Goal-based Open-ended Autonomous Learning Robots

Rezultaty

Communication activities, supported by services from Robohub within the collaboration with them, and Blogs, in particular within the Digital Europe Agenda system.

Professional video on GOAL3 Demo

Professional video on GOAL3 Demo.

Project web-site and logo

First version of project web-site. Logo of project. The maintenance of the web-site is an activity that will last during the whole project. The consortium, under the lead of CNR, will work to design the web-site structure and logo, and to populate it with contents related to the project. CNR will pay some professionals for support on technical aspects contributing to the realisation of the web-site.

Professional video on GOAL4 Demo.
Professional video on GOAL2 Demo

Professional video on the second demo GOAL2 .

Action Check Meeting 2

Draft agenda and list of presentations of Check Meeting 2.

Action Check Meeting 3

Draft agenda and list of presentations of Check Meeting 3.

Action Check Meeting 1

Draft agenda and list of presentations of Check Meeting 1.

Dissemination and Exploitation Plan: first version

Plan of dissemination and exploitation: first compilation. CNR will lead the whole plan compilation. As stated in the submitted proposal, TUDa will lead the exploitation section of the plan.

Goal-based skill learning: first results

Algorithms allowing autonomous robots to learn large repertoires of flexible skills based on goals.

Scientific publications and conferences

Publications in journals, and presentations at conferences and other similar scientific events, on the project results.

Self goal-generation: consolidated results

Goal-formation/architectures to acquire sequential/hierarchical skills.

GOAL in infants and its models: first results

Report on how contingencies and goals are discovered and drive autonomous motor learning in infants, and formalisation of discovered mechanisms in computational models.

GOAL in infants and its models: consolidated results

Report on principles of generalisation, transfer, and agency, related to contingencies and goals, in infants and robots.

Dissemination and Exploitation Plan: third version

Plan of dissemination and exploitation: revision leading to the third version of the plan. CNR will lead the whole plan compilation. As stated in the submitted proposal, TUDa will lead the exploitation section of the plan.

Journal Special Issue

Journal Special Issue on the project results, hosted in a relevant journal.

Self goal-generation: first results

Mechanisms for goal formation, and architectures/mechanisms to support open-ended learning of skills in robots.

Goal-based skill learning: consolidated results

Algorithms to learn repertoires of flexible sequential/hierarchical skills.

Dissemination and Exploitation Plan: second version

Plan of dissemination and exploitation: revision leading to the second version of the plan. CNR will lead the whole plan compilation. As stated in the submitted proposal, TUDa will lead the exploitation section of the plan.

International Workshop

International Workshop on the project topics, involving researchers from both the project consortium and the scientific community beyond it.

Industry fair: second participation

Second participation to an industry fair and contacts with companies for the possible exploitation of the project outcomes.

Second open-ended learning competition

Second open-ended learning competition and improvement of open-ended learning benchmark.

Second ethical implications workshop

Organisation of the second workshop on the possible implications of open-ended learning for society.

First ethical implications workshop

Organisation of the first workshop on the possible implications of open-ended learning for society.

Industry fair: third participation

Third participation to an industry fair and contacts with companies for the possible exploitation of the project outcomes.

First open-ended learning competition

First open-ended learning competitions related to open-ended learning, supporting the definition of a benchmark for open-ended learning.

International Summer School

International Summer School on the project topics and approach to open-ended learning.

Industry fair: first participation

First participation to an industry fair and contacts with companies for the possible exploitation of the project outcomes.

GOAL1 Demonstrator

GOAL1 demonstrator will show: (a) the set-ups used in the Demos; (b) the operation of the basic robot architectures supporting open-ended learning of GOAL2/GOAL3; (c) the successful accomplishment of initial open-ended learning processes.

