Robots Understanding Their Actions by Imagining Their Effects

Livrables

This deliverable will contain an analysis of the main elements of the data management policy used by the applicants with regard to all data sets generated by the project This will include a data set reference name description standards metadata and management principles such as sharing archiving and preservation

Continuation plan

This deliverable will be a report that summarizes all relevant national and international funding opportunities which would allow us to continue the IMAGINE concept into higher TRL levels after the end of this project It will also address possible involvement from enduser here taking care especially about the business requirements of ECYC

Business Analysis and IPR management report

This deliverable will report on the different possible opportunities for bringing the IMAGINE softwarehardware system and its subcomponents closer to the market It will also address all planned and performed IPR activities of our project

Report on benchmarking results

Report on the evolution of the benchmarking results for the defined benchmarks

Report on benchmark definitions

Definition of benchmarks for performance evaluation on component and system level on disassembly scenarios from the recycling domain

Project website live

This deliverable is the project website comprising the main dissemination and exploitation channels for promoting and communicating the project relevant activities and achievements A fully functional and user friendly website will be designed and serve as a major dissemination tool It will also have a part acting as an active blog of research where partners can put articles about intermediate results events etc The website will adhere to the general communication strategy Periodically updates of the website according to users evaluation session planned in dissemination will be carried out

Publications

Parametrik Dinamik Motor Primitifleri

Auteurs: Girgin, Hakan; Ugur, Emre
Publié dans: Turkish Robotics Journal, Numéro 3, 2018
Éditeur: Bogazici University
DOI: 10.5281/zenodo.4726690

How does explicit exploration influence Deep Reinforcement Learning?

Auteurs: Jakob Hollenstein, Erwan Renaudo, Matteo Saveriano, Justus Piater
Publié dans: Proceedings of the Joint Austrian Computer Vision and Robotics Workshop 2020, 2020, Page(s) 29-30, ISBN 978-3-85125-752-6
Éditeur: TUGraz OPEN Library
DOI: 10.3217/978-3-85125-752-6

Belief Regulated Dual Propagation Nets for Learning Action Effects on Groups of Articulated Objects

Auteurs: Ahmet E. Tekden, Aykut Erdem, Erkut Erdem, Mert Imre, M. Yunus Seker, Emre Ugur
Publié dans: 2020 IEEE International Conference on Robotics and Automation (ICRA), 2020, Page(s) 10556-10562, ISBN 978-1-7281-7395-5
Éditeur: IEEE
DOI: 10.1109/icra40945.2020.9196878

Reconfigurable Behavior Trees: Towards an Executive Framework Meeting High-level Decision Making and Control Layer Features

Auteurs: de la Cruz, Pilar; Piater, Justus; Saveriano, Matteo
Publié dans: IEEE International Conference on Systems, Man, and Cybernetics, 2020
Éditeur: IEEE

Leveraging Multiple Environments for Learning and Decision Making: a Dismantling Use Case

Auteurs: Alejandro Suarez-Hernandez, Thierry Gaugry, Javier Segovia-Aguas, Antonin Bernardin, Carme Torras, Maud Marchal, Guillem Alenya
Publié dans: 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020, Page(s) 6902-6908, ISBN 978-1-7281-6212-6
Éditeur: IEEE
DOI: 10.1109/iros45743.2020.9341182

ACNMP: Skill Transfer and Task Extrapolation through Learning from Demonstration and Reinforcement Learning via Representation Sharing

Auteurs: Akbulut, M. Tuluhan; Oztop, Erhan; Seker, M. Yunus; Xue, Honghu; Tekden, Ahmet E.; Ugur, Emre
Publié dans: Conference on Robot Learning (CoRL), Numéro 11, 2020
Éditeur: JMLR Workshop & Conference Proceedings series

DCNN-Based Screw Detection for Automated Disassembly Processes

Auteurs: Erenus Yildiz, Florentin Worgotter
Publié dans: 2019 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), 2019, Page(s) 187-192, ISBN 978-1-7281-5686-6
Éditeur: IEEE
DOI: 10.1109/sitis.2019.00040

A Visual Intelligence Scheme for Hard Drive Disassembly in Automated Recycling Routines

