tasks. The development and evolution of different topics related to neural networks is described (simulators, implementations, and real-world applications) showing that the field has acquired maturity and consolidation, proven by its competitiveness in solving real-world problems. The paper also shows how, over time, artificial neural networks have contributed to fundamental concepts at the birth and development of other disciplines such as Computational Neuroscience, Neuro-engineering, Computational Intelligence and Machine Learning. A better understanding of the human brain is considered one of the challenges of this century, and to achieve it, as this paper goes on to describe, several important national and multinational projects and initiatives are marking the way to follow in neural-network research.
Great progress has been achieved in the last few years in Neurorehabilitation and Neural Engineering. Thanks to the parallel development of medical research, the chances to survive a neural injury are growing, so it is necessary to develop technologies that can be used both for rehabilitation and to improve daily activities and social life. New robotic and prosthetic devices and technologies such as Functional Electrical Stimulation, Brain-Computer Interfaces and Virtual Reality are slowly becoming part of clinical rehabilitation setting, but they are far from being part of everyday life for the patients. As technology improves, expectations keep rising and new problems emerge: from cost reduction to the diffusion in the medical environment, from the enlargement of the number of patients who may benefit from these technologies to transferring rehabilitation to the patient’s home. All these requests lead to great challenges that researchers have to face to enhance their contribution towards the improvement of rehabilitation and life conditions of patients with neural impairment.
Neuroprosthetics is a comparatively young, dynamically developing subject with double-digit sales growth rates. Due to the preconditions on implantability, biocompatibility, and miniaturization, it is strongly linked to the development of microsystems technology, nanotechnology, information technology, biotechnology, and the application of new materials. The fields of application of neuroprostheses are diseases associated with impairments of myogenic or neurogenic functions. These can lead to the loss of the whole function. Neuroprostheses use electric stimuli to stimulate neural structures, muscles or receptors, in order to support, augment or partly restore the respective disordered or lost function. Functional disorders include paralysis after stroke, reduced hearing, tremor as an example of movement disorders, or the loss of an extremity. Often, the use of a neural prosthesis can improve the quality of life of the person concerned. The objective is to help the patient to participate in everyday life. Thus, cosmetic, ethical, and social aspects always have to be considered.
ResearchGate has not been able to resolve any references for this publication.