Boyko Iliev

Demonstration-based learning and control for automatic grasping

We present a method for automatic grasp generation based on object shape primitives in a Programming by Demonstration framework. The system first recognizes the grasp performed by a demonstrator as well as the object it is applied on and then generates a suitable grasping strategy on the robot. We start by presenting how to model and learn grasps and map them to robot hands. We continue by performing dynamic simulation of the grasp execution with a focus on grasping objects whose pose is not perfectly known.

A fuzzy technique for food- and water quality assessment with an electronic tongue

The problem of food- and water quality assessment is important for many practical applications, such as food industry and environmental monitoring. In this article we present a method for fast online quality assessment based on electronic tongue measurements. The idea is implemented in two steps. First we apply a fuzzy clustering technique to obtain prototypes corresponding to good and bad quality from a set of training data. During the second, online step we evaluate the membership of the current measurement to each cluster and make a decision about its quality. The result is presented to the user in a simple and understandable way, similar to the concept of traffic light signals. Namely, good quality is indicated with by a green light, bad quality with a red one, and a yellow light is a warning signal. The approach is demonstrated in two case studies: quality assessment of drinking water and baby food.

Recognition of human grasps by time-clustering and fuzzy modeling

In this paper, we address the problem of recognition of human grasps for five-fingered robotic hands and industrial robots in the context of programming-by-demonstration. The robot is instructed by a human operator wearing a data glove capturing the hand poses. For a number of human grasps, the corresponding fingertip trajectories are modeled in time and space by fuzzy clustering and Takagi-Sugeno (TS) modeling. This so-called time-clustering leads to grasp models using time as an input parameter and fingertip positions as outputs. For a sequence of grasps, the control system of the robot hand identifies the grasp segments, classifies the grasps and generates the sequence of grasps shown before. For this purpose, each grasp is correlated with a training sequence. By means of a hybrid fuzzy model, the demonstrated grasp sequence can be reconstructed.

On the efficient computation of independent contact regions for force closure grasps

Since the introduction of independent contact regions in order to compensate for shortcomings in the positioning accuracy of robotic hands, alternative methods for their generation have been proposed. Due to the fact that (in general) such regions are not unique, the computation methods used usually reflect the envisioned application and/or underlying assumptions made. This paper introduces a parallelizable algorithm for the efficient computation of independent contact regions, under the assumption that a user input in the form of initial guess for the grasping points is readily available. The proposed approach works on discretized 3D-objects with any number of contacts and can be used with any of the following models: frictionless point contact, point contact with friction and soft finger contact. An example of the computation of independent contact regions comprising a non-trivial task wrench space is given.

Programming by Demonstration of Pick-and-Place Tasks for Industrial Manipulators using Task Primitives

This article presents an approach to Programming by Demonstration (PbD) to simplify programming of industrial manipulators. By using a set of task primitives for a known task type, the demonstration is interpreted and a manipulator program is automatically generated. A pick-and-place task is analyzed, based on the velocity profile, and decomposed in task primitives. Task primitives are basic actions of the robot/gripper, which can be executed in a sequence to form a complete a task. For modeling and generation of the demonstrated trajectory, fuzzy time clustering is used, resulting in smooth and accurate motions. To illustrate our approach, we carried out our experiments on a real industrial manipulator.

Programming-by-Demonstration of reaching motions-A next-state-planner approach

This paper presents a novel approach to skill acquisition from human demonstration. A robot manipulator with a morphology which is very different from the human arm simply cannot copy a human motion, but has to execute its own version of the skill. When a skill once has been acquired the robot must also be able to generalize to other similar skills, without a new learning process. By using a motion planner that operates in an object-related world frame called hand-state, we show that this representation simplifies skill reconstruction and preserves the essential parts of the skill.

Learning of Grasp Behaviors for an Artificial Hand by Time Clustering and Takagi-Sugeno Modeling

The focus of the paper is the learning of grasp primitives for a five-Angered anthropomorphic robotic hand via teaching-by-demonstration and fuzzy modeling. In this approach, a number of basic grasps is demonstrated by a human operator wearing a data glove which continuously captures the hand pose. The resulting fingertip trajectories and joint angles are clustered and modeled in time and space so that the motions of the fingers forming a particular grasp are modeled in a most effective and compact way. Classification and learning are based on fuzzy clustering and Takagi Sugeno (TS) modeling. The presented method allows to learn, imitate and recognize the motion sequences forming specific grasps.

Segmentation and Recognition of Human Grasps for Programming-by-Demonstration using Time-clustering and Fuzzy Modeling

In this article we address the problem of programming by demonstration (PbD) of grasping tasks for a five-fingered robotic hand. The robot is instructed by a human operator wearing a data glove capturing the hand poses. For a number of human grasps, the corresponding fingertip trajectories are modeled in time and space by fuzzy clustering and Takagi-Sugeno modeling. This so-called time-clustering leads to grasp models using the time as input parameter and the fingertip positions as outputs. For a test sequence of grasps the control system of the robot hand identifies the grasp segments, classifies the grasps and generates the sequence of grasps shown before. For this purpose, each grasp is correlated with a training sequence. By means of a hybrid fuzzy model the demonstrated grasp sequence can be reconstructed.

Grasp recognition by time-clustering, fuzzy modeling, and Hidden Markov Models (HMM) - a comparative study

This paper deals with three different methods for grasp recognition for a human hand. Grasp recognition is a major part of the approach for programming-by-demonstration (PbD) for five-fingered robotic hands. A human operator instructs the robot to perform different grasps wearing a data glove. For a number of human grasps, the finger joint angle trajectories are recorded and modeled by fuzzy clustering and Takagi-Sugeno modeling. This leads to grasp models using the time as input parameter and the joint angles as outputs. Given a test grasp by the human operator the robot classifies and recognizes the grasp and generates the corresponding robot grasp. Three methods for grasp recognition are presented and compared. In the first method the test grasp is compared with model grasps using the difference between the model outputs. In the second one, qualitative fuzzy models are used for recognition and classification. The third method is based on hidden-Markov-models (HMM) which are commonly used in robot learning.

Fuzzy gain scheduling for flight control

This paper presents a method for design of fuzzy gain scheduled output feedback H/sub /spl infin// controllers for affine Takagi-Sugeno (TS) systems. The method relies on recent developments in design for classical gain scheduling, based on linear matrix inequalities. It is shown how the previous results can be extended to general nonlinear systems that admits a TS fuzzy system approximation. The design method is demonstrated on a nonlinear missile model.