GOAL4 Demonstrator

GOAL4 demonstrator will show a solution to the tidy-up challenge in a real-life scenario. The pivotal element of the demo is that the robot will solve the challenge by relying on knowledge and skills autonomously acquired through a prolonged GOAL-based development preceding the challenge itself, without knowing in advance the type of initial object configuration, object misplacement, and specific objects involved. The autonomous-learning abilities of the robots will be shown by giving the robots new objects.

GOAL2 Demonstrator

GOAL2 demonstrator will show robots that can learn several different skills in an open-ended fashion.

GOAL3 Demonstrator

GOAL3 demonstrator will show robots that not only can learn several different skills with little supervision, but can also learn to perform each skill in several different conditions.

Plan for Open Data Pilot: first version

First document describing the data management plan to comply to the Open Data Pilot initiative.

Plan for Open Data Pilot: second version

Revised second document describing the data management plan to comply to the Open Data Pilot initiative.

Plan for Open Data Pilot: third version

Third revised document describing the data management plan to comply to the Open Data Pilot initiative.

Publikacje

Intrinsic motivation and mental replay enable efficient online adaptation in stochastic recurrent networks

Autorzy: Tanneberg, Daniel; Peters, Jan; Rueckert, Elmar
Opublikowane w: Neural Networks, Numer 1, 2018, ISSN 0893-6080
Wydawca: Pergamon Press Ltd.

Detection of sensorimotor contingencies in infants before the age of 1 year: A comprehensive review.

Autorzy: Lisa Jacquey, Jacqueline Fagard, Rana Esseily, J. Kevin O'Regan
Opublikowane w: Developmental Psychology, Numer 56/7, 2020, Strona(/y) 1233-1251, ISSN 0012-1649
Wydawca: American Psychological Association
DOI: 10.1037/dev0000916

General differential Hebbian learning: Capturing temporal relations between events in neural networks and the brain

Autorzy: Stefano Zappacosta, Francesco Mannella, Marco Mirolli, Gianluca Baldassarre
Opublikowane w: PLOS Computational Biology, Numer 14/8, 2018, Strona(/y) e1006227, ISSN 1553-7358
Wydawca: Public Library Of Science
DOI: 10.1371/journal.pcbi.1006227

Sensorimotor Contingencies as a Key Drive of Development: From Babies to Robots

Autorzy: Lisa Jacquey, Gianluca Baldassarre, Vieri Giuliano Santucci, J. Kevin O’Regan
Opublikowane w: Frontiers in Neurorobotics, Numer 13, 2019, ISSN 1662-5218
Wydawca: Frontiers Research Foundation
DOI: 10.3389/fnbot.2019.00098

Editorial: Intrinsically Motivated Open-Ended Learning in Autonomous Robots

Autorzy: Vieri Giuliano Santucci, Pierre-Yves Oudeyer, Andrew Barto, Gianluca Baldassarre
Opublikowane w: Frontiers in Neurorobotics, Numer 13, 2020, ISSN 1662-5218
Wydawca: Frontiers Research Foundation
DOI: 10.3389/fnbot.2019.00115

Development of body knowledge as measured by arm differentiation in infants: From global to local?

Autorzy: Lisa Jacquey, Sergiu Tcaci Popescu, Judith Vergne, Jacqueline Fagard, Rana Esseily, Kevin O’Regan
Opublikowane w: British Journal of Developmental Psychology, Numer 38/1, 2020, Strona(/y) 108-124, ISSN 0261-510X
Wydawca: Wiley-Blackwell
DOI: 10.1111/bjdp.12309

Acceptability of the Transitional Wearable Companion “+me” in Children With Autism Spectrum Disorder: A Comparative Pilot Study

Autorzy: Valerio Sperati, Beste Özcan, Laura Romano, Tania Moretta, Simone Scaffaro, Noemi Faedda, Giada Turturo, Francesca Fioriello, Simone Pelosi, Federica Giovannone, Carla Sogos, Vincenzo Guidetti, Gianluca Baldassarre
Opublikowane w: Frontiers in Psychology, Numer 11, 2020, ISSN 1664-1078
Wydawca: Frontiers Research Foundation
DOI: 10.3389/fpsyg.2020.00951

