Filters








9,193 Hits in 33.7 sec

When the goal is to generate a series of activities: A self-organized simulated robot arm [article]

Tim Koglin, Bulcsú Sándor, Claudius Gros
2019 arXiv   pre-print
We believe that our approach may be generalized to generate self-organized sequences of activities in general.  ...  We study the emergence of autonomous task switching for the case of a simulated robot arm. Grasping one of several moving objects corresponds in this setting to a specific activity.  ...  Conclusion One of the biggest challenges in the design of controllers for autonomous agents is the combination of different goal oriented behaviors into a series of self-organized activities [36] .  ... 
arXiv:1905.07235v1 fatcat:a3os6rsnvbgt5lvv6udcq73u2e

When the goal is to generate a series of activities: A self-organized simulated robot arm

Tim Koglin, Bulcsú Sándor, Claudius Gros, Dante R. Chialvo
2019 PLoS ONE  
We believe that our approach may be generalized to generate self-organized sequences of activities in general.  ...  We study the emergence of autonomous task switching for the case of a simulated robot arm. Grasping one of several moving objects corresponds in this setting to a specific activity.  ...  Conclusion One of the biggest challenges in the design of controllers for autonomous agents is the combination of different goal oriented behaviors into a series of self-organized activities [36] .  ... 
doi:10.1371/journal.pone.0217004 pmid:31216272 pmcid:PMC6584010 fatcat:3alm3u7cwzc3tcqumis3rykvh4

Active learning of inverse models with intrinsically motivated goal exploration in robots

Adrien Baranes, Pierre-Yves Oudeyer
2013 Robotics and Autonomous Systems  
We introduce the Self-Adaptive Goal Generation - Robust Intelligent Adaptive Curiosity (SAGG-RIAC) architecture as an intrinsi- cally motivated goal exploration mechanism which allows active learning of  ...  This allows a robot to efficiently and actively learn distributions of parameterized motor skills/policies that solve a corresponding distribution of parameterized tasks/goals.  ...  Acknowledgment We thank everyone who gave us their feedback on the paper. This research was partially funded by ERC Grant EXPLOR-ERS 240007  ... 
doi:10.1016/j.robot.2012.05.008 fatcat:hb7lzdcgergujekl4fi4zfsxza

Active exploration for body model learning through self-touch on a humanoid robot with artificial skin [article]

Filipe Gama and Maksym Shcherban and Matthias Rolf and Matej Hoffmann
2020 arXiv   pre-print
In this work, we present an embodied computational model on a simulated humanoid robot with artificial sensitive skin on large areas of its body.  ...  The mechanisms of infant development are far from understood. Learning about one's own body is likely a foundation for subsequent development.  ...  The observation space is the robot skin-activation generated when the robot contacts its torso or face with its arm. This is a discrete space of individual taxels and their activation.  ... 
arXiv:2008.13483v1 fatcat:vlbkg5jie5dtpobcr7z3f5bg3e

R-IAC: Robust Intrinsically Motivated Exploration and Active Learning

A. Baranes, P.-Y. Oudeyer
2009 IEEE Transactions on Autonomous Mental Development  
Intelligent adaptive curiosity (IAC) was initially introduced as a developmental mechanism allowing a robot to self-organize developmental trajectories of increasing complexity without preprogramming the  ...  to IAC in a complex sensorimotor space where only a small subspace is neither unlearnable nor trivial.  ...  ACKNOWLEDGMENT The authors would like to thank M. Li for his crucial help in the elaboration and evaluation of the ILO-GMR regression algorithm.  ... 
doi:10.1109/tamd.2009.2037513 fatcat:m52j25t6xbdmzn25wpecazsnge

Active inference and robot control: a case study

Léo Pio-Lopez, Ange Nizard, Karl Friston, Giovanni Pezzulo
2016 Journal of the Royal Society Interface  
Here, we discuss a proof-of-principle implementation of the active inference scheme for the control or the 7-DoF arm of a (simulated) PR2 robot.  ...  In the discussion, we consider the potential importance of being able to implement active inference in robots.  ...  Active inference starts from the fundaments of self-organization which suggests that any adaptive agent needs to maintain its biophysical states within limits, therefore maintaining a generalized homeostasis  ... 
doi:10.1098/rsif.2016.0616 pmid:27683002 pmcid:PMC5046960 fatcat:abrywa7iijes5ihprd3rrvj27e

Intrinsically Motivated Exploration for Developmental and Active Sensorimotor Learning [chapter]

Pierre-Yves Oudeyer, Adrien Baranes, Frédéric Kaplan
2010 Studies in Computational Intelligence  
Finally, an open-source accompanying software containing these algorithms as well as tools to reproduce all the experiments in simulation presented in this paper is made publicly available.  ...  Then, we introduce a novel formulation of IAC, called R-IAC, and show that its performances as an intrinsically motivated active learning algorithm are far superior to IAC in a complex sensorimotor space  ...  Acknowledgements The work presented here was partly realized and supported by the Sony CSL Laboratory, Paris, France (the Playground Experiment in particular), and partly realized and supported by INRIA  ... 
doi:10.1007/978-3-642-05181-4_6 fatcat:233hqi2zx5cypeqthc7hvhsgrq

