AN IMPROVED SYNERGETIC ALGORITHM FOR IMAGE CLASSIFICATION

A major application of pattern recognition technology is in industrial manufacturing. In this paper, we develop a synergetic algorithm for pattern recognition which is based purely on the appearance of the object, without reference to a CAD model of the object, making the technique generic and flexible. In particular, we apply this algorithm to the problem of classifying an object into a number of user-defined aspects, which is an important problem in robotic manipulation of objects. The technique is fast and can be trained using a non-iterative, deterministic training scheme which will find a zero-error solution on a training set, if such a solution exists.     

基于遗传算法的原型模式选取算法

该文了原型模式选取对协同方法的模式识别性能有着非常重要的作用,并提出了一种基于遗传算法的原型模式选取算法,对从实际应用中获得的样本进行的实验证明：新算法能有效地在原型模式空间搜索全局最优解,使协同方法的识别性能有较大提高。     

基于协同感知的视觉选择注意计算模型

鉴于在任务相关的视觉注意中,需要建立基于任务的视觉注意显著图来引导视觉注意,为此利用与人认知过程相接近的协同感知理论来研究基于任务的视觉注意计算模型,即首先利用协同识别理论研究二义及多义模式的视觉感知,得到协同视觉感知理论;然后将协同视觉感知中的模式与从视觉注意模型中提取的底层视觉特征相对应,利用偏置矩阵的性质计算底层视觉特征间受任务影响而产生的偏置,再由此偏置和底层视觉特征生成基于任务的视觉注意显著图;最后提出了基于协同感知理论的视觉选择注意计算模型。该算法用于基于任务的视觉搜索的实验结果表明,该算法是有效的,在认知上是合理的。     

模式识别协同算法的平移不变性

在模式识别的协同学理论框架下，引入了和坐标空间相关的模式矢量及其关于坐标的Ｆｏｕｒｉｅｒ变换，从而解决了平移不变性的问题。文中以染色体识别为例作了验证。     

Reflective workpiece detection and localization for flexible robotic cells

A smart vision system for industrial robotic cells is presented. It can recognize and localize a reflective workpiece, and allows for automatic adjustments of the robot program. The purpose of the study is to improve industrial robots awareness of the environment and to increase adaptability of the manufacturing processes where full control over environment is not achievable. This approach is particularly relevant to small batch robotic production, often suffering from only partial control of the process parameters, such as the order of jobs, workpiece position, or illumination conditions.A distinguishing aspect of the study is detection of workpieces made of diverse materials, including shiny metals. Reflective surfaces are common in the industrial manufacturing, but are rarely considered in the research on object recognition because they hinder many of the object recognition algorithms. The proposed solution has been qualified and tested on a selected benchmark in a realistic workshop environment with artificial light conditions. The training of the object recognition software is an automatic process and can be executed by non-expert industrial users to allow for recognition of different types of objects.     

Accurate robotic belt grinding of workpieces with complex geometries using relative calibration techniques

Robotic belt grinding operations are performed by mounting a workpiece to the end effector and commanding it to move along a trajectory while maintaining contact with the belt grinding wheel. A constant contact force throughout the grinding process is necessary to provide a smooth finish on the workpiece, but it is difficult to maintain this force due to a multitude of installation, manipulation, and calibration errors. The following describes a novel methodology for robotic belt grinding, which primarily focuses on system calibration and force control to improve grinding performance. The overall theory is described and experimental results of turbine blade grinding for each step of the methodology are shown.     

Adaptive stiffness estimation for compliant robotic manipulation using stochastic disturbance models

To achieve haptic telepresence and proper contact behaviour, the control action of a robotic manipulator must be designed with respect to contact parameters. Unfortunately, it is hard to know these parameters exactly in unknown or partly known environments. In this case, contact instability and poor dynamic accuracy can arise due to the presence of modelling errors in the control design. To overcome these problems, online estimation of the relevant contact parameters can be performed, with corresponding adaptation of control laws. This article presents an algorithm for online stiffness estimation for compliant robotic manipulation based on the extended state-space representation of the system and force signals. No position or velocity measurements are required. The algorithm, supported by theoretical analysis, uses offline data concerning several stiffness mismatch scenarios and, through a least square error analysis, computes an estimate of the stiffness value. Simulation results are presented, with fast and accurate estimation even in the presence of noise, highlighting the merits of the method.     

Evaluation of a grey scale tactile array sensor pad for robotic applications

Since sensory feedback is an important part of robot control and the acquisition, manipulation, and recognition of objects, incorporating a sense of touch into a robotic system can greatly enhance the performance of that system. This article describes the evaluation of a recently developed low-resolution tactile array sensor pad system for use in robotic applications. Computer algorithms are developed which acquire data from the sensor pad and display the data on a CRT screen. Vision algorithms are implemented in order to extract the necessary information from the tactile data which will aid in the acquisition, manipulation, and recognition of objects. An object's pose is estimated by calculating its center of gravity (position) and principal axis (orientation). Recognizing an object and distinguishing between different objects is accomplished by implementing algorithms which estimate an object's perimeter (shape) and area (size). This work demonstrates that a low-resolution tactile array sensor is capable of providing the information that is required for many robotic applications in which objects must be acquired, manipulated, and recognized. Such a system provides a low-cost alternative to more conventional vision-based systems.     

Survey of robotic manipulation studies intending practical applications in real environments -object recognition,soft robot hand,and challenge program and benchmarking-

Aiming at accelerating the creation of new techniques on dexterous robotic manipulations, this paper surveyed the recent results on object recognition, soft robotic hands, and benchmarks and challenge/competition programs. The former two topics construct the elemental components of the new technologies on robotic manipulations, while the last one is a key for proceeding the creation and realization of the actual robotic manipulations with the new techniques. With these surveys, we will reveal the solved and unsolved issues for the next step to realize robotic dexterous manipulation systems comparable to human being.     

Improving the Behavior of Intelligent Tutoring Agents with Data Mining

This article presents a novel framework for adapting the behavior of intelligent agents. The framework consists of an extended sequential pattern mining algorithm that, in combination with association rule discovery techniques, is used to extract temporal patterns and relationships from the behavior of human agents executing a procedural task. The proposed framework has been integrated within the CanadarmTutor, an intelligent tutoring agent aimed at helping students solve procedural problems that involve moving a robotic arm in a complex virtual environment. We present the results of an evaluation that demonstrates the benefits of this integration to agents acting in ill-defined domains.     

Force control-based vibration suppression in robotic grinding of large thin-wall shells

Vibration suppression is a major difficulty in the grinding of low-stiffness large thin-wall shells. The paper proposes that effective workpiece vibration control can be performed by a novel force-controlled end-effector integrated into a robotic grinding workcell. First, a dynamics model is built to capture the characteristics and vibration suppression mechanism of force control-based robotic grinding, then a novel force control-based vibration suppression method is designed for grinding large thin-wall shells, and three robotic grinding tests are conducted to validate the effects of the new method and the grinding performance of the force control-based robotic grinding workcell. The results are: 75% reduction in the amplitude of workpiece vibration; effective suppression of non-tool passing frequency; stable grinding of large thin-wall shells remarkably enhancing grinding depth up to 0.3 mm per pass, grinding depth error less than ±0.1 mm, and significant improvement of the workpiece surface quality up to Ra=0.762 μm.     

Development of cutaneo-motor coordination in an autonomous robotic system

The capability of autonomously discovering relations between perceptual data and motor actions is crucial for the development of robust adaptive robotic systems intended to operate in an unknown environment. In the case of robotic tactile perception, a proper interaction between contact sensing and motor control is the basic step toward the execution of complex motor procedures such as grasping and manipulation.In this paper the autonomous development of cutaneo-motor coordination is investigated in the case of a robotic finger mounted on a robotic manipulator, for a particular class of micromovements. A neural network architecture linking changes in the sensed tactile pattern with the motor actions performed is described and experimental results are analyzed. Examples of application of the developed sensory-motor coordination in the generation of motor control procedures for the estimate of surface curvature are considered.     

Learning to design synergetic computers with an extended symmetric diffusion network.