Action observation and motor imagery for rehabilitation in Parkinson's disease: A systematic review and an integrative hypothesis

Autorzy: Daniele Caligiore, Magda Mustile, Gianfranco Spalletta, Gianluca Baldassarre
Opublikowane w: Neuroscience & Biobehavioral Reviews, Numer 72, 2017, Strona(/y) 210-222, ISSN 0149-7634
Wydawca: Pergamon Press Ltd.
DOI: 10.1016/j.neubiorev.2016.11.005

The architecture challenge: Future artificial-intelligence systems will require sophisticated architectures, and knowledge of the brain might guide their construction

Autorzy: Gianluca Baldassarre, Vieri Giuliano Santucci, Emilio Cartoni, Daniele Caligiore
Opublikowane w: Behavioral and Brain Sciences, Numer 40, 2017, ISSN 0140-525X
Wydawca: Cambridge University Press
DOI: 10.1017/S0140525X17000036

Which limb is it? Responses to vibrotactile stimulation in early infancy

Autorzy: Eszter Somogyi, Lisa Jacquey, Tobias Heed, Matej Hoffmann, Jeffrey J. Lockman, Lionel Granjon, Jacqueline Fagard, J. Kevin O'Regan
Opublikowane w: British Journal of Developmental Psychology, 2017, ISSN 0261-510X
Wydawca: Wiley-Blackwell
DOI: 10.1111/bjdp.12224

Know Your Body Through Intrinsic Goals

Autorzy: Francesco Mannella, Vieri G. Santucci, Eszter Somogyi, Lisa Jacquey, Kevin J. O'Regan, Gianluca Baldassarre
Opublikowane w: Frontiers in Neurorobotics, Numer 12, 2018, ISSN 1662-5218
Wydawca: Frontiers Research Foundation
DOI: 10.3389/fnbot.2018.00030

Acceptability of the Transitional Wearable Companion “+me” in Typical Children: A Pilot Study

Autorzy: Valerio Sperati, Beste Özcan, Laura Romano, Simone Scaffaro, Tania Moretta, Giada Turturo, Maria Nicoletta Aliberti, Vincenzo Guidetti, Gianluca Baldassarre
Opublikowane w: Frontiers in Psychology, Numer 10, 2019, ISSN 1664-1078
Wydawca: Frontiers Research Foundation
DOI: 10.3389/fpsyg.2019.00125

Action Observation With Dual Task for Improving Cognitive Abilities in Parkinson’s Disease: A Pilot Study

Autorzy: Daniele Caligiore, Magda Mustile, Alissa Fineschi, Laura Romano, Fabrizio Piras, Francesca Assogna, Francesco E. Pontieri, Gianfranco Spalletta, Gianluca Baldassarre
Opublikowane w: Frontiers in Systems Neuroscience, Numer 13, 2019, ISSN 1662-5137
Wydawca: Frontiers Research Foundation
DOI: 10.3389/fnsys.2019.00007

Bio-Inspired Model Learning Visual Goals and Attention Skills Through Contingencies and Intrinsic Motivations

Autorzy: Valerio Sperati, Gianluca Baldassarre
Opublikowane w: IEEE Transactions on Cognitive and Developmental Systems, Numer 10/2, 2018, Strona(/y) 326-344, ISSN 2379-8920
Wydawca: IEEE
DOI: 10.1109/tcds.2017.2772908

Dysfunctions of the basal ganglia-cerebellar-thalamo-cortical system produce motor tics in Tourette syndrome

Autorzy: Daniele Caligiore, Francesco Mannella, Michael A. Arbib, Gianluca Baldassarre
Opublikowane w: PLOS Computational Biology, Numer 13/3, 2017, Strona(/y) e1005395, ISSN 1553-7358
Wydawca: Public Library of Science
DOI: 10.1371/journal.pcbi.1005395

