https://biecoll.ub.uni-bielefeld.de/index.php/robotdoc <p>Editor: Joanna Szufnarowska</p> Research Institute for Cognition and Robotics (CoR-Lab) en-US Post-Graduate Conference on Robotics and Development of Cognition: Proceedings https://biecoll.ub.uni-bielefeld.de/index.php/robotdoc/article/view/348 As psychologists considered synchrony as an important parameter for social interaction, we hypothesize that in the case of social interaction, people focus their attention on regions of interest where the visual stimuli are synchronized with their inner dynamics. Then, we assume that a mechanism able to detect synchrony between internal dynamics of a robot and external visual stimuli can be used as a starting point for human robot interaction. Inspired by human psychological and neurobiological data, we propose a synchrony based neural network architecture capable of selecting the robot interaction partner and of locating Focus of Attention. Syed Khursheed Hasnain Philippe Gaussier Ghiles Mostafaoui Copyright (c) 2023 Post-Graduate Conference on Robotics and Development of Cognition: Proceedings 2012-12-31 2012-12-31 10.2390/biecoll-robotdoc2012-06 https://biecoll.ub.uni-bielefeld.de/index.php/robotdoc/article/view/349 Maarten Versteegh Christina Bergmann Louis ten Bosch Lou Boves Copyright (c) 2023 Post-Graduate Conference on Robotics and Development of Cognition: Proceedings 2012-12-31 2012-12-31 10.2390/biecoll-robotdoc2012-20 https://biecoll.ub.uni-bielefeld.de/index.php/robotdoc/article/view/350 Marek Rucinski Francesca Stramandinoli Copyright (c) 2023 Post-Graduate Conference on Robotics and Development of Cognition: Proceedings 2012-12-31 2012-12-31 10.2390/biecoll-robotdoc2012-19 https://biecoll.ub.uni-bielefeld.de/index.php/robotdoc/article/view/351 The exploration and interaction of humanoid robots with the environment through tactile sensing is an important task for achieving truly autonomous agents. Recently much research has been focused on the development of new technologies for tactile sensors and new methods for tactile exploration. Edge detection is one of the tasks required in robots and humanoids to explore and recognise objects. In this work we propose a method for edge and plane classification with a biomimetic iCub fingertip using a probabilistic approach. The iCub fingertip mounted on an xy-table robot is able to tap and collect the data from the surface and edge of a plastic wall. Using a maximum likelihood classifier the xy-table knows when the iCub fingertip has reached the edge of the object. The study presented here is also biologically inspired by the tactile exploration performed in animals. Uriel Martinez-Hernandez Nathan F. Lepora Hector Barron-Gonzalez Tony Dodd Tony J. Prescott Copyright (c) 2023 Post-Graduate Conference on Robotics and Development of Cognition: Proceedings 2012-12-31 2012-12-31 10.2390/biecoll-robotdoc2012-09 https://biecoll.ub.uni-bielefeld.de/index.php/robotdoc/article/view/352 For modern biology and ethology, the reason for the emergence of leaders-followers patterns in groups of living organisms, is the need of social coordination. In this paper we attempt to examine factors contributing to the emergence of leadership, trying to understand the relation between leader role and behavioral capabilities. In order to achieve this goal, we use a simulation technique where a group of foraging robots has to choose between two identical food zones. Thus, robots must coordinate in some way in order to select the same food zone and collectively gathering food. Behavioral and quantitative analysis indicate that a form of leadership emerges and the emergence of leadership relates with high level of fitness. Moreover, we show that more skilled individuals in a group tend to assume a leadership role, in agreement with literature. Francesco Pugliese Alberto Acerbi Orazio Miglino Davide Marocco Copyright (c) 2023 Post-Graduate Conference on Robotics and Development of Cognition: Proceedings 2012-12-31 2012-12-31 10.2390/biecoll-robotdoc2012-13 https://biecoll.ub.uni-bielefeld.de/index.php/robotdoc/article/view/353 We investigate whether spontaneous movements, which initiate and guide early development in animals, can be accounted for by the properties underlying embodiment. We constructed computer and robotic models of several biological species with biologically plausible musculoskeletal bodies and nervous systems, and