Auteurs: Erenus Yildiz, Tobias Brinker, Erwan Renaudo, Jakob Hollenstein, Simon Haller-Seeber, Justus Piater, Florentin Wörgötter
Publié dans: Proceedings of the International Conference on Robotics, Computer Vision and Intelligent Systems, 2020, Page(s) 17-27, ISBN 978-989-758-479-4
Éditeur: SCITEPRESS - Science and Technology Publications
DOI: 10.5220/0010016000170027

Active Deformation through Visual Servoing of Soft Objects

Auteurs: Romain Lagneau, Alexandre Krupa, Maud Marchal
Publié dans: 2020 IEEE International Conference on Robotics and Automation (ICRA), 2020, Page(s) 8978-8984, ISBN 978-1-7281-7395-5
Éditeur: IEEE
DOI: 10.1109/icra40945.2020.9197506

Conditional Neural Movement Primitives

Auteurs: Muhammet Yunus Seker, Mert Imre, Justus Piater, Emre Ugur
Publié dans: Robotics: Science and Systems XV, 2019, ISBN 978-0-9923747-5-4
Éditeur: Robotics: Science and Systems Foundation
DOI: 10.15607/rss.2019.xv.071

The KIT Gripper: A Multi-Functional Gripper for Disassembly Tasks

Auteurs: Klas, C., Hundhausen, F., Gao, J., Dreher, C. R. G., Reither, S., Zhou, Y. and Asfour, T.
Publié dans: IEEE International Conference on Robotics and Automation (ICRA), May, 2021, 2021
Éditeur: IEEE

Towards a Mirror Neuron System via Dual Channel Conditional Neural Movement Primitives

Auteurs: Seker, M. Yunus; Oztop, Erhan; Akbulut, Mete Tuluhan; Asada, Minoru; Ugur, Emre
Publié dans: ICRA Brain-PIL Workshop, New advances in brain-inspired perception, interaction and learning, Numéro 10, 2020
Éditeur: brain-pil.github.io/icra2020/
DOI: 10.5281/zenodo.4726656

Evaluating Planning for Policy Search

Auteurs: Jakob Hollenstein and Justus Piater
Publié dans: 1st Workshop on Workshop on Closing the Reality Gap in Sim2real Transfer for Robotic Manipulation, 2019
Éditeur: informal

Coping with the variability in humans reward during simulated human-robot interactions through the coordination of multiple learning strategies *

Auteurs: Remi Dromnelle, Benoit Girard, Erwan Renaudo, Raja Chatila, Mehdi Khamassi
Publié dans: 2020 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), 2020, Page(s) 612-617, ISBN 978-1-7281-6075-7
Éditeur: IEEE
DOI: 10.1109/ro-man47096.2020.9223451

Reward Conditioned Neural Movement Primitives for Population Based Variational Policy Optimization

Auteurs: Akbulut, M. Tuluhan; Bozdogan, Utku; Tekden, Ahmet; Ugur, Emre
Publié dans: 2021 IEEE International Conference on Robotics and Automation (ICRA), Numéro 3, 2021
Éditeur: IEEE

DCNN-based Screw Classification in Automated Disassembly Processes

Auteurs: Erenus Yildiz, Florentin Wörgötter
Publié dans: Proceedings of the International Conference on Robotics, Computer Vision and Intelligent Systems, 2020, Page(s) 61-68, ISBN 978-989-758-479-4
Éditeur: SCITEPRESS - Science and Technology Publications
DOI: 10.5220/0009979900610068

Conflicting Bundles: Adapting Architectures Towards the Improved Training of Deep Neural Networks

Auteurs: Peer, David; Stabinger, Sebastian; Rodriguez-Sanchez, Antonio
Publié dans: IEEE/CVF Winter Conference on Applications of Computer Vision, 2021
Éditeur: IEEE

Online Action Recognition

Auteurs: Suárez-Hernández, Alejandro; Segovia-Aguas, Javier; Torras, Carme; Alenyà, Guillem
Publié dans: AAAI Conference on Artificial Intelligence, Numéro 14, 2021
Éditeur: AAAI