Fetal Origin of Sensorimotor Behavior

Autorzy: Jaqueline Fagard, Rana Esseily, Lisa Jacquey, Kevin O’Regan, Eszter Somogyi
Opublikowane w: Frontiers in Neurorobotics, Numer 12, 2018, ISSN 1662-5218
Wydawca: Frontiers Research Foundation
DOI: 10.3389/fnbot.2018.00023

Stage-Wise Learning of Reaching Using Little Prior Knowledge

Autorzy: François de La Bourdonnaye, Céline Teulière, Jochen Triesch, Thierry Chateau
Opublikowane w: Frontiers in Robotics and AI, Numer 5, 2018, ISSN 2296-9144
Wydawca: Frontiers
DOI: 10.3389/frobt.2018.00110

Intrinsic motivation and mental replay enable efficient online adaptation in stochastic recurrent networks

Autorzy: Daniel Tanneberg, Jan Peters, Elmar Rueckert
Opublikowane w: Neural Networks, Numer 109, 2019, Strona(/y) 67-80, ISSN 0893-6080
Wydawca: Pergamon Press Ltd.
DOI: 10.1016/j.neunet.2018.10.005

A Reinforcement Learning Architecture that Transfers Knowledge between Skills when Solving Multiple Tasks

Autorzy: Paolo Tommasino, Daniele Caligiore, Marco Mirolli, Gianluca Baldassarre
Opublikowane w: IEEE Transactions on Cognitive and Developmental Systems, 2019, Strona(/y) 1-1, ISSN 2379-8920
Wydawca: IEEE
DOI: 10.1109/tcds.2016.2607018

Inverse reinforcement learning via nonparametric spatio-temporal subgoal modeling

Autorzy: A. Šošić, E. Rueckert, J. Peters, A. M. Zoubir, H. Koeppl
Opublikowane w: The Journal of Machine Learning Research, 2018, ISSN 1532-4435
Wydawca: MIT Press

Autonomous Development of Active Binocular and Motion Vision Through Active Efficient Coding

Autorzy: Alexander Lelais, Jonas Mahn, Vikram Narayan, Chong Zhang, Bertram E. Shi, Jochen Triesch
Opublikowane w: Frontiers in Neurorobotics, Numer 13, 2019, ISSN 1662-5218
Wydawca: Frontiers Research Foundation
DOI: 10.3389/fnbot.2019.00049

Robot End Effector Tracking Using Predictive Multisensory Integration

Autorzy: Lakshitha P. Wijesinghe, Jochen Triesch, Bertram E. Shi
Opublikowane w: Frontiers in Neurorobotics, Numer 12, 2018, ISSN 1662-5218
Wydawca: Frontiers Research Foundation
DOI: 10.3389/fnbot.2018.00066

An Embodied Agent Learning Affordances With Intrinsic Motivations and Solving Extrinsic Tasks With Attention and One-Step Planning

Autorzy: Gianluca Baldassarre, William Lord, Giovanni Granato, Vieri Giuliano Santucci
Opublikowane w: Frontiers in Neurorobotics, Numer 13, 2019, ISSN 1662-5218
Wydawca: Frontiers Research Foundation
DOI: 10.3389/fnbot.2019.00045

Different Dopaminergic Dysfunctions Underlying Parkinsonian Akinesia and Tremor

Autorzy: Daniele Caligiore, Francesco Mannella, Gianluca Baldassarre
Opublikowane w: Frontiers in Neuroscience, Numer 13, 2019, ISSN 1662-453X
Wydawca: Frontiers
DOI: 10.3389/fnins.2019.00550

A generative spiking neural-network model of goal-directed behaviour and one-step planning

Autorzy: Ruggero Basanisi, Andrea Brovelli, Emilio Cartoni, Gianluca Baldassarre
Opublikowane w: PLOS Computational Biology, Numer 16/12, 2020, Strona(/y) e1007579, ISSN 1553-7358
Wydawca: Public Library Of Science
DOI: 10.1371/journal.pcbi.1007579