extracted the embodied and motor networks based on inter-muscle connectivities. In computer simulations and robot experiments, we found that the embodied and motor networks had similar global and local topologies, suggesting the key role of embodiment in generating spontaneous movements in animals. Yasunori Yamada Yasuo Kuniyoshi Copyright (c) 2023 Post-Graduate Conference on Robotics and Development of Cognition: Proceedings 2012-12-31 2012-12-31 10.2390/biecoll-robotdoc2012-22 https://biecoll.ub.uni-bielefeld.de/index.php/robotdoc/article/view/354 The goal of this research is to create a non-verbal system able to interact safely and naturally with humans. The main hypothesis is that mechanisms of high level interactions such as cooperation and understanding intentions can be obtained from well designed low-level systems. For example, an effector device instrumented to detect force constraints applied by others allows to get easily the direction (opposing vs facilitating) and, at a higher level of interpretation, the intention of others concerning the device's movement. This is one of the reasons we preferred hydraulic technology which presents a potential of physical compliance. Moreover, pressure control in the pistons is closer to muscles control than the electric motors. For the control architecture, we are interested in modeling the layers of motor command : low level force control, multimodal inputs (especially vision) leading to prediction and anticipation capabilities. To do so, this research includes the design of a bio-inspired neural network able to provide a force control of the hardware and merging inputs from different kind of sensors including vision and proprioception. The control has to be as close as possible to the hardware with the less layer possible. It is based on a control by activation of agonist and antagonist muscles. The position and torque sensor as well as short range proximity sensor are used to learn simple movements and their sensory outcome. The vision is also available through robotic eye mounted on a fast pan-tilt system allowing movement at human speed. High definition camera gives a video flow that can be used to analyze the scene. The neural network designed allows the system to analyze the scene using point of interest. By extracting local features around those points it is possible to construct a library of visual feature. Using this library objects can be recognize by learning simple associations between those local feature and sensorial context including supervision signals. Action can then be associated with the context or the presence of an object. Moreover sequences of simple actions can be learned through cognitive maps. For example the robot can learn from the human teacher to grasp, move and release an object. From then and with the recognition of object the robot is able to learn tasks such as sorting objects using their visual characteristic. As we construct this controller we hope to improve our knowledge of some structures of the brain such as the motor cortex, the pre-frontal cortex, the striatum or the cerebellum. Models of all these structures and other are used in the model here developed. The researches aim especially to better understand the influence of each structure on the global behavior of the robot as well as the synergies that emerge from the cooperation between structures and to create a new type of humanoid robot where all parts from the technology, through the low level control to the high level control is thought in the optic of realistic interactions with humans. David Bailly Pierre Andry Philippe Gaussier Copyright (c) 2023 Post-Graduate Conference on Robotics and Development of Cognition: Proceedings 2012-12-31 2012-12-31 10.2390/biecoll-robotdoc2012-02 https://biecoll.ub.uni-bielefeld.de/index.php/robotdoc/article/view/355 The use of concepts is a fundamental capacity underlying complex, human-level cognition. A number of theories have explored the means of concept representation and their links to lower-level features, with one notable example being the Conceptual Spaces theory. While these provide an account for such essential functional processes as prototypes and typicality, it is not entirely clear how these aspects of human cognition can arise in a system undergoing continuous development - postulated to be a necessity from the developmental systems perspective. This