Kaldırma Aksiyonuyla Oluşan Yörüngenin Uzun Kısa Dönem Hafıza Modeliyle Tahmini

Auteurs: Tekden, Ahmet Ercan; Ugur, Emre
Publié dans: Turkish Robotics Conference, Numéro 12, 2018
Éditeur: Bogazici University
DOI: 10.5281/zenodo.4726712

STRIPS action discovery

Auteurs: Alejandro Suárez Hernández, Javier Segovia-Aguas,Carme Torras, Guillem Alenyà
Publié dans: GenPlan AAAI Workshop on Generalization in Planning, 2020
Éditeur: AAAI

Autonomous skill-centric testing using deep learning

Auteurs: Simon Hangl, Sebastian Stabinger, Justus Piater
Publié dans: 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2017, Page(s) 95-102, ISBN 978-1-5386-2682-5
Éditeur: IEEE
DOI: 10.1109/IROS.2017.8202143

Towards Generalizable Associative Skill Memories

Auteurs: Hakan Girgin; Emre Ugur
Publié dans: ICRA 2017 Workshop on Learning and control for autonomous manipulation systems: the role of dimensionality reduction, Numéro 1, 2017
Éditeur: ICRA Workshop on Learning and control for autonomous manipulation systems: the role of dimensionality reduction
DOI: 10.5281/zenodo.1183528

Model-Based Reinforcement Learning via Meta-Policy Optimization

Auteurs: Clavera, Ignasi; Rothfuss, Jonas; Schulman, John; Fujita, Yasuhiro; Asfour, Tamim; Abbeel, Pieter
Publié dans: Conference on Robot Learning, Numéro 1, 2018
Éditeur: Proceedings of Machine Learning Research

Interleaving Hierarchical Task Planning and Motion Constraint Testing for Dual-Arm Manipulation

Auteurs: Alejandro Suarez-Hernandez, Guillem Alenya, Carme Torras
Publié dans: 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018, Page(s) 4061-4066, ISBN 978-1-5386-8094-0
Éditeur: IEEE
DOI: 10.1109/IROS.2018.8593847

Associative Skill Memory Models

Auteurs: Hakan Girgin; Emre Ugur
Publié dans: IEEE/RSJ International Conference on Intelligent Robots and Systems, Numéro 1, 2018, Page(s) 6043-6048
Éditeur: IEEE

Learning Visual Dynamics Models of Rigid Objects using Relational Inductive Biases10-30

Auteurs: Ferreira, Fabio; Shao, Lin; Asfour, Tamim; Bohg, Jeannette
Publié dans: NeurIPS 2019 Graph Representation Learning workshop, Numéro 1, 2019
Éditeur: none
DOI: 10.5281/zenodo.3523161

The KIT Swiss Knife Gripper for Disassembly Tasks: A Multi-Functional Gripper for Bimanual Manipulation with a Single Arm

Auteurs: Julia Borras, Raphael Heudorfer, Samuel Rader, Peter Kaiser, Tamim Asfour
Publié dans: 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018, Page(s) 4590-4597, ISBN 978-1-5386-8094-0
Éditeur: IEEE
DOI: 10.1109/IROS.2018.8593567

Learning Via-Point Movement Primitives with Inter- and Extrapolation Capabilities

Auteurs: Zhou, You; Gao, Jianfeng; Asfour, Tamim
Publié dans: IEEE/RSJ International Conference on Intelligent Robots and Systems, Numéro 1, 2019
Éditeur: IEEE
DOI: 10.5281/zenodo.3523144

Sekil Bağlamı Kullanarak Eylem-Etki Tahmini

Auteurs: Seker, M. Yunus; Çağırıcı, Erhan; Ugur, Emre
Publié dans: Turkish Robotics Conference, Numéro 3, 2018
Éditeur: Bogazici University
DOI: 10.5281/zenodo.4726698

How do Offline Measures for Exploration in Reinforcement Learning behave?

