In the paper finite-dimensional dynamical control systems described by first order semilinear both stationary and nonstationary ordinary differential state equations with single variable point delay in control are con...
详细信息
In the paper finite-dimensional dynamical control systems described by first order semilinear both stationary and nonstationary ordinary differential state equations with single variable point delay in control are considered. Using a generalized open mapping theorem, sufficient conditions for constrained local controllability in a given time interval are formulated and proved. These conditions require verification of constrained global controllability of the associated linear first-order stationary or nonstationary dynamical control systems. It is generally assumed, that the values of admissible controls are in a convex and closed cone with vertex at zero. Moreover, several remarks and comments on the existing results for controllability of semilinear dynamical control systems are also presented. Finally, simple numerical example which illustrates theoretical considerations is also given. It should be pointed out, that the results given in the paper extend for the case of semilinear nonstationary first-order dynamical systems constrained controllability conditions, which were previously known only for linear stationary first-order systems.
The present proposal is inspired by bionics; in this way, local path planning is developed by using the perception system under a deliberative strategy. Indoor global navigation is attained by solving local goals with...
详细信息
The present proposal is inspired by bionics; in this way, local path planning is developed by using the perception system under a deliberative strategy. Indoor global navigation is attained by solving local goals within an occupancy grid framework. Path-planning is computed at each perception step by using the on-robot monocular perception system and considering the detected obstacles. In this context, artificial potential fields are used for attracting the robot towards the desired coordinates. Trajectory tracking is based on reactive behaviors that are performed by using local model predictive control techniques. Global navigation is done by considering a set of local points that have to be reached using reactive behaviors. Dead reckoning problems are set to zero by selecting natural structured landmarks as local passage points that act as local attraction fields towards the goal. The research work is completed with a set of local experiments developed on a wheeled mobile robot.
The conventional mouth gender recognition is based on a static image and ignore the dynamic information. In this paper, we propose a lip movement gender recognition method to improve the accuracy by exploring the dyna...
详细信息
The conventional mouth gender recognition is based on a static image and ignore the dynamic information. In this paper, we propose a lip movement gender recognition method to improve the accuracy by exploring the dynamic information while a user is speaking. In order to overcome the difficulty caused by the nonlinear distribution of the lip images, Gausian Mixture Models (GMM) is adopted to represent the lip images. A similarity measure is defined to measure the difference between the successive frames. Gender recognition, as a soft biometric trait, can provide useful information for improving the performance of the speaker recognition systems. The accuracy of voice-based speaker gender recognition is high if the condition of the environment is good. But it will be drastically decreased if the test is conducted in a noisy environment. In this paper, we showed that lip movement, considered as a sequence of mouth images, can provide additional information than mouth alone for recognizing gender Experimental result obtained showed the effectiveness of the proposed method which is comparable to using just the voice information.
Reaching and grasping of objects in an everyday-life environment seems so simple for humans, though so complicated from an engineering point of view. Humans use a variety of strategies for reaching and grasping anythi...
详细信息
Reaching and grasping of objects in an everyday-life environment seems so simple for humans, though so complicated from an engineering point of view. Humans use a variety of strategies for reaching and grasping anything from the simplest to the most complicated objects, achieving high dexterity and efficiency. This seemingly simple process of reach-to-grasp relies on the complex coordination of the musculoskeletal system of the upper limbs. In this paper, we study the muscular co-activation patterns during a variety of reach-to-grasp motions, and we introduce a learning scheme that can discriminate between different strategies. This scheme can then classify reach-to-grasp strategies based on the muscular co-activations. We consider the arm and hand as a whole system, therefore we use surface ElectroMyoGraphic (sEMG) recordings from muscles of both the upper arm and the forearm. The proposed scheme is tested in extensive paradigms proving its efficiency, while it can be used as a switching mechanism for task-specific motion and force estimation models, improving EMG-based control of robotic arm-hand systems.
Due to the rapid increase of number of industrial or domestic systems that must be controlled it is clear that new, more natural methods of control are needed. This paper presents an intelligent human machine interfac...
