Articles

Permanent URI for this collection

https://testres.nu.edu.kz/handle/123456789/1165

Browse

Browsing Articles by Author "Folgheraiter, Michele"

Now showing 1 - 7 of 7
  • Thumbnail Image
    ItemOpen Access
    A Chaotic Neural Network as Motor Path Generator for Mobile Robotics
    (IEEE International Conference on Robotics and Biomimetics, 2014) Folgheraiter, Michele; Gini, Giuseppina
    This work aims at developing a motor path generator for applications in mobile robotics based on a chaotic neural network. The computational paradigm inspired by the neural structure of microcircuits located in the human prefrontal cortex is adapted to work in real-time and used to generate the joints trajectories of a lightweight quadruped robot. The recurrent neural network was implemented in Matlab and a software framework was developed to test the performances of the system with the robot dynamic model. Preliminary results demonstrate the capability of the neural controller to learn period signals in a short period of time allowing adaptation during the robot operation
  • Thumbnail Image
    ItemOpen Access
    A combined B-Spline-Neural-Network and ARX Model for Online Identi cation of Nonlinear Dynamic Actuation Systems
    (Neurocomputing, 2016) Folgheraiter, Michele
    This paper presents a block oriented nonlinear dynamic model suitable for online identi cation.The model has the well known Hammerstein architecture where as a novelty the nonlinear static part is represented by a B-spline neural network (BSNN), and the linear static one is formalized by an auto regressive exogenous model (ARX). The model is suitable as a feed-forward control module in combination with a classical feedback controller to regulate velocity and position of pneumatic and hydraulic actuation systems which present non stationary nonlinear dynamics. The adaptation of both the linear and nonlinear parts is taking place simultaneously on a patterby- patter basis by applying a combination of error-driven learning rules and the recursive least squares method. This allows to decrease the amount of computation needed to identify the model's parameters and therefore makes the technique suitable for real time applications. The model was tested with a silver box benchmark and results show that the parameters are converging to a stable value after 1500 samples, equivalent to 7.5s of running time. The comparison with a pure ARX and BSNN model indicates a substantial improvement in terms of the RMS error, while the comparison with alternative non linear dynamic models like the NNOE and NNARX, having the same number of parameters but greater computational complexity, shows comparable performances.
  • Thumbnail Image
    ItemOpen Access
    A Multi-Modal haptic interface for Virtual Reality and Robotics
    (Journal of Intelligent and Robotic Systems, 2008-08) Folgheraiter, Michele; Gini, Giuseppina; Vercesi, Dario
    In this paper we present an innovative haptic device that combines the electro-tactile stimulation with the force and visual feedbacks in order to improve the perception of a virtual world. We discuss about the sensation evoked in a user by the haptic, force, and visual interface provided by this device, implemented as a special glove, equipped with sensors and actua- tors connected to a PC. The techniques used to recreate tactile and kines- thetic sensations are based on an innovative use of cutaneous stimulation integrated with actuators and 3D modelling techniques. We discuss about the specificity of haptic interfaces, their controllers, their open problems. We present results about generating the sensation of touching virtual ob- jects with our device. Experiments show also that, using a multi-modal sensorial pattern of stimulation, the subject perceives more realistically the virtual object. We discuss about possible use of the same technique as a way to interface intelligent robots.
  • Thumbnail Image
    ItemOpen Access
    A Neuromorphic Motion Controller for a Biped Robot
    (Human Performance and Robotics, Satellite Workshop of IEEE Humanoid 2016, 2016) Folgheraiter, Michele; Keldibek, Amina; Aubakir, Bauyrzhan; Salakchinov, Shyngys; Gini, Giuseppina; Mauro Franchi, Alessio
    Here we propose a neuromorphic control system for a medium size humanoid robot under development in the Robotics and Mechatronics Department at Nazarbayev University and in cooperation with Politecnico di Milano.
  • Thumbnail Image
    ItemOpen Access
    Actuation Design Methodology for Haptic Interfaces and Rehabilitation Systems
    (IEEE 8th International Conference on Application of Information and Communication Technologies, 2014) Folgheraiter, Michele
    This paper introduces a methodology and a software framework intended to optimize and speed up the design process of a haptic interface or a rehabilitation system. Starting from an initial mechanical design the procedure allows to export the kinematic and dynamic properties of the robotic system in a simulation environment. The software receives as additional input the Cartesian or joints trajectories and generates as output the required torques at the joints. From the recorded measurements the program extracts the torque ranges necessary to choose a suitable actuation system for the robot. The possibility to run the simulation in batch modality allows also to define different optimization techniques that may be used to reduce the overall system weight or increase its payload
  • Thumbnail Image
    ItemOpen Access
    ADVANCED STEPS IN BIPED ROBOTICS: INNOVATIVE DESIGN AND INTUITIVE CONTROL THROUGH SPRING-DAMPER ACTUATOR
    (4th IEEE/RAS International Conference on Humanoid Robots, 2004) Scarfogliero, Umberto; Folgheraiter, Michele; Gini, Giuseppina
    This paper focuses on the study and design of an anthropomorphical light biped robot. The robot presents a total of twelve degree of freedom that will permit it to act a walk in a three dimensional space, right now tested only in simulation. Each joint resemble the functionalities of the human articulation and is moved by tendon connected with actuator located in the robot’s pelvis. We implemented and tested an innovative actuator that permits to set the joint stiffness in real time maintaining a simple position control paradigm. The controller is able to estimate the external load measuring the spring deflection and demonstrated to be particularly robust respect to system uncertainties, such as inertia value changes. Comparing the resulting control law with existing models we found several similarities with the Equilibrium Point Theory.
  • Thumbnail Image
    ItemOpen Access
    Development of a neuromorphic control system for a lightweight humanoid robot
    (The International Conference on Information Technology and Digital Applications, 2016-11) Folgheraiter, Michele; Keldibek, Amina; Aubakir, Bauyrzhan; Salakchinov, Shyngys
    A neuromorphic control system for a lightweight middle size humanoid biped robot built using 3D printing techniques is proposed. The control architecture consists of different modules capable to learn and autonomously reproduced complex periodic trajectories. Each modul is represented by a chaotic Recurrent Neural Network (RNN) with a core of dynamic neurons randomly and sparsely connected with fixed synapses . A set of read-out units with adaptable synapses realize a linear combination of the neurons output in order to reproduce the target signals. Different experiments were conducted to find out the optimal initialization for the RNN`s parameters. From simulation results, using normalized signals obtained from the robot model, it was proven that all the instances of the control module can learn and reproduce the target trajectories with an average RMS error of 1.63 and variance 0.74