Auteurs: Hollenstein, Jakob J.; Auddy, Sayantan; Saveriano, Matteo; Renaudo, Erwan; Piater, Justus
Publié dans: Knowledge Based Reinforcement Learning Workshop, 2021
Éditeur: workshop organizers

An Energy-based Approach to Ensure the Stability of Learned Dynamical Systems

Auteurs: Matteo Saveriano
Publié dans: 2020 IEEE International Conference on Robotics and Automation (ICRA), 2020, Page(s) 4407-4413, ISBN 978-1-7281-7395-5
Éditeur: IEEE
DOI: 10.1109/icra40945.2020.9196978

Simultaneous Tracking and Elasticity Parameter Estimation of Deformable Objects

Auteurs: Agniva Sengupta, Romain Lagneau, Alexandre Krupa, Eric Marchand, Maud Marchal
Publié dans: 2020 IEEE International Conference on Robotics and Automation (ICRA), 2020, Page(s) 10038-10044, ISBN 978-1-7281-7395-5
Éditeur: IEEE
DOI: 10.1109/icra40945.2020.9196770

An Interactive Physically-based Model for Active Suction Phenomenon Simulation

Auteurs: Antonin Bernardin, Christian Duriez, Maud Marchal
Publié dans: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019, Page(s) 1466-1471, ISBN 978-1-7281-4004-9
Éditeur: IEEE
DOI: 10.1109/iros40897.2019.8967526

Locally Weighted CNMPs for Generating Flexible Action Sequences

Auteurs: Ahmetoglu, Alper; Seker, Yunus; Oztop, Erhan; Asada, Minoru; Ugur, Emre
Publié dans: Winter Workshop on Mechanism of Brain and Mind, Numéro 12, 2020
Éditeur: http://brainmind.umin.jp/eng-index.html
DOI: 10.5281/zenodo.4726673

Generalized Planning with Positive and Negative Examples

Auteurs: Javier Segovia-Aguas, Sergio Jiménez, Anders Jonsson
Publié dans: Proceedings of the AAAI Conference on Artificial Intelligence, Numéro 34/06, 2020, Page(s) 9949-9956, ISSN 2374-3468
Éditeur: Association for the Advancement of Artificial Intelligence
DOI: 10.1609/aaai.v34i06.6550

Automatic Shape Control of Deformable Wires Based on Model-Free Visual Servoing

Auteurs: Romain Lagneau, Alexandre Krupa, Maud Marchal
Publié dans: IEEE Robotics and Automation Letters, Numéro 5/4, 2020, Page(s) 5252-5259, ISSN 2377-3766
Éditeur: IEEE
DOI: 10.1109/lra.2020.3007114

conflicting_bundle.py—A python module to identify problematic layers in deep neural networks

Auteurs: David Peer, Sebastian Stabinger, Antonio Rodríguez-Sánchez
Publié dans: Software Impacts, Numéro 7, 2021, Page(s) 100053, ISSN 2665-9638
Éditeur: Elsevier
DOI: 10.1016/j.simpa.2021.100053

Symbol Emergence in Cognitive Developmental Systems: A Survey

Auteurs: Tadahiro Taniguchi, Justus Piater, Florentin Worgotter, Emre Ugur, Matej Hoffmann, Lorenzo Jamone, Takayuki Nagai, Benjamin Rosman, Toshihiko Matsuka, Naoto Iwahashi, Erhan Oztop
Publié dans: IEEE Transactions on Cognitive and Developmental Systems, Numéro 11/4, 2019, Page(s) 494-516, ISSN 2379-8920
Éditeur: IEEE
DOI: 10.1109/TCDS.2018.2867772

Learning from Multiple Demonstrations with Different Modes of Operations

Auteurs: Utku Bozdogan
Publié dans: International Journal of Intelligent Systems and Applications in Engineering, Numéro 8/1, 2020, Page(s) 37-44, ISSN 2147-6799
Éditeur: Selcuk University
DOI: 10.18201/ijisae.2020158887

Computational models of affordance in robotics: a taxonomy and systematic classification

Auteurs: Philipp Zech, Simon Haller, Safoura Rezapour Lakani, Barry Ridge, Emre Ugur, Justus Piater
Publié dans: Adaptive Behavior, Numéro 25/5, 2017, Page(s) 235-271, ISSN 1059-7123
Éditeur: SAGE Publications
DOI: 10.1177/1059712317726357

Extraction of Physically Plausible Support Relations to Predict and Validate Manipulation Action Effects

