Opendata, web and dolomites

IMAGINE SIGNED

Robots Understanding Their Actions by Imagining Their Effects

Total Cost €

0

EC-Contrib. €

0

Partnership

0

Views

0

Project "IMAGINE" data sheet

The following table provides information about the project.

Coordinator
UNIVERSITAET INNSBRUCK 

Organization address
address: INNRAIN 52
city: INNSBRUCK
postcode: 6020
website: http://www.uibk.ac.at

contact info
title: n.a.
name: n.a.
surname: n.a.
function: n.a.
email: n.a.
telephone: n.a.
fax: n.a.

 Coordinator Country Austria [AT]
 Project website https://imagine-h2020.eu/
 Total cost 3˙797˙050 €
 EC max contribution 3˙797˙050 € (100%)
 Programme 1. H2020-EU.2.1.1. (INDUSTRIAL LEADERSHIP - Leadership in enabling and industrial technologies - Information and Communication Technologies (ICT))
 Code Call H2020-ICT-2016-1
 Funding Scheme RIA
 Starting year 2017
 Duration (year-month-day) from 2017-01-01   to  2021-02-28

 Partnership

Take a look of project's partnership.

# participants  country  role  EC contrib. [€] 
1    UNIVERSITAET INNSBRUCK AT (INNSBRUCK) coordinator 744˙250.00
2    GEORG-AUGUST-UNIVERSITAT GOTTINGENSTIFTUNG OFFENTLICHEN RECHTS DE (GOTTINGEN) participant 689˙000.00
3    KARLSRUHER INSTITUT FUER TECHNOLOGIE DE (KARLSRUHE) participant 667˙500.00
4    INSTITUT NATIONAL DES SCIENCES APPLIQUEES DE RENNES FR (RENNES CEDEX 7) participant 628˙550.00
5    AGENCIA ESTATAL CONSEJO SUPERIOR DEINVESTIGACIONES CIENTIFICAS ES (MADRID) participant 500˙625.00
6    BOGAZICI UNIVERSITESI TR (ISTANBUL) participant 365˙750.00
7    ELECTROCYCLING GMBH DE (GOSLAR) participant 201˙375.00

Map

 Project objective

'Today's robots are good at executing programmed motions, but they do not understand their actions in the sense that they could automatically generalize them to novel situations or recover from failures. IMAGINE seeks to enable robots to understand the structure of their environment and how it is affected by its actions. 'Understanding' here means the ability of the robot (a) to determine the applicability of an action along with parameters to achieve the desired effect, and (b) to discern to what extent an action succeeded, and to infer possible causes of failure and generate recovery actions.

The core functional element is a generative model based on an association engine and a physics simulator. 'Understanding' is given by the robot's ability to predict the effects of its actions, before and during their execution. This allows the robot to choