A Fuzzy Classifier for Tactile Sensing (original) (raw)
Related papers
A learning fuzzy decision tree and its application to tactile image
Proceedings. 1998 IEEE/RSJ International Conference on Intelligent Robots and Systems. Innovations in Theory, Practice and Applications (Cat. No.98CH36190)
Decision trees play important roles in many fields such as pattem recognition and classification. It is because they have simple, apparent and fast reasoning process. This paper develops an algorithm to generate a leaming fuzzy decision tree. This algorithm firstly collects enough training data for generating a practical decision tree. It then uses fuzzy statistics to calculate fuzzy sets for representing the training data in order to save computing memory and increase generation speed. Finally, this algorithm uses a sub-optimal criterion to leam a d e c p tree from the resultant fuzzy sets. The algorithm is applied to a general-purpose tactile force sensing system. This system uses fuzzy logic to interpolate the force data. Then, the proposed algorithm is used to generate the desired decision tree from the tactile data. Based on the decision tree, the objects can be on-line recognized precisely.
Computational Intelligence Techniques for Tactile Sensing Systems
Sensors, 2014
Tactile sensing helps robots interact with humans and objects effectively in real environments. Piezoelectric polymer sensors provide the functional building blocks of the robotic electronic skin, mainly thanks to their flexibility and suitability for detecting dynamic contact events and for recognizing the touch modality. The paper focuses on the ability of tactile sensing systems to support the challenging recognition of certain qualities/modalities of touch. The research applies novel computational intelligence techniques and a tensor-based approach for the classification of touch modalities; its main results consist in providing a procedure to enhance system generalization ability and architecture for multi-class recognition applications. An experimental campaign involving 70 participants using three different modalities in touching the upper surface of the sensor array was conducted, and confirmed the validity of the approach.
Classification of rigid and deformable objects using a novel tactile sensor
2011 15th International Conference on Advanced Robotics (ICAR), 2011
In this paper, we present a novel tactile-array sensor for use in robotic grippers based on flexible piezoresistive rubber. We start by describing the physical principles of piezoresistive materials, and continue by outlining how to build a flexible tactile-sensor array using conductive thread electrodes. A real-time acquisition system scans the data from the array which is then further processed. We validate the properties of the sensor in an application that classifies a number of household objects while performing a palpation procedure with a robotic gripper. Based on the haptic feedback, we classify various rigid and deformable objects. We represent the array of tactile information as a time series of features and use this as the input for a k-nearest neighbors classifier. Dynamic time warping is used to calculate the distances between different time series. The results from our novel tactile sensor are compared to results obtained from an experimental setup using a Weiss Robotics tactile sensor with similar characteristics. We conclude by exemplifying how the results of the classification can be used in different robotic applications.
Tactile-Data Classification of Contact Materials Using Computational Intelligence
IEEE Transactions on Robotics, 2000
The two major components of a robotic tactile sensing system are the tactile sensing hardware at the lower level, and the computational/software tools at the higher level. Focusing on the later, this research assesses the suitability of Computational Intelligence tools for tactile data processing. In this context, this paper addresses the classification of sensed object material from the recorded raw tactile data. For this purpose, three computational intelligence paradigms, namely, Support Vector Machine (SVM), Regularized Least Square (RLS) and Regularized Extreme Learning Machine (RELM) have been employed and their performance compared for the said task. The comparative analysis shows that SVM provides the best trade-off between classification accuracy and computational complexity of the classification algorithm. Experimental results indicate that the Computational Intelligence tools are effective in dealing with the challenging problem of material classification.
An approach to integrated tactile perception
Proceedings of International Conference on Robotics and Automation
This paper presents an integrated approach to tactile perception, both in terms of data acquisition and of data interpretation. In humans, touch sensing is implemented through a number of different sensing elements embedded in: the skin. The interpretation of perceived data to the level of detection of basic features, such as material, shape of surjface, shape of contact, is achieved by integrating the different sensorial inputs at a low level, with no involvement of high level cognitive processes. The approach we propose in this paper follows this anthropomorphic model of tactile perception, by including, on one hand, a miniature fingertip integrating different sensors and, on the other hand, a parallel data interpretation module, implemented through a fuzzy neural-network, which processes all the different inputs at the same level. The paper describes the characteristics of the integrated fingertip sensor and of the neuro-fuuy system, and discusses experimental results achieved during exploratory tasks on a set of common object are discussed in detail in the following.
Acquisition and Application of a Tactile Database
Proceedings 2007 IEEE International Conference on Robotics and Automation, 2007
We present a database of 2D pressure profile timeseries as a testbed for tactile object and surface recognition. The tactile database captures the surfaces of household and toy objects by moving a 2D pressure sensor mounted to an industrial robot arm around the objects using real-time trajectory calculation. Thus, it represents different "views" of the objects in a similar way as the well known Columbia Object Image Library (COIL) captures different views of an object by a camera. As a first application, objects in the database are classified using a neural network architecture.
Featureless classification of tactile contacts in a gripper using neural networks
Sensors and Actuators A: Physical, 1997
A direct, featureless process to classify contact impressions of objects gripped by a robot hand is presented. The inforlnation about the type of contact allows the selection of the most appropriate manipulating strategy to handle the grasped object. A learning vector quantization (LVQ) network is applied introducing a contact-pattern preprocessing technique to improve the robustness of tbe classification with respect to the pattern variations in position, orientation and size. © 1997 Elsevier Science S.A.
CONTACT RECOGNITION USING TACTILE SENSOR
ace.ucv.ro
The surface recognition algorithm that determines the types of contact surfaces by fusing information collected by the tactile sensor system is proposed. The tactile system will be determined from the shape of the object image which can then be characterized using the mathematical properties of Quadric surface. This algorithm can recognize 3-D objects using a 2-fingered robot gripper, on which tactile sensors are mounted. Experiments have demonstrated the reliability of the surface classification method and the accuracy of transformations independent of an object's shape, translation and rotation.
This paper proposes a new computationally fast algorithm for classifying the primitive shape and pose of the local contact area in real-time using a tactile array sensor attached on a robotic fingertip. The proposed approach abstracts the lower structural property of the tactile image by analyzing the covariance between pressure values and their locations on the sensor and identifies three orthogonal principal axes of the pressure distribution. Classifying contact shapes based on the principal axes allows the results to be invariant to the rotation of the contact shape. A naïve Bayes classifier is implemented to classify the shape and pose of the local contact shapes. Using an off-shelf low resolution tactile array sensor which comprises of 5×9 pressure elements, an overall accuracy of 97.5% has been achieved in classifying six primitive contact shapes. The proposed method is very computational efficient (total classifying time for a local contact shape = 576μs (1736 Hz)). The test results demonstrate that the proposed method is practical to be implemented on robotic hands equipped with tactile array sensors for conducting manipulation tasks where real-time classification is essential.
3D-Shape Recognition Based Tactile Sensor
Smart Sensors and Sensing …, 2008
The surface recognition algorithm that determines the types of contact surfaces by fusing information collected by the tactile sensor system are proposed. This algorithm can recognize 3-D objects using a 2-fingered robot hand, on which tactile sensors are mounted. Experiments demonstrate the reliability of the surface classification method and the accuracy of transformations independent of object shape, translation and rotation. Surface recognition is a more complicated task in tactile perception than in visual perception. This is because there are a number of additional factors which affect the quality of tactile images such as complex strain-stress relationships in elastic overlays, amount of force, and contact angle during the tactile perception process.