This article proposes an extended symmetric diffusion network that is applied to the design of synergetic computers. The state of a synergetic computer is translated to that of order parameters whose dynamics is described by a stochastic differential equation. The order parameter converges to the Boltzmann distribution, under some condition on the drift term, derived by the Fokker-Planck equation. The network can learn the dynamics of the order parameters from a nonlinear potential. This property is necessary to design the coefficient values of the synergetic computer. We propose a searching function for the image processing executed by the synergetic computer. It is shown that the image processing with the searching function is superior to the usual image-associative function of synergetic computation. The proposed network can be related, as a special case, to the discrete-state Boltzmann machine by some transformation. Finally, the extended symmetric diffusion network is applied to the estimation problem of an entire density function, as well as the proposed searching function for the image processing.     

Generic development methodology for flexible robotic pick-and-place workcells based on Digital Twin

Together with the trends of mass personalization, flexible robotic applications become more and more popular. Although conventional robotic automation of workpiece manipulation seems to be solved, advanced tasks still need great amount of effort to be reached. In most cases, on-site robot programming methods, which are intuitive and easy to use, are not applicable in flexible scenarios. On the other hand, the application of offline programming methods requires careful modeling and planning. Consequently, this paper proposes a generalized development methodology for flexible robotic pick-and-place workcells, in order to provide guidance and thus facilitate the development process. The methodology is based on the Digital Twin (DT) concept, which allows the iterative refinement of the workcell both in the digital and in the physical space. The goal is to speed up the overall commissioning (or reconfiguration) process and reduce the amount of work in the physical workcell. This can be achieved by digitizing and automating the development, and maintaining sufficient twin closeness. With that, the operation of the digital model can be accurately realized in the physical workcell. The methodology is presented through a semi-structured pick-and-place task, realized in an experimental robotic workcell together with a reconfiguration scenario.     

An instrumented glove for grasp specification invirtual-reality-based point-and-direct telerobotics

Hand posture and force, which define aspects of the way an object is grasped, are features of robotic manipulation. A means for specifying these grasping “flavors” has been developed that uses an instrumented glove equipped with joint and force sensors. The new grasp specification system will be used at the Pennsylvania State University (Penn State) in a Virtual Reality based Point-and-Direct (VR-PAD) robotics implementation. Here, an operator gives directives to a robot in the same natural way that human may direct another. Phrases such as “put that there” cause the robot to define a grasping strategy and motion strategy to complete the task on its own. In the VR-PAD concept, pointing is done using virtual tools such that an operator can appear to graphically grasp real items in live video. Rather than requiring full duplication of forces and kinesthetic movement throughout a task as is required in manual telemanipulation, hand posture and force are now specified only once. The grasp parameters then become object flavors. The robot maintains the specified force and hand posture flavors for an object throughout the task in handling the real workpiece or item of interest     

In-hand recognition and manipulation of elastic objects using a servo-tactile control strategy

Grasping and manipulating objects with robotic hands depend largely on the features of the object to be used. Especially, features such as softness and deformability are crucial to take into account during the manipulation tasks. Indeed, positions of the fingers and forces to be applied by the robot hand when manipulating an object must be adapted to the caused deformation. For unknown objects, a previous recognition stage is usually needed to get the features of the object, and the manipulation strategies must be adapted depending on that recognition stage. To obtain a precise control in the manipulation task, a complex object model is usually needed and performed, for example using the Finite Element Method. However, these models require a complete discretization of the object and they are time-consuming for the performance of the manipulation tasks. For that reason, in this paper a new control strategy, based on a minimal spring model of the objects, is presented and used for the control of the robot hand. This paper also presents an adaptable tactile-servo control scheme that can be used in in-hand manipulation tasks of deformable objects. Tactile control is based on achieving and maintaining a force value at the contact points which changes according to the object softness, a feature estimated in an initial recognition stage.     

