Alle Publikationen
- <<
- <
- 1
2017
-
(2017): Building Multiversal Semantic Maps for Mobile Robot Operation. In: KNOWLEDGE-BASED SYSTEMS 119, S. 257-272. DOI: 10.1016/j.knosys.2016.12.016
DOI: https://doi.org/10.1016/j.knosys.2016.12.016 Abstract: Semantic maps augment metric-topological maps with meta-information, i.e. l semantic knowledge aimed at the planning and execution of high-level robotic tasks. Semantic knowledge typically encodes human-like concepts, like types of objects and rooms, which are connected to sensory data when symbolic representations of percepts from the robot workspace are grounded to those concepts. Such a symbol grounding is usually carried out by algorithms that individually categorize each symbol and provide a crispy outcome – a symbol is either a member of a category or not. Such approach is valid for a variety of tasks, but it fails at: (i) dealing with the uncertainty inherent to the grounding process, and (ii) jointly exploiting the contextual relations among concepts (e.g. microwaves are usually in kitchens). This work provides a solution for probabilistic symbol grounding that overcomes these limitations. Concretely, we rely on Conditional Random Fields (CRFs) to model and exploit contextual relations, and to provide measurements about the uncertainty coming from the possible groundings in the form of beliefs (e.g. an object can be categorized (grounded) as a microwave or as a nightstand with beliefs 0.6 and 0.4, respectively). Our solution is integrated into a novel semantic map representation called Multiversal Semantic Map (MvSmap), which keeps the sets of different groundings, or universes, as instances of ontologies annotated with the obtained beliefs for their posterior exploitation. The suitability of our proposal has been proven with the Robot@Home dataset, a repository that contains challenging multi-modal sensory information gathered by a mobile robot in home environments. (PsycINFO Database Record (c) 2017 APA, all rights reserved)
2016
-
(2016): Anticipating Human Activities Using Object Affordances for Reactive Robotic Response. In: IEEE transactions on pattern analysis and machine intelligence 38 (1), S. 14-29. DOI: 10.1109/TPAMI.2015.2430335
DOI: http://www.ncbi.nlm.nih.gov/pubmed/26656575 Abstract: An important aspect of human perception is anticipation, which we use extensively in our day-to-day activities when interacting with other humans as well as with our surroundings. Anticipating which activities will a human do next (and how) can enable an assistive robot to plan ahead for reactive responses. Furthermore, anticipation can even improve the detection accuracy of past activities. The challenge, however, is two-fold: We need to capture the rich context for modeling the activities and object affordances, and we need to anticipate the distribution over a large space of future human activities. In this work, we represent each possible future using an anticipatory temporal conditional random field (ATCRF) that models the rich spatial-temporal relations through object affordances. We then consider each ATCRF as a particle and represent the distribution over the potential futures using a set of particles. In extensive evaluation on CAD-120 human activity RGB-D dataset, we first show that anticipation improves the state-of-the-art detection results. We then show that for new subjects (not seen in the training set), we obtain an activity anticipation accuracy (defined as whether one of top three predictions actually happened) of 84.1, 74.4 and 62.2 percent for an anticipation time of 1, 3 and 10 seconds respectively. Finally, we also show a robot using our algorithm for performing a few reactive responses.
Keywords: Affordance, affordances, Affordanz, Algorithms, Aniticipation, Human Activities, Humans, Imaging, Intentionserkennung (Roboter erkennt Menschenintention), J. J. Gibson's theory of affordance, machine learning, MODELS, Movement, PERCEPTION, Psychological, Robotics, Soziosensitive Systeme, Soziosensitivität, Statistical, Three-Dimensional, Video Recording 2015
-
(2015): Political science. Exposure to ideologically diverse news and opinion on Facebook. In: Science (New York, N.Y.) 348 (6239), S. 1130-1132. DOI: 10.1126/science.aaa1160
DOI: http://www.ncbi.nlm.nih.gov/pubmed/25953820 Abstract: Exposure to news, opinion, and civic information increasingly occurs through social media. How do these online networks influence exposure to perspectives that cut across ideological lines? Using deidentified data, we examined how 10.1 million U.S. Facebook users interact with socially shared news. We directly measured ideological homophily in friend networks and examined the extent to which heterogeneous friends could potentially expose individuals to cross-cutting content. We then quantified the extent to which individuals encounter comparatively more or less diverse content while interacting via Facebook's algorithmically ranked News Feed and further studied users' choices to click through to ideologically discordant content. Compared with algorithmic ranking, individuals' choices played a stronger role in limiting exposure to cross-cutting content.