Auteurs: Rainer Kartmann, Fabian Paus, Markus Grotz, Tamim Asfour
Publié dans: IEEE Robotics and Automation Letters, Numéro 3/4, 2018, Page(s) 3991-3998, ISSN 2377-3766
Éditeur: IEEE
DOI: 10.1109/lra.2018.2859448

Practical Resolution Methods for MDPs in Robotics Exemplified With Disassembly Planning

Auteurs: Alejandro Suarez-Hernandez, Carme Torras, Guillem Alenya
Publié dans: IEEE Robotics and Automation Letters, Numéro 4/3, 2019, Page(s) 2282-2288, ISSN 2377-3766
Éditeur: IEEE
DOI: 10.1109/LRA.2019.2901905

Deep effect trajectory prediction in robot manipulation

Auteurs: M. Yunus Seker, Ahmet E. Tekden, Emre Ugur
Publié dans: Robotics and Autonomous Systems, Numéro 119, 2019, Page(s) 173-184, ISSN 0921-8890
Éditeur: Elsevier BV
DOI: 10.1016/j.robot.2019.07.003

Context-based affordance segmentation from 2D images for robot actions

Auteurs: Timo Lüddecke, Tomas Kulvicius, Florentin Wörgötter
Publié dans: Robotics and Autonomous Systems, Numéro 119, 2019, Page(s) 92-107, ISSN 0921-8890
Éditeur: Elsevier BV
DOI: 10.1016/j.robot.2019.05.005

Compliant Parametric Dynamic Movement Primitives

Auteurs: Emre Ugur, Hakan Girgin
Publié dans: Robotica, 2019, Page(s) 1-18, ISSN 0263-5747
Éditeur: Cambridge University Press
DOI: 10.1017/S026357471900078X

Relational reinforcement learning for planning with exogenous effects

Auteurs: Martinez , David; Alenya , Guillem; Ribeiro , Tony; Inoue , Katsumi; Torras , Carme
Publié dans: Journal of Machine Learning Research, Numéro 18, 2017, ISSN 1533-7928
Éditeur: JMLR Inc.

Action representations in robotics: A taxonomy and systematic classification

Auteurs: Philipp Zech, Erwan Renaudo, Simon Haller, Xiang Zhang, Justus Piater
Publié dans: The International Journal of Robotics Research, Numéro 38/5, 2019, Page(s) 518-562, ISSN 0278-3649
Éditeur: SAGE Publications
DOI: 10.1177/0278364919835020

Affordance-based altruistic robotic architecture for human–robot collaboration

Auteurs: Mert Imre, Erhan Oztop, Yukie Nagai, Emre Ugur
Publié dans: Adaptive Behavior, Numéro 27/4, 2019, Page(s) 223-241, ISSN 1059-7123
Éditeur: SAGE Publications
DOI: 10.1177/1059712318824697

Combining decision making and dynamical systems for monitoring and executing manipulation tasks

Auteurs: Matteo Saveriano, Justus Piater
Publié dans: e & i Elektrotechnik und Informationstechnik, Numéro 137/6, 2020, Page(s) 309-315, ISSN 0932-383X
Éditeur: Springer Verlag
DOI: 10.1007/s00502-020-00816-7

Limitation of capsule networks

Auteurs: David Peer, Sebastian Stabinger, Antonio Rodríguez-Sánchez
Publié dans: Pattern Recognition Letters, Numéro 144, 2021, Page(s) 68-74, ISSN 0167-8655
Éditeur: Elsevier BV
DOI: 10.1016/j.patrec.2021.01.017

Auto-tuning of Deep Neural Networks by Conflicting Layer Removal

Auteurs: Peer, David; Stabinger, Sebastian; Rodriguez-Sanchez, Antonio
Publié dans: submitted to Neural Networks, 2021
Éditeur: arXiv.org

Object and Relation Centric Representations for Push Effect Prediction

Auteurs: Tekden, Ahmet E.; Erdem, Aykut; Erdem, Erkut; Asfour, Tamim; Ugur, Emre
Publié dans: 2021
Éditeur: arXiv.org

Livrables

Publications

Partager cette page

Télécharger