paper seeks to establish the foundation of an approach to this question by showing that a distributed, associative and continuous development mechanism, founded on principles of biological memory, can achieve classification performance comparable to the Conceptual Spaces model. We show how qualitatively similar prototypes are formed by both systems when exposed to the same dataset, which illustrates how both models can account for the development of conceptual primitives. Joachim de Greeff Paul Baxter Rachel Wood Tony Belpaeme Copyright (c) 2023 Post-Graduate Conference on Robotics and Development of Cognition: Proceedings 2012-12-31 2012-12-31 10.2390/biecoll-robotdoc2012-03 https://biecoll.ub.uni-bielefeld.de/index.php/robotdoc/article/view/356 Irini Giannopulu Copyright (c) 2023 Post-Graduate Conference on Robotics and Development of Cognition: Proceedings 2012-12-31 2012-12-31 10.2390/biecoll-robotdoc2012-05 https://biecoll.ub.uni-bielefeld.de/index.php/robotdoc/article/view/357 Martin F. Stoelen Davide Marocco Angelo Cangelosi Fabio Bonsignorio Carlos Balaguer Copyright (c) 2023 Post-Graduate Conference on Robotics and Development of Cognition: Proceedings 2012-12-31 2012-12-31 10.2390/biecoll-robotdoc2012-18 https://biecoll.ub.uni-bielefeld.de/index.php/robotdoc/article/view/358 Lauriane Rat-Fischer Kevin J. O'Regan Jacqueline Fagard Copyright (c) 2023 Post-Graduate Conference on Robotics and Development of Cognition: Proceedings 2012-12-31 2012-12-31 10.2390/biecoll-robotdoc2012-16 https://biecoll.ub.uni-bielefeld.de/index.php/robotdoc/article/view/359 Nick Wilkinson Francesco Rea Katrin Lohan Giorgio Metta Gustaf Gredeback Copyright (c) 2023 Post-Graduate Conference on Robotics and Development of Cognition: Proceedings 2012-12-31 2012-12-31 10.2390/biecoll-robotdoc2012-21 https://biecoll.ub.uni-bielefeld.de/index.php/robotdoc/article/view/360 Amir Aly Adriana Tapus Copyright (c) 2023 Post-Graduate Conference on Robotics and Development of Cognition: Proceedings 2012-12-31 2012-12-31 10.2390/biecoll-robotdoc2012-01 https://biecoll.ub.uni-bielefeld.de/index.php/robotdoc/article/view/361 Stigmergy is defined as a mechanism of coordination through indirect communication among agents, which can be commonly observed in social insects such as ants. In this work we investigate the emergence of coordination for locomotion in modular robots through indirect communication among modules. We demonstrate how intra-configuration forces that exist between physically connected modules can be used for self-organization in modular robots, and how the emerging global behavior is a result of the morphology of the robotic configuration. Avinash Ranganath Juan Gonzalez-Gomez Luis Moreno Lorente Copyright (c) 2023 Post-Graduate Conference on Robotics and Development of Cognition: Proceedings 2012-12-31 2012-12-31 10.2390/biecoll-robotdoc2012-15 https://biecoll.ub.uni-bielefeld.de/index.php/robotdoc/article/view/362 The paper presents the evaluation process of a first version of the one axis torque sensor designed for the iCub humanoid robot. Newly designed strain gauges equipped sensor was found to show a significant readouts hysteresis, therefore several tests were run to define the reason of the hysteresis. Some of the design issues met while testing the new sensor are discussed including the screws connection and relative rigidity of the sensor's elements analyses. Verification of the assembly procedure is also included. Tests revealed several problems on both design stage and exploitation of the sensor. Possible solutions to the encountered problems are further proposed. Wiktor Sieklicki Francesco Becchi Copyright (c) 2023 Post-Graduate Conference on Robotics and Development of Cognition: Proceedings 2012-12-31 2012-12-31 10.2390/biecoll-robotdoc2012-17 https://biecoll.ub.uni-bielefeld.de/index.php/robotdoc/article/view/363 Xavier Hinaut Maxime Petit Peter F. Dominey Copyright (c) 2023 Post-Graduate Conference on Robotics and Development of Cognition: Proceedings 2012-12-31 2012-12-31 10.2390/biecoll-robotdoc2012-07 https://biecoll.ub.uni-bielefeld.de/index.php/robotdoc/article/view/365 Our experimental results show that infants while learning to walk intend to reach for unreachable objects. These distance errors may result from inappropriate integration of reaching and locomotor actions, attention control and near/far visual space. Infants during their first months