6-Month-Old Infants’ Sensitivity to Contingency in a Variant of the Mobile Paradigm With Proximal Stimulation Studied at Fine Temporal Resolution in the Laboratory

Autorzy: Sergiu Tcaci Popescu, Alice Dauphin, Judith Vergne, J. Kevin O’Regan
Opublikowane w: Frontiers in Psychology, Numer 12, 2021, ISSN 1664-1078
Wydawca: Frontiers Research Foundation
DOI: 10.3389/fpsyg.2021.610002

Développement du savoir-faire corporel durant la première année de vie du bébé

Autorzy: Lisa Jacquey, Jacqueline Fagard, Kevin O’Regan, Rana Esseily
Opublikowane w: Enfance, Numer N°2/2, 2020, Strona(/y) 175, ISSN 0013-7545
Wydawca: Presses Universitaires de France
DOI: 10.3917/enf2.202.0175

A computational model of language functions in flexible goal-directed behaviour

Autorzy: Giovanni Granato, Anna M. Borghi, Gianluca Baldassarre
Opublikowane w: Scientific Reports, Numer 10/1, 2020, ISSN 2045-2322
Wydawca: Nature Publishing Group
DOI: 10.1038/s41598-020-78252-y

Evolutionary training and abstraction yields algorithmic generalization of neural computers

Autorzy: Daniel Tanneberg, Elmar Rueckert, Jan Peters
Opublikowane w: Nature Machine Intelligence, Numer 2/12, 2020, Strona(/y) 753-763, ISSN 2522-5839
Wydawca: Springer
DOI: 10.1038/s42256-020-00255-1

Intrinsic motivations and open-ended learning

Autorzy: Baldassarre, Gianluca
Opublikowane w: Numer 13, 2019
Wydawca: arXiv

Recurrent Connectivity Aids Recognition of Partly Occluded Objects

Autorzy: Ernst, Markus Roland; Triesch, Jochen; Burwick, Thomas
Opublikowane w: Numer 1, 2019
Wydawca: arXiv

Learning High-Level Planning Symbols from Intrinsically Motivated Experience

Autorzy: Oddi, Angelo; Rasconi, Riccardo; Cartoni, Emilio; Sartor, Gabriele; Baldassarre, Gianluca; Santucci, Vieri Giuliano
Opublikowane w: Numer 3, 2019
Wydawca: arXiv

Autonomous learning of multiple, context-dependent tasks

Autorzy: Santucci, Vieri Giuliano; Montella, Davide; da Silva, Bruno Castro; Baldassarre, Gianluca
Opublikowane w: Numer 1, 2020
Wydawca: arXiv

Autonomous Open-Ended Learning of Interdependent Tasks

Autorzy: Santucci, Vieri Giuliano; Cartoni, Emilio; da Silva, Bruno Castro; Baldassarre, Gianluca
Opublikowane w: Numer 2, 2019
Wydawca: arXiv

ImitationFlow: Learning Deep Stable Stochastic Dynamic Systems by Normalizing Flows

Autorzy: Urain, Julen; Ginesi, Michelle; Tateo, Davide; Peters, Jan
Opublikowane w: Numer 12, 2020
Wydawca: arXiv

An open-ended learning architecture to face the REAL 2020 simulated robot competition

Autorzy: Cartoni, Emilio; Montella, Davide; Triesch, Jochen; Baldassarre, Gianluca
Opublikowane w: Numer 1, 2020
Wydawca: arXiv

The Development of Active Binocular Vision under Normal and Alternate Rearing Conditions

Autorzy: Lukas Klimmasch; Johann Schneider; Alexander Lelais; Bertram E. Shi; Jochen Triesch
Opublikowane w: Numer 1, 2020
Wydawca: BioRxiv
DOI: 10.1101/2020.02.20.957449

Learning Algorithmic Solutions to Symbolic Planning Tasks with a Neural Computer Architecture

