1,720,962 research outputs found
Controlling an autonomous agent using internal value based action selection
No full textIn this paper we describe an approach of controlling an autonomous robot by means of a hierarchical control structure, with a learning action selection. Since Damasio's 'Descartes' error' in 1994 the number of approaches to action selection that use internal values, derived from psychological models of emotions or drives has increased significantly. The approach realises a learning action selection mechanism in a hierarchy of sensory and actuatory layers. The sensory values yield the internal states, as a basis for action selection. In addition they are used to calculate the reinforcement signal that trains the action selection
Learning Hierarchical Action Selection for an Autonomous Robot
No full textIn this paper we describe an approach of controlling an autonomous robot by means of a hierarchical organised control structure. The realised action selection mechanism is capable of learning to switch between different modes of actions with respect to the internal state of the robot. We present an approach that realises a learning action selection mechanism in a hierarchy of sensory and actuator layers. The sensory values yield the internal states which serve as a basis for the action selection. In addition, the internal states are used to calculate the reinforcement signal that trains, and improves the action selection
Neural networks for the EMOBOT robot control architecture
No full textWithin the EMOBOT approach to adaptive behaviour, the task of learning to control the behaviour is one of the most interesting challenges. Learned action selection between classically implemented control mechanisms, with respect to internal values and sensor readings, provides a way to modulate a variety of behavioural capabilities. To demonstrate the potential of the learning emotional controller, we chose a 10-5-12 MLP to implement the r, a controller of the EMOBOT. Since no teacher vector is available for the chosen task, the neural network is trained with a reinforcement strategy. The emotion-value-dependent reinforcement signal, together with the output of the network, is the basis with which to compute an artificial teacher vector. Then, the established gradient descent method (backpropagation of error) is applied to train the neural network. First results obtained by extensive simulations show that a still unrevealed richness in behaviour can be realised when using the neural-network-based learning emotional controller
Applicability of feature selection on multivariate time series data for robotic discovery
No full textOpen ended robotic discovery aims at enabling robots to autonomously design and execute sophisticated experiments for gaining conceptual insight about real world. Such experiments are planned activities rather than innate motor commands and thus each single experiment results in a multivariate time series. In such a scenario, reducing the number of features in order to allow a symbolic learner to build a correct conceptual model of underlying phenomena is a fundamental task. Only few feature selection approaches deal with finding relevant features in multivariate time series, which is just what the robot receives through its sensors. In this paper, we present results of applicability of a range of feature selection and time series analysis approaches on a novel real world scenario for autonomous robotic discovery. We found that even sophisticated representations and state of the art techniques, which perform very well on other benchmarks, do not show significant results in context of open ended discovery
Towards iterative learning of autonomous robots using ILP
No full textInductive Logic Programming (ILP) induces first-order clausal theories from learning examples (positive and negative) and knowledge of the domain. Such theories can be used for gradually increasing the understanding of a robot about its world through iterative learning process. In this work we present a method for autonomous creation of negative examples for an ILP learner (i.e. sifting method). We also present a method for managing the iterative learning process (i.e. step transition method) for an autonomous robot that uses the ILP learner for learning. The sifting method uses 'out-of-domain' values of the parameters involved in the learning process to create a set of possible negative examples. From these examples the robot autonomously selects those which allow it to efficiently learn better hypotheses. The step transition method enables the autonomous robot to decide how should it learn the new knowledge such that it can also gain profit from its experience. The robot makes this decision by comparing results of two different learning processes conducted on different data sets produced by the same action of the robot. The proposed methods are developed using the ILP learner Aleph, however they can also be used with other similar ILP learners. We experiment with these methods for learning primitive concepts for a mobile autonomous robot in a simple world. Results of the experiments show that the robot learns meaningful definitions of different physical notions in a hierarchical manner
Slides of the RDM Workshop for the CRC1456 from 2022-09-26 and 2022-09-27
No full textPresentation slides used in the Research data management workshop of the CRC1456 from Monday, September 26th 2022 and Tuesday September 27th 202
Automatic stimulation of experiments and learning based on prediction failure recognition
Get PDFIn this paper we focus on the task of automatically and autonomously initiating experimentation and learning based on the recognition of prediction failure. We present a
mechanism that utilizes conceptual knowledge to predict the outcome of robot actions, observes their execution and indicates when discrepancies occur. We show how this mechanism was applied to a robot that learns using the paradigm of learning by experimentation, and present first results obtained from this implementation
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Get PDF“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
- …