are fairly immobile, their attention and actions are constrained to near (reachable) space. Walking, in contrast, lures attention to distal displays and provides the information to disambiguate far space. In this paper, we make use of a reward-mediated learning to mimic the development of absolute distance perception. The results obtained with the NAO robot support further our hypothesis that the representation of near space changes after the onset of walking, which may cause the occurrence of distance errors. Beata J. Grzyb Vicente Castello Angel P. del Pobil Copyright (c) 2023 Post-Graduate Conference on Robotics and Development of Cognition: Proceedings 2012-12-31 2012-12-31 10.2390/biecoll-robotdoc2012-04 https://biecoll.ub.uni-bielefeld.de/index.php/robotdoc/article/view/366 In perception systems for object recognition, the advantage of multiple modalities, of combining approaches, and several views is emphasized, as they improve accuracy. However, there are great variances in the implementation, suggesting that there is no consensus yet on how to approach this problem. Nonetheless, we can identify some common features of the methods and propose a flexible system where existing and future approaches can be tested, compared and combined. We present a modular system in which perception routines can be easily added, and define the logic of making them work together based on the lessons learned from different experiments. Zoltan-Csaba Marton Florian Seidel Michael Beetz Copyright (c) 2023 Post-Graduate Conference on Robotics and Development of Cognition: Proceedings 2012-12-31 2012-12-31 10.2390/biecoll-robotdoc2012-10 https://biecoll.ub.uni-bielefeld.de/index.php/robotdoc/article/view/367 Our humanoid robot learns to provide position estimates of objects placed on a table, even while the robot is moving its torso, head and eyes (cm range accuracy). These estimates are provided by trained artificial neural networks (ANN) and a genetic programming (GP) method, based solely on the inputs from the two cameras and the joint encoder positions. No prior camera calibration and kinematic model is used. We find that ANN and GP are both able to localise objects robustly regardless of the robot's pose and without an explicit kinematic model or camera calibration. These approaches yield an accuracy comparable to current techniques used on the iCub. Jürgen Leitner Simon Harding Mikhail Frank Alexander Förster Jürgen Schmidhuber Copyright (c) 2023 Post-Graduate Conference on Robotics and Development of Cognition: Proceedings 2012-12-31 2012-12-31 10.2390/biecoll-robotdoc2012-08 https://biecoll.ub.uni-bielefeld.de/index.php/robotdoc/article/view/368 This paper studies an interactive learning system that couples internally guided learning and social interaction in the case it can interact with several teachers. Socially Guided Intrinsic Motivation with Interactive learning at the Meta level (SGIMIM) is an algorithm for robot learning of motor skills in highdimensional, continuous and non-preset environments, with two levels of active learning: SGIM-IM actively decides at a metalevel when and to whom to ask for help; and an active choice of goals in autonomous exploration. We illustrate through an air hockey game that SGIM-IM efficiently chooses the best strategy. Sao Mai Nguyen Pierre-Yves Oudeyer Copyright (c) 2023 Post-Graduate Conference on Robotics and Development of Cognition: Proceedings 2012-12-31 2012-12-31 10.2390/biecoll-robotdoc2012-11 https://biecoll.ub.uni-bielefeld.de/index.php/robotdoc/article/view/364 The aim of the Postgraduate Conference on Robotics and Development of Cognition (RobotDoC-PhD) is to bring together young scientists working on developmental cognitive robotics and its core disciplines. The conference aims to provide both feedback and greater visibility to their research as lively and stimulating discussion can be held amongst participating PhD students and senior researchers. The conference is open to all PhD students and post-doctoral researchers in the field. RobotDoC-PhD conference is an initiative as a part of Marie-Curie Actions ITN RobotDoC and will be organized as a satellite event of the 22nd International Conference on Artificial Neural Networks ICANN 2012. Joanna Szufnarowska Copyright (c) 2023 Post-Graduate Conference on Robotics and Development of Cognition: Proceedings 2012-12-31 2012-12-31 10.2390/biecoll-robotdoc2012-12