详细信息
Due to the rapid increase of number of industrial or domestic systems that must be controlled it is clear that new, more natural methods of control are needed. This paper presents an intelligent human machine interface based on hand's gesture recognition. The gestures based control system is composed by two subsystems that communicated via radio waves. The first subsystem is a bracelet that captures the movement of the hand using accelerometers. The second subsystem is the control box on which the data processing takes place. Artificial Neural Networks (ANN) are used to add learning capabilities and adaptive behavior to intelligent interfaces that can be used even by elderly or impaired people. Field Programmable Gate Array (FPGA) implementation is an easy an attractive way for hardware implementation. The desired network is modeled, trained and simulated using Neural Network Toolbox. Many networks architecture trained with different methods could be simulated and the network that is best performing for given application is chosen for hardware implementation using System Generator tool developed by Xilinx Inc. This also allows the easy generation of Hardware Description Language (HDL) code from the system representation in Simulink. This HDL design can then be synthesized for implementation in the Xilinx family of FPGA devices.
The development of a Hardware-in-the-Loop (HiL) simulation platform for precision induction motor (IM) servo drive development, evaluation and testing of various control architectures is described in this paper. The p...
详细信息
The development of a Hardware-in-the-Loop (HiL) simulation platform for precision induction motor (IM) servo drive development, evaluation and testing of various control architectures is described in this paper. The platform uses industrial graded hardware components, i.e. Mitsubishi IGBT inverter, 3-phase induction motor and incremental optical encoder as well as various measurement sensors. Its main computational core is implemented using an xPC Target platform which enables rapid validation, prototyping and deployment of various control algorithms via Matlab & Simulink.
This paper proposes a methodology for the real-time finger gesture following and control of mechatronic systems based on computer vision and machine learning techniques. The goal of this research is to develop a human...
详细信息
This paper proposes a methodology for the real-time finger gesture following and control of mechatronic systems based on computer vision and machine learning techniques. The goal of this research is to develop a human-machine interface that could be able to control a mechatronic system by performing finger gestures in space or on a surface without the use of any kind of keyboard neither a joystick. The finger gestures will be continuously followed and directly mapped with commands of mechatronic systems such as start moving, stop moving, forward moving, backward moving etc. The proposed methodology relies on the finger gesture data acquisition, hand segmentation, fingertips localization/ identification, high-level feature extraction, early recognition and prediction using machine learning techniques and its integration into a mechatronic system. The LEGO MINDSTORMS NXT robotics platform controlled by matlab software could be used in the proposed methodology.
The paper deals with constructing the inertial navigation system(hereafter INS) which will be utilized for the calibration of a robotic workplace. The calibration is necessary for adapting the simulation of a producti...
详细信息
The paper deals with constructing the inertial navigation system(hereafter INS) which will be utilized for the calibration of a robotic workplace. The calibration is necessary for adapting the simulation of a production device model to real geometric conditions. The goal is to verify experimentally the proposed inertial navigation system in real conditions of the industrial robot operation.
An embedded particle swarm optimization(PSO)technique combined with virtual pheromones deposition and rules for artificial bird flocking is proposed to handle an area coverage problem using a swarm of mobile robots.A ...
详细信息
An embedded particle swarm optimization(PSO)technique combined with virtual pheromones deposition and rules for artificial bird flocking is proposed to handle an area coverage problem using a swarm of mobile robots.A simulation tool VERA that was developed to simulate a swarm behavior of a group of mobile agents is *** of simulation experiments and tests on Lego robots that prove the concept are *** are discussed and future development is suggested in the end of the paper.
The most common image feature extraction algorithms such as SIFT (Scale Invariant Feature Transform) and SURF (Speeded Up Robust Feature) have been proven to be invariant to changes in rotation, scale and with restric...
详细信息
The most common image feature extraction algorithms such as SIFT (Scale Invariant Feature Transform) and SURF (Speeded Up Robust Feature) have been proven to be invariant to changes in rotation, scale and with restrictions to illumination and viewpoint changes. These algorithms generate descriptor vectors around keypoints in 2D images. Close descriptors suggest similar image patch. In case of mobile robotics applications it is important to achieve good viewpoint invariance and stability to detect landmarks and objects with high reliability. Improving viewpoint invariance for image feature detection increases the efficiency of SLAM algorithms. In this paper we present and evaluate a method to use additional data provided by range image sensors to supplement traditional feature extraction algorithms to improve viewpoint invariance. We present the method and results of computer simulation and also real world examples comparing the SURF (OpenSURF) with and without the improvement. An active structured light based range and intensity image sensor was used to acquire real world test images.
暂无评论