Autorzy: Tanneberg, Daniel; Rueckert, Elmar; Peters, Jan
Opublikowane w: Numer 13, 2020
Wydawca: arXiv

Supervised Topological Maps

Autorzy: Mannella, Francesco
Opublikowane w: Numer 15, 2020
Wydawca: arXiv

Sensorimotor Contingencies as a Key Drive of Development: From Babies to Robots

Autorzy: Lisa Jacquey; Gianluca Baldassarre; Vieri Giuliano Santucci; J. Kevin O'Regan
Opublikowane w: https://hal.archives-ouvertes.fr/hal-03130944, Numer 1, 2019
Wydawca: PsyArXiv
DOI: 10.31234/osf.io/sr52x

Recurrent Connections Aid Occluded Object Recognition by Discounting Occluders

Autorzy: Ernst, Markus Roland; Triesch, Jochen; Burwick, Thomas
Opublikowane w: Lecture Notes in Computer Science - Artificial Neural Networks and Machine Learning – ICANN 2019: Image Processing, Numer 1, 2019
Wydawca: arXiv

Advancing Trajectory Optimization with Approximate Inference: Exploration, Covariance Control and Adaptive Risk

Autorzy: Watson, Joe; Peters, Jan
Opublikowane w: Numer 1, 2021
Wydawca: arXiv

Optimal Options for Multi-Task Reinforcement Learning Under Time Constraints

Autorzy: Del Verme, Manuel; da Silva, Bruno Castro; Baldassarre, Gianluca
Opublikowane w: Numer 9, 2020
Wydawca: arXiv

Autonomous discovery of the goal space to learn a parameterized skill

Autorzy: E. Cartoni, G. Baldassarre
Opublikowane w: 2018
Wydawca: arXiv

Learning to touch objects through stage-wise deep reinforcement learning

Autorzy: de La Bourdonnaye , François; Teulière , Céline; Triesch , Jochen; Chateau , Thierry
Opublikowane w: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Numer 1, 2019
Wydawca: IEEE

Autonomous Reinforcement Learning of Multiple Interrelated Tasks

Autorzy: Santucci V. G., Baldassarre G. and Cartoni E.
Opublikowane w: arXiv, 2019
Wydawca: arXiv

Recurrent Connectivity Aids Recognition of Partly Occluded Objects

Autorzy: Ernst, Markus Roland and Triesch, Jochen and Burwick, Thomas
Opublikowane w: arXiv, 2019
Wydawca: Cornell University

Self-Calibrating Active Binocular Vision via Active Efficient Coding with Deep Autoencoders

Autorzy: Wilmot, Charles; Shi, Bertram E.; Triesch, Jochen
Opublikowane w: Numer 6, 2021
Wydawca: arXiv

Learning walk and trot from the same objective using different types of exploration

Autorzy: Liu, Zinan; Ploeger, Kai; Stark, Svenja; Rueckert, Elmar; Peters, Jan
Opublikowane w: Numer 11, 2019
Wydawca: arXiv

Learning Abstract Representations through Lossy Compression of Multi-Modal Signals

Autorzy: Wilmot, Charles; Triesch, Jochen
Opublikowane w: Numer 1, 2021
Wydawca: arXiv

Model-Based Quality-Diversity Search for Efficient Robot Learning

Autorzy: Keller, Leon; Tanneberg, Daniel; Stark, Svenja; Peters, Jan
Opublikowane w: Numer 13, 2020
Wydawca: arXiv

Advancing Trajectory Optimization with Approximate Inference: Exploration, Covariance Control and Adaptive Risk

Autorzy: Watson, Joe; Peters, Jan
Opublikowane w: arXiv, Numer 1, 2021
Wydawca: arXiv

SKID RAW: Skill Discovery From Raw Trajectories

Autorzy: Daniel Tanneberg, Kai Ploeger, Elmar Rueckert, Jan Peters
Opublikowane w: IEEE Robotics and Automation Letters, Numer 6/3, 2021, Strona(/y) 4696-4703, ISSN 2377-3766
Wydawca: arXiv
DOI: 10.1109/lra.2021.3068891