-
(2015): From honeybees to robots and back. Division of labour based on partitioning social inhibition. In: Bioinspiration & biomimetics 10 (6). DOI: 10.1088/1748-3190/10/6/066005
DOI: http://www.ncbi.nlm.nih.gov/pubmed/26501169 Abstract: In this paper, a distributed adaptive partitioning algorithm inspired by division of labor in honeybees is investigated for its applicability in a swarm of underwater robots in one hand and is qualitatively compared with the behavior of honeybee colonies on the other hand. The algorithm, partitioning social inhibition (PSI), is based on local interactions and uses a simple logic inspired from age-polyethism and task allocation in honeybee colonies. The algorithm is analyzed in simulation and is successfully applied here to partition a swarm of underwater robots into groups demonstrating its adaptivity to changes and applicability in real world systems. In a turn towards the inspiration origins of the algorithm, three honeybee colonies are then studied for age-polyethism behaviors and the results are contrasted with a simulated swarm running the PSI algorithm. Similar effects are detected in both the biological and simulated swarms suggesting biological plausibility of the mechanisms employed by the artificial system.
Keywords: Algorithms, Animal Machine, Animals, Bees/physiology, Behavior, Animal/physiology, Biomimetics/instrumentation/methods, Cooperative Behavior, Equipment Design, Equipment Failure Analysis, Feeding Behavior/physiology, Inhibition (Psychology), interdisziplinär, Partitioning Social Inhibition (PSI), Robotics/instrumentation/methods, Social Behavior 2014
-
(2014): Learning Compliant Manipulation through Kinesthetic and Tactile Human-Robot Interaction. In: IEEE Transactions on Haptics 7 (3), S. 367-380. DOI: 10.1109/TOH.2013.54
DOI: https://doi.org/10.1109/TOH.2013.54 Abstract: Robot Learning from Demonstration (RLfD) has been identified as a key element for making robots useful in daily lives. A wide range of techniques has been proposed for deriving a task model from a set of demonstrations of the task. Most previous works use learning to model the kinematics of the task, and for autonomous execution the robot then relies on a stiff position controller. While many tasks can and have been learned this way, there are tasks in which controlling the position alone is insufficient to achieve the goals of the task. These are typically tasks that involve contact or require a specific response to physical perturbations. The question of how to adjust the compliance to suit the need of the task has not yet been fully treated in Robot Learning from Demonstration. In this paper, we address this issue and present interfaces that allow a human teacher to indicate compliance variations by physically interacting with the robot during task execution. We validate our approach in two different experiments on the 7 DoF Barrett WAM and KUKA LWR robot manipulators. Furthermore, we conduct a user study to evaluate the usability of our approach from a non-roboticists perspective.