Modular active curiosity-driven discovery of tool use

Sebastien Forestier, Pierre-Yves Oudeyer
2016 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)  
MB exploits efficiently a modular representation of the space of parameterized problems/effects. We also study an active version of Model Babbling (the MACOB architecture).  ...  In particular, we consider goal babbling architectures that were designed to explore and learn solutions to fields of sensorimotor problems, i.e. to acquire inverse models mapping a space of parameterized  ...  Experimental setup We designed a robotic setup where a 2D simulated arm can grasp two sticks that can be used to move some of the out-of-reach objects (see Fig.2 ).  ... 
doi:10.1109/iros.2016.7759584 dblp:conf/iros/ForestierO16 fatcat:bvbbra73rfconof6lktkwnydxy

Revisiting active perception

Ruzena Bajcsy, Yiannis Aloimonos, John K. Tsotsos
2017 Autonomous Robots  
The history of these ideas, perhaps selective due to our perspectives, is presented with the goal of organizing the past literature and highlighting the seminal contributions.  ...  Despite the recent successes in robotics, artificial intelligence and computer vision, a complete artificial agent necessarily must include active perception.  ...  Active Perception systems attempt to deal with the perceptual-motor loop of a robot in a real environment, rejecting simulated worlds.  ... 
doi:10.1007/s10514-017-9615-3 pmid:31983809 pmcid:PMC6954017 fatcat:oqx5jim2frdtjpvz5kh4q22uuq

Revisiting Active Perception [article]

Ruzena Bajcsy and Yiannis Aloimonos and John K. Tsotsos
2016 arXiv   pre-print
The history of these ideas, perhaps selective due to our perspectives, is presented with the goal of organizing the past literature and highlighting the seminal contributions.  ...  Despite the recent successes in robotics, artificial intelligence and computer vision, a complete artificial agent necessarily must include active perception.  ...  Active Perception systems attempt to deal with the perceptual-motor loop of a robot in a real environment, rejecting simulated worlds.  ... 
arXiv:1603.02729v2 fatcat:wnt362piu5g4flvf7tkqz6ncd4

Robot Learning by Active Imitation [chapter]

Juan Pedro, Rebeca Marfil, Luis Molina, Juan Antonio, Antonio Bandera, Francisco Sandoval
2007 Humanoid Robots, Human-like Machines  
TIN2005-01359, and by the European Robotics Research Network (EURON), Project VISOR.  ...  Acknowledgement This work has been partially granted by the Spanish Ministerio de Educación y Ciencia (MEC) and FEDER funds, Project n.  ...  The model mechanism is validated in simulation and in a humanoid robot to perform a simple task, in which the robot imitates movements performed by a human demonstrator.  ... 
doi:10.5772/4821 fatcat:ybz3usowljectoogk2l7lwpww4

Adversarial Active Exploration for Inverse Dynamics Model Learning [article]

Zhang-Wei Hong, Tsu-Jui Fu, Tzu-Yun Shann, Yi-Hsiang Chang, Chun-Yi Lee
2020 arXiv   pre-print
The latter is trained with samples collected by the former, and generates rewards for the former when it fails to predict the actual action taken by the former.  ...  We evaluate the effectiveness of our method on several robotic arm and hand manipulation tasks against multiple baseline models.  ...  Experimental Results In this section, we present experimental results for a series of robotic control tasks, and validate that (i) our method is effective for common robotic arm control and in-hand manipulation  ... 
arXiv:1806.10019v2 fatcat:pgliesgdu5f7pol3jswn66utoi

Active Inference in Robotics and Artificial Agents: Survey and Challenges [article]

Pablo Lanillos, Cristian Meo, Corrado Pezzato, Ajith Anil Meera, Mohamed Baioumy, Wataru Ohata, Alexander Tschantz, Beren Millidge, Martijn Wisse, Christopher L. Buckley, Jun Tani
2021 arXiv   pre-print
Recently, it has been shown to be a promising approach to the problems of state-estimation and control under uncertainty, as well as a foundation for the construction of goal-driven behaviours in robotics  ...  Active inference is a mathematical framework which originated in computational neuroscience as a theory of how the brain implements action, perception and learning.  ...  ACKNOWLEDGMENT We would like to thank Karl Friston for his comments on the manuscript and his invaluable inspiration for AIF in robotics.  ... 
arXiv:2112.01871v1 fatcat:dux4iuejufb4bomn27eqv5rpea

Intelligent robot trends and predictions for the .net future

Ernest L. Hall, David P. Casasent, Ernest L. Hall
2001 Intelligent Robots and Computer Vision XX: Algorithms, Techniques, and Active Vision  
In this type of learning, a critic provides a grade to the controller of an action module such as a robot. The adaptive critic is a good model for human learning.  ...  An intelligent robot is a remarkably useful combination of a manipulator, sensors and controls.  ...  In some modern simulation software, once a series of motions are selected, the robot code generator program can translate the motions into robot programming language automatically and download this program  ... 
doi:10.1117/12.444228 fatcat:xv65xlvamvb37n4566q6bueywy

Active Inferants: An Active Inference Framework for Ant Colony Behavior

Daniel Ari Friedman, Alec Tschantz, Maxwell J. D. Ramstead, Karl Friston, Axel Constant
2021 Frontiers in Behavioral Neuroscience  
In this paper, we introduce an active inference model of ant colony foraging behavior, and implement the model in a series of in silico experiments.  ...  Active inference is a multiscale approach to behavioral modeling that is being applied across settings in theoretical biology and ethology.  ...  This is the scale that we explored here in this series of simulations.  ... 
doi:10.3389/fnbeh.2021.647732 pmid:34248515 pmcid:PMC8264549 fatcat:nvurzinpybc2hftnfah2atu4w4
« Previous Showing results 1 — 15 out of 9,193 results