Autonomous Reinforcement Learning of Multiple Interrelated Tasks

Autorzy: Vieri Giuliano Santucci, Gianluca Baldassarre, Emilio Cartoni
Opublikowane w: 2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob), 2019, Strona(/y) 221-227, ISBN 978-1-5386-8128-2
Wydawca: IEEE
DOI: 10.1109/devlrn.2019.8850713

Local Online Motor Babbling: Learning Motor Abundance of a Musculoskeletal Robot Arm *

Autorzy: Zinan Liu, Arne Hitzmann, Shuhei Ikemoto, Svenja Stark, Jan Peters, Koh Hosoda
Opublikowane w: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019, Strona(/y) 6594-6601, ISBN 978-1-7281-4004-9
Wydawca: IEEE
DOI: 10.1109/iros40897.2019.8967791

Intrinsically Motivated Discovered Outcomes Boost User’s Goals Achievement in a Humanoid Robot

Autorzy: Kristsana Seepanomwan, Vieri Giuliano Santucci, Gianluca, Baldassarre
Opublikowane w: Development and Learning and Epigenetic Robotics (ICDL-EpiRob), 2017 Joint IEEE International Conference on, 2017
Wydawca: IEEE

Workshop On Ethical Issues of Open Ended-Learning in Autonomous Robots

Autorzy: Daniele Caligiore, Vieri Giuliano Santucci, Gianluca Baldassarre
Opublikowane w: Development and Learning and Epigenetic Robotics (ICDL-EpiRob), 2017 Joint IEEE International Conference on, 2017
Wydawca: IEEE

Learning of Active Binocular Vision in a Biomechanical Model of the Oculomotor System

Autorzy: Lukas Klimmasch, Alexander Lelais, Alexander Lichtenstein, Bertram Emil Shi, Jochen Triesch
Opublikowane w: Development and Learning and Epigenetic Robotics (ICDL-EpiRob), 2017 Joint IEEE International Conference on, 2017
Wydawca: IEEE

Online Learning with Stochastic Recurrent Neural Networks using Intrinsic Motivation Signals

Autorzy: Tanneberg D., Peters J., Rueckert E.
Opublikowane w: Proceedings of Machine Learning Research: Conference on Robot Learning (CoRL), 2017
Wydawca: PMLR

Learning Inverse Dynamics Models in O(n) time with LSTM networks

Autorzy: Rueckert E., Nakatenus M., Tosatto S., Peters, J
Opublikowane w: Proceedings of the International Conference on Humanoid Robots (HUMANOIDS), 2017
Wydawca: IEEE

Efficient Online Adaptation with Stochastic Recurrent Neural Networks

Autorzy: Tanneberg D., Peters J., Rueckert E.
Opublikowane w: Proceedings of the International Conference on Humanoid Robots (HUMANOIDS), 2017
Wydawca: IEEE

A Comparison of Distance Measures for Learning Nonparametric Motor Skill Libraries

Autorzy: Stark S., Peters J., Rueckert E.
Opublikowane w: Proceedings of the International Conference on Humanoid Robots (HUMANOIDS), 2017
Wydawca: IEEE

Simulation of the underactuated Sake Robotics Gripper in V-REP

Autorzy: Thiem S., Stark S., Tanneberg D., Peters J., Rueckert E.
Opublikowane w: Workshop at the International Conference on Humanoid Robots (HUMANOIDS), 2017
Wydawca: IEEE

Development of reaching to the body in early infancy: From experiments to robotic models

Autorzy: Matej Hoffmann, Lisa K. Chinn, Eszter Somogyi, Tobias Heed, Jacqueline Fagard, Jeffrey J. Lockman, J. Kevin O'Regan
Opublikowane w: 2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob), 2017, Strona(/y) 112-119, ISBN 978-1-5386-3715-9
Wydawca: IEEE
DOI: 10.1109/devlrn.2017.8329795