Keywords: Algorithms, Analysis, Bedienung & Handhabung, Biomechanical Phenomena, compliance control, compliance variations, compliant control, compliant manipulation, Computer Simulation, education, Force, haptic feedback, haptic interfaces, human-robot interaction, Humans, Impedance, Joints, Kinesthesis, kinesthetic human-robot interaction, KUKA LWR robot manipulators, Learning, manipulator kinematics, Physical Human-Robot Interaction, position control, RLfD, Robot kinematics, robot learning from demonstration, Robot sensing systems, Robotics, stiff position controller, tactile human-robot interaction, tactile interfaces, task kinematics, task model, Task Performance, Touch -
(2014): Towards robust task execution for domestic service robots. In: Journal of Intelligent & Robotic Systems 76 (1), S. 5-33. DOI: 10.1007/s10846-013-0005-6
DOI: https://doi.org/10.1007/s10846-013-0005-6 Abstract: In the field of domestic service robots, recovery from faults is crucial to promote user acceptance. In this context we will focus, in particular, on some specific faults which arise from interaction of the robot with its real world environment. In these situations even a well modelled robot may fail to perform its tasks successfully due to external faults which occur while interacting. We reason along the most frequent failures in typical scenarios which we have observed in real-world demonstrations and competitions using the autonomous service robot Jenny. We propose four different fault classes caused by disturbances, imperfect perception, inadequate planning or chaining of action sequences. The faults are first classified and then mapped to a small number of fault handling techniques partly known, partly extended by us. In addition to existing techniques we present two approaches to handle external faults from inadequate descriptions of the planner operator class. The first approach uses naive physics concepts to find information about detected external faults. The second approach is simulation based, utilising a single simulation that shows a manipulated object’s behaviour for successfully completing an action. The approach uses the N-Bins learning algorithm to suggest a releasing state of the object that avoids the occurrence of external faults. We apply the proposed approaches to the scenarios where a robot performs the pick-and-place manipulation tasks. The results of these applications show that both approaches hold great promises for handling external faults in domestic service robotics. (PsycINFO Database Record (c) 2016 APA, all rights reserved)
2012
-
(2012): Towards building intelligent speech interfaces through the use of more flexible, robust and natural dialogue management solutions. In: Interacting with Computers 24 (6), S. 482-498. DOI: 10.1016/j.intcom.2012.09.003
DOI: https://doi.org/10.1016/j.intcom.2012.09.003 Abstract: In this paper a Bayesian Networks-based solution for dialogue modelling is presented. This solution is combined with carefully designed contextual information handling strategies. With the purpose of validating these solutions, and introducing a spoken dialogue system for controlling a Hi-Fi audio system as the selected prototype, a real-user evaluation has been conducted. Two different versions of the prototype are compared. Each version corresponds to a different implementation of the algorithm for the management of the actuation order, the algorithm for deciding the proper order to carry out the actions required by the user. The evaluation is carried out in terms of a battery of both subjective and objective metrics collected from speakers interacting with the Hi-Fi audio box through predefined scenarios. Defined metrics have been specifically adapted to measure: first, the usefulness and the actual relevance of the proposed solutions, and, secondly, their joint performance through their intelligent combination mainly measured as the level achieved with regard to the user satisfaction. A thorough and comprehensive study of the main differences between both approaches is presented. Two-way analysis of variance (ANOVA) tests are also included to measure the effects of both: the system used and the type of scenario factors, simultaneously. Finally, the effect of bringing this flexibility, robustness and naturalness into our home dialogue system is also analyzed through the results obtained. These results show that the intelligence of our speech interface has been well perceived, highlighting its excellent ease of use and its good acceptance by users, therefore validating the approached dialogue management solutions and demonstrating that a more natural, flexible and robust dialogue is possible thanks to them. (PsycINFO Database Record (c) 2016 APA, all rights reserved)
-
(2012): TripleR: An R package for social relations analyses based on round-robin designs. In: Behavior research methods 44 (2), S. 455-470. DOI: 10.3758/s13428-011-0150-4
DOI: https://doi.org/10.3758/s13428-011-0150-4 Abstract: In this article, we present TripleR, an R package for the calculation of social relations analyses (Kenny, 1994) based on round-robin designs. The scope of existing software solutions is ported to R and enhanced with previously unimplemented methods of significance testing in single groups (Lashley & Bond, 1997) and handling of missing values. The package requires only minimal knowledge of R, and results can be exported for subsequent analyses to other software packages. We demonstrate the use of TripleR with several didactic examples.