A neural network approach to characterize pattern parameters in process control charts

Abnormal patterns on manufacturing process control charts can reveal potential quality problems due to assignable causes at an early stage, helping to prevent defects and improve quality performance. In recent years, neural networks have been applied to the pattern recognition task for control charts. The emphasis has been on pattern detection and identification rather than more detailed pattern parameter information, such as shift magnitude, trend slope, etc., which is vital for effective assignable cause analysis. Moreover, the identification of concurrent patterns (where two or more patterns exist together) which are commonly encountered in practical manufacturing processes has not been reported. This paper proposes a neural network-based approach to recognize typical abnormal patterns and in addition to accurately identify key parameters of the specific patterns involved. Both single and concurrent patterns can be characterized using this approach. A sequential pattern analysis (SPA) design was adopted to tackle complexity and prevent interference between pattern categories. The performance of the model has been evaluated using a simulation approach, and numerical and graphical results are presented which demonstrate that the approach performs effectively in control chart pattern recognition and accurately identifies the key parameters of the recognized pattern(s) in both single and concurrent pattern circumstances.     

Advanced teleoperation and control system for industrial robots based on augmented virtuality and haptic feedback

There are some industrial tasks that are still mainly performed manually by human workers due to their complexity, which is the case of surface treatment operations (such as sanding, deburring, finishing, grinding, polishing, etc.) used to repair defects. This work develops an advanced teleoperation and control system for industrial robots in order to assist the human operator to perform the mentioned tasks. On the one hand, the controlled robotic system provides strength and accuracy, holding the tool, keeping the right tool orientation and guaranteeing a smooth approach to the workpiece. On the other hand, the advanced teleoperation provides security and comfort to the user when performing the task. In particular, the proposed teleoperation uses augmented virtuality (i.e., a virtual world that includes non-modeled real-world data) and haptic feedback to provide the user an immersive virtual experience when remotely teleoperating the tool of the robot system to treat arbitrary regions of the workpiece surface. The method is illustrated with a car body surface treatment operation, although it can be easily extended to other surface treatment applications or even to other industrial tasks where the human operator may benefit from robotic assistance. The effectiveness of the proposed approach is shown with several experiments using a 6R robotic arm. Moreover, a comparison of the performance obtained manually by an expert and that obtained with the proposed method has also been conducted in order to show the suitability of the proposed approach.     

Classifiers sensitive to external context – theory and applications to video sequences

An external context like weather conditions, lighting, etc. influences classification results, but it is frequently omitted in a mathematical model of the problem at hand. Our aim is to propose a mathematical model, which extends the Bayesian problem of pattern recognition by incorporating external context variables. They are implanted as functions, which influence parameters of class distributions. We prove that context variables influence a shape or a position of the optimal class separating surface, without enlarging the dimensionality of a pattern space. Thus, one can treat the proposed extended Bayesian model as a fusion of patterns and external context variables, embedded into the same pattern space. Then, learning algorithms for neural network classifiers are proposed, which take context variables into account.     

Flexible telemanipulation based handy robot teaching on tape masking with complex geometry

Traditional robot teaching methods are cumbersome, tedious and difficult to scale for high-mix low-volume applications. The tape masking, a common process for surface protection before plasma spraying, spray painting and shot peening, is one of those domains where robotic automation lacks flexibility and reliability due to the complexity in task. Fortunately, it is still within the grasps of human-robot collaborative systems. This work presents a telemanipulation-based robot teaching framework that is able to let the robot manipulator cope with the taping tasks with complex workpiece geometries. The proposed framework allows quick calibration, variable motion mapping, and indexing so that the operators can easily set up and guide the robotic taping system to cover the tapes onto the layers and grooves of different workpieces. This framework enables the operators to change the motion mapping scale for both large-scale guidance and fine motion dexterous manipulation. Meanwhile, an indexing function makes it possible for the operators to re-map their poses from the edges of their comfortable regions. A portable VR system is applied in the telemanipulation system. With its six DoF motion precisely measured in real-time, the proposed motion remapping algorithms enable the operators to directly guide the robot in their selected scales. Experimental results show that the proposed framework facilitates robot programming on the manipulation of the complex workpieces that have multi-layer surfaces and grooves in between. It also reduces the teaching time comparing to other methods. This system and method improve teaching efficiency and convenience, which has potential value to be deployed in manufacturing.