Action-outcome contingencies as the engine of open-ended learning: computational models and developmental experiments

Autorzy: G. Baldassarre, F. Mannella, V.G. Santucci,E. Somogyi, L. Jacquey, M. Hamilton, J.K. O’Regan
Opublikowane w: Proceedings of The 8th IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob2018), 2018
Wydawca: IEEE

Learning to Categorize Bug Reports with LSTM Networks

Autorzy: K.D. Gondaliya, J. Peters, E. Rueckert
Opublikowane w: International Conference on Advances in System Testing and Validation Lifecycle, 2018
Wydawca: IARIA XPS Press

Experience Reuse with Probabilistic Movement Primitives

Autorzy: Svenja Stark, Jan Peters, Elmar Rueckert
Opublikowane w: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019, Strona(/y) 1210-1217, ISBN 978-1-7281-4004-9
Wydawca: IEEE
DOI: 10.1109/iros40897.2019.8968545

La sensibilité aux contingences sensorimotrices chez le bébé et son rôle dans le développement du savoir-faire corporel. Approche croisée en robotique et psychologie du développement

Autorzy: Jacquey, Lisa
Opublikowane w: 2019
Wydawca: Université de Paris

Understand-Compute-Adapt: Neural Networks for Intelligent Agents

Autorzy: Tanneberg, Daniel
Opublikowane w: Numer 4, 2020
Wydawca: Technische Universität Darmstadt,
DOI: 10.25534/tuprints-00017234

Développement de la sensibilité aux contingences sensorimotrices lors des 6 premiers mois de vie

Autorzy: Fremond Claire
Opublikowane w: 2020
Wydawca: Master of Science and Technology, Sorbonne University

An Active Efficient Coding Model of Binocular Vision Development Under Normal and Abnormal Rearing Conditions

Autorzy: Lukas Klimmasch, Johann Schneider, Alexander Lelais, Bertram E. Shi, Jochen Triesch
Opublikowane w: From Animals to Animats 15 - 15th International Conference on Simulation of Adaptive Behavior, SAB 2018, Frankfurt/Main, Germany, August 14-17, 2018, Proceedings, Numer 10994, 2018, Strona(/y) 66-77, ISBN 978-3-319-97627-3
Wydawca: Springer International Publishing
DOI: 10.1007/978-3-319-97628-0_6

The development of reaching and grasping: towards an integrated framework based on a critical review of computational and robotic models

Autorzy: D. Caligiore, G. Baldassarre
Opublikowane w: 2019
Wydawca: Taylor and Francis Group

Recurrent Connections Aid Occluded Object Recognition by Discounting Occluders

Autorzy: Markus Roland Ernst, Jochen Triesch, Thomas Burwick
Opublikowane w: Artificial Neural Networks and Machine Learning – ICANN 2019: Image Processing - 28th International Conference on Artificial Neural Networks, Munich, Germany, September 17–19, 2019, Proceedings, Part III, Numer 11729, 2019, Strona(/y) 294-305, ISBN 978-3-030-30507-9
Wydawca: Springer International Publishing
DOI: 10.1007/978-3-030-30508-6_24

Learning Hierarchical Integration of Foveal and Peripheral Vision for Vergence Control by Active Efficient Coding

Autorzy: Zhetuo Zhao, Jochen Triesch, Bertram E. Shi
Opublikowane w: From Animals to Animats 15 - 15th International Conference on Simulation of Adaptive Behavior, SAB 2018, Frankfurt/Main, Germany, August 14-17, 2018, Proceedings, Numer 10994, 2018, Strona(/y) 78-89, ISBN 978-3-319-97627-3
Wydawca: Springer International Publishing
DOI: 10.1007/978-3-319-97628-0_7

Wyszukiwanie danych OpenAIRE...

Rezultaty

Publikacje

Udostępnij tę stronę

Pobierz