Keywords: Algorithms, Analysis of Variance, Data Interpretation, Statistical, Group Structure, Humans, Interpersonal Relations, Longitudinal Studies, Models, Psychological, Models, Statistical, Psychology, Social/methods/statistics & numerical data, Research Design, Social Behavior, Social Perception, Software 2007
-
(2007): An engineering approach to sociable robots. In: Journal of Experimental & Theoretical Artificial Intelligence 19 (4), S. 285-306. DOI: 10.1080/09528130701208174
DOI: https://doi.org/10.1080/09528130701208174 Abstract: Robotics researchers and cognitive scientists are becoming more and more interested in so-called sociable robots. These machines normally have expressive power (facial features, voice,...) as well as abilities for locating, paying attention to, and addressing people. The design objective is to make robots which are able to sustain natural interactions with people. This capacity falls within the range classed as social intelligence in humans. This position paper argues that the reproduction of social intelligence, as opposed to other types of human ability, may lead to fragile performance, in the sense that tested cases may produce rather different performances to future (untested) cases and situations. This limitation stems from the fact that our social abilities, which appear early in life, are mainly unconscious in origin. This is in contrast with other human abilities that we carry out using conscious effort, and for which we can easily conceive algorithms and representations. This novel perspective is deemed useful for defining the obstacles and limitations of a field that is generating increasing interest. Taking into account the mentioned issues, a development approach suited to the problem is proposed. The use of this approach is demonstrated in the development of CASIMIRO, a robotic head with basic interaction abilities. (PsycINFO Database Record (c) 2016 APA, all rights reserved)
2005
-
(2005): Intelligent and Efficient Strategy for Unstructured Environment Sensing Using Mobile Robot Agents. In: Journal of Intelligent & Robotic Systems 43 (2-4), S. 217-253. DOI: 10.1007/s10846-004-3063-y
DOI: https://doi.org/10.1007/s10846-004-3063-y Abstract: In field environments it is not usually possible to provide robots in advance with valid geometric models of its task and environment. The robot or robot teams need to create these models by scanning the environment with its sensors. Here, an information-based iterative algorithm to plan the robot’s visual exploration strategy is proposed to enable it to most efficiently build 3D models of its environment and task. The method assumes mobile robot (or vehicle) with vision sensors mounted at a manipulator end-effector (eye-in-hand system). This algorithm efficiently repositions the systems’ sensing agents using an information theoretic approach and fuses sensory information using physical models to yield a geometrically consistent environment map. This is achieved by utilizing a metric derived from Shannon’s information theory to determine optimal sensing poses for the agent(s) mapping a highly unstructured environment, This map is then distributed among the agents using an information-based relevant data reduction scheme, This method is particularly well suited to unstructured environments, where sensor uncertainty is significant. Issues addressed include model-based multiple sensor data fusion, and uncertainty and vehicle suspension motion compensation. Simulation results show the effectiveness of this algorithm. (PsycINFO Database Record (c) 2016 APA, all rights reserved)
2004
-
(2004): Models of social networks based on social distance attachment. In: Physical review. E, Statistical, nonlinear, and soft matter physics 70 (5 Pt 2). DOI: 10.1103/PhysRevE.70.056122
DOI: http://www.ncbi.nlm.nih.gov/pubmed/15600707 Abstract: We propose a class of models of social network formation based on a mathematical abstraction of the concept of social distance. Social distance attachment is represented by the tendency of peers to establish acquaintances via a decreasing function of the relative distance in a representative social space. We derive analytical results (corroborated by extensive numerical simulations), showing that the model reproduces the main statistical characteristics of real social networks: large clustering coefficient, positive degree correlations, and the emergence of a hierarchy of communities. The model is confronted with the social network formed by people that shares confidential information using the Pretty Good Privacy (PGP) encryption algorithm, the so-called web of trust of PGP.
Keywords: Algorithms, Computer Simulation, degree of acquaintance, Disziplin, Favoriten, Gruppenverhalten / Joint Action, Hierarchy, Social, Interpersonal Relations, Modelle/Theorien, Models, Biological, Netzwerktheorien, Population Dynamics, Residence Characteristics, Social Behavior, Social Change, Social Distance, social networks based on social distance, Social Support, Soziale Angemessenheit, Soziale Distanz, Soziologie, SV 1997
-
(1997) : The modularity of social intelligence In: Whiten, Andrew; Byrne, Richard W. (Hg.): Machiavellian intelligence II. Extensions and evaluations: Cambridge: Cambridge University Press, S. 264-288
Abstract: Argues that the social intelligence hypothesis, while stimulating and exciting, is vague and imprecise, and that some of its propositions are empirically empty and should be dropped. A "modular" version of the social intelligence hypothesis is proposed, which offers a specific theory about the mechanisms of social intelligence. Assumptions of this hypothesis are discussed in detail and an example of an experimental test of the resulting predictions illustrates that the hypothesis produces testable predictions and can explain apparently contradictory data previously considered irrational. It is argued that the investigation of social intelligence should be driven by theory and empirically tested and that the modular version outlined offers a starting point.
- <<
- <
- 1