10 search hits
-
Intuitive Human-Robot Interaction by Intention Recognition
(2013)
-
Muhammad Awais
- For two humans to interact with each other to perform a common task, they need to know the expectation of each other during interaction. For example if we consider an example of a waiter and a guest. If the waiter tilts the bottle to offer a drink to the guest then he may expect two actions from the guest, i.e., either the guest will forward his glass to get it filled or he will take his glass backward for not accepting the drink. If the guest forwards his glass then the waiter expects that the guest will keep his glass at a certain point until he pours the liquid into the glass. Similarly if the guest takes its glass backward then he expects from the waiter not to pour the liquid into his glass. In any case of misunderstanding an accident can occur. It applies to almost all the instances of human-human interaction. The recognition of the intention plays a key role in human-human interaction. It is equally important in human-robot interaction.
With the increase of research in the field of robotics, the robots are and will be becoming more and more part of human life. For the robots to be the effective part of the human life they should be helpful to the human. For a robot to be helpful to the human he should act according to the human. In case if the robot tries to help the human without knowing the intention of the interacting human then the robot can be itself a problem rather than a solution to the problems. Therefore it is necessary for a robot to know the intention of the human with whom the robot is supposed to interact to facilitate him.
The aim of this work is to propose a solution to make the human robot interaction intuitive. For making the human-robot interaction intuitive the intention of the human should be known to the interacting robot. A probabilistic approach is introduced to recognize the human intention. The approach uses the finite state machines. Each finite state machine representing a unique human intention carries a probabilistic value that is called the weight of the finite state machine. That weight tells the robot about the current human intention.
Since it is not possible to embed all the possible intentions into the robot that the robot may need to recognize. Thus, there should be a measure that the robot can learn new human intentions. An approach is discussed for this purpose.
For the human-robot interaction to be intelligent the robot should be quick in his response towards the human intention. An approach is described that addresses the issue of quick (proactive) response of the robot. The proposed approach also discusses the scenario concerning the ambiguous human intention. An ambiguous intention is a human intention that apparently corresponds to more than one human intention.
There may be a scenario in which the human has a totally new intention that the robot does not know already and also has not learned that intention. In this case, apparently there is no human- robot interaction. In order to cope with this problem an approach is discussed that enables the robot to select an appropriate action to interact with the human.
An approach concerning the generalization of the human intention is also discussed. By generalizing the human intention, the robot can extend its response according to the human intention. The extension of the response means that the robot takes those actions that were not instructed to him to be taken concerning the human intention.
-
Navigation with Local Sensors in Surgical Robotics
(2011)
-
Philipp J. Stolka
- Using robots in medicine and especially in surgery requires an adequate representation of and reaction to a changing environment. This is usually achieved by modeling the environment at different representation levels throughout the process, ranging from complex 3D imaging modalities which reflect the environment geometry to finding appropriate low-level control parameters for actual motion through environment regions. In this work, a common framework for different types of navigational problems in surgical robotics is proposed, and validated by the introduction of navigation cycles on novel local sensors. Currently industrial (and surgical) robotic systems employ almost exclusively static global maps -- if any -- for navigation and planning purposes. Additional information -- intra-process, spatial, current, and persistent sensor data -- is useful to cope with uncertainty, measurement errors, and incompleteness of data. Between global pre-operative navigation and control, this work introduces the concept of intra-operative navigation on local sensor data into surgical robotics. This includes the creation and maintenance (both concurrent as well as independent) of local environment maps for navigation purposes. This intermediate level of sensory feedback and processing allows to react to changes in the environment, based on persistent but incremental mapping. Furthermore, local sensors permit intra-operative sampling of additional information which may be unattainable before process execution, or available only with reduced precision. This work proposes to augment robot world models by introducing such local sensors (in particular, force and sound as well as ultrasonic sensors, all of which provide data from an estimated local epsilon-environment) and to build precise maps from local sensors, which serve as input for several introduced navigation algorithms. This map-building is improved by precise data localisation and precise data insertion. The general idea of nested control loops is illustrated on the basis of a specific surgical application -- robot-based milling at the lateral skull base.
-
Agent Assignment for Process Management: Resource Management Support for Skill Intensive Applications of Workflow Technology Technical and Methodological Issues
(2011)
-
Muhammad Ramzan Talib
- Managing an organization’s resource talent particularly in assigning the right person to the right job at the right time is among the top challenges of today’s competitive business environments especially in skill intensive applications of workflow technology since skills of their employees directly affect the business paybacks. Despite that many companies already deal with managing their processes and their human resources, organizations are still feeling the problem of poor resource management. The dilemma is that Workflow Management Systems (WfMSs) support the execution of business process but do only offer static assignment strategies for resources such that an overall poor process performance results. Furthermore, Human Resource Management (HRM) performance evaluation methods lack agility and analytical capabilities that results in poor resource development. To solve this dilemma of poor resource management, this thesis contributes some technical and methodological supports considering some use case scenarios from a textile industry. It offers Agent Performance Evaluation (APE) Framework and Competency-driven Dynamic Resource Management (CDRM) Methodology to overcome the problem of static assignments and also to support proper resource development. Our APE framework not only evaluates and gives feedbacks of employees’ competency profiles but also performs an analysis of employees’ competencies for making best use of their talents thus supporting proper resource development. While, our CDRM methodology allocates dynamically only successful employees to their business processes through consistent support of APE framework and thus supports process optimization. This thesis also contributes a construct in the form of Goal concept and a methodology for continuous resource development in the form of Workflow Lifecycle Support for Continuous Resource Improvement. Defining goals within the process layer, enables organizations to define success criteria of their employees in parallel with all other criteria that influence the performance of an employee within the process. In fact, our APE Framework uses this criteria for evaluating the employees’ competency profiles that are latter used by CDRM methodology to allocate only successful employees to their business processes. The Workflow Lifecycle Support for Continuous Resource Improvement aims to define a precise and comprehensive methodology to elaborate a set of basic tasks that are needed to be performed during different phases of the standard workflow lifecycle to achieve continuous resource improvement.
-
Structuring Descriptive Data of Organisms — Requirement Analysis and Information Models
(2007)
-
Gregor Hagedorn
- Data that describe organisms in a structured form are indispensable not only for taxonomic and identification purposes, but also many phylogenetic, genetic, or ecological analyses. By analyzing existing information models and performing selected fundamental requirement analyses, the present work contributes to a broadening of the understanding of these forms of data. It falls into an interdisciplinary area between biology and information science. The term “descriptive data” is understood here in a broad sense: As descriptions of individuals, populations, or taxa, intended for various purposes (e. g., genetic, phylogenetic, diagnostic, taxonomic, or ecological), and covering a wide array of observation methods and data types (e. g., morphological, anatomical, genetic, physiological, molecular, or behavioral data). The position of descriptive data in the context of biodiversity framework concepts (covering, e. g., nomenclatural data, specimen collection data, or resource management) is discussed. A number of fundamental problems arise when modeling biological descriptive data. The ways in which existing data exchange formats, information models, and software applications address them are studied and future possible solutions are outlined. One such solution, the information model for the software “DiversityDescriptions (DeltaAccess)” is one of the results of this thesis and fully documented (Ch. 7). This entity relationship model fully supports the concepts of the traditional DELTA data exchange format (Description Language for Taxonomy; TDWG standard since 1986). If further improves on DELTA by introducing “modifiers” as a new terminology class, by introducing a more flexible system of handling statistical measures, by improving the handling of multilingual data sets, by supporting subset and filter features for concurrent collaborative editing (instead of supporting these for report-generation purposes alone), by supporting improved character attributes to create natural language descriptions from structured descriptions, and by adding metadata for a data set to improve the ability of data exchange without external documentation. In preparation of a future improved information model for descriptive data, the results of three requirement analyses are presented: a data-centric analysis of general concepts, a process-centric analysis of identification tools, and a high-level use case analysis. The first analysis (Ch. 4) is a structured inventory of fundamental approaches and problems involved in collecting and summarizing scientific descriptions of organisms. It is informed in part by current practices in information science, comparative data analysis, statistical, descriptive or phylogenetic software applications, and data exchange formats in biodiversity informatics. At the end three topics are discussed in particular detail (“Federation and modularization of terminology”, “Modifiers”, and “Secondary classification resulting in description scopes”). Except for phylogenetic analyses, identification is the most common usage of descriptive data. The second analysis (Ch. 5) therefore studies the processes, data structures, presentational and user interface requirements for printable and computer-aided identification tools (“keys”). Finally, a general use case analysis is performed with the goal of creating a framework of high-level use cases into which present as well as future requirements may be integrated (Ch. 6). All three requirement analyses are explorative and do not fulfill formal criteria of software engineering. They identify many requirements not addressed by the relational DiversityDescriptions model. Some of these could only be explored and await future solutions. For others solutions are proposed (some of which could already be incorporated into the design of SDD, an xml-based TDWG standard since 2005): The traditional data types are changed into an extensible character type model. The importance of data aggregation concepts was recognized to be fundamental. Complementary to data aggregation, the present and potentially future use of data inheritance along the lines of the taxonomic hierarchy is briefly studied. The concept of calculated characters could be addressed only insofar as the mapping between values can potentially be generalized. Character decomposition models are studied, but ultimately the traditional character concept, supplemented with a forest of ontologies for compositional and generalization concept hierarchies, is preferred as a more general concept. Both the traditional character subset and character applicability models can be integrated into concept hierarchies.
-
Parallel Low-Storage Runge-Kutta Solvers for ODE Systems with Limited Access Distance
(2010)
-
Matthias Korch
Thomas Rauber
- We consider the solution of initial value problems (IVPs) of large systems of ordinary differential equations (ODEs) for which memory space requirements determine the choice of the integration method. In particular, we discuss the space-efficient sequential and parallel implementation of embedded Runge-Kutta (RK) methods. We focus on the exploitation of a special structure of commonly appearing ODE systems, referred to as "limited access distance", to improve scalability and memory usage. Such systems may arise, for example, from the semi-discretization of partial differential equations (PDEs). The storage space required by classical RK methods is directly proportional to the dimension n of the ODE system and the number of stages s of the method. We propose an implementation strategy based on a pipelined processing of the stages of the RK method and show how the memory usage of this computation scheme can be reduced to less than three storage registers by an overlapping of vectors without compromising the choice of method coefficients or the potential for efficient stepsize control. We analyze and compare the scalability of different parallel implementation strategies in detailed runtime experiments on different parallel architectures.
-
Multi-View Reconstruction in-between Known Environments
(2010)
-
Stefan Kuhn
Dominik Henrich
- We present a novel multi-view 3D reconstruction algorithm which unifies the advantages of several recent reconstruction approaches. Based on a known environment causing occlusions and on the cameras pixel grid discretization, an irregular partitioning of the reconstruction space is chosen. Reconstruction artifacts are rejected by using plausibility checks based on additional information about the objects to be reconstructed. The binary occupancy decision is solely performed in reconstruction space instead of fusing back-projected silhouettes in image space. Hierarchical data structures are used to reconstruct the objects progressively focusing on boundary regions. Thus, the algorithm can be stopped at any time with a certain conservative level of detail. Most parts of the algorithm may be processed in parallel using GPU programming techniques. The main application domain is the surveillance of real environments like in human/robot coexistence and cooperation scenarios.
-
Multi-View Reconstruction of Unknown Objects in the Presence of Known Occlusions
(2009)
-
Stefan Kuhn
Dominik Henrich
- We present a general method for reconstructing unknown objects (e.g. humans) within a known environment (e.g. tables, racks, robots) which usually has occlusions. These occlusions have to be considered since parts of the unknown objects might be hidden in some or even all camera views. Besides grayscale and color cameras also depth sensors are considered. In order to avoid cluttered reconstructions, plausibility checks are used to eliminate reconstruction artifacts which actually do not contain any unknown object. One application is a supervision/surveillance system for safe human/robot-coexistence and –cooperation. Experiments for a voxel-based implementation are given.
-
Integral point sets over Z_n^m
(2007)
-
Axel Kohnert
Sascha Kurz
- There are many papers studying properties of point sets in the Euclidean space or on integer grids, with pairwise integral or rational distances. In this article we consider the distances or coordinates of the point sets which instead of being integers are elements of Z_n, and study the properties of the resulting combinatorial structures.
-
Symmetric functions in MAGMA
(2007)
-
Axel Kohnert
- We describe two algorithms which were used to implement symmetric functions in the computer algebra system MAGMA. We describe one algorithm based on the work of Lascoux and Schutzenberger for the multiplication. One further algorithm is given for the computation of plethysms.
-
Construction of Two-Weight Codes
(2005)
-
Axel Kohnert
- This is a talk given at the conference: Algebra and Computation 2005 in Tokyo. We describe a method for the construction of two-weight codes. This also allows to realize certain strongly regular graphs or equivalently certain point sets in the a finite projective geometry. We use the method of prescibed automorphisms, which allows us to reduce the problem to a size where we can use powerful Diophantine equation solvers provided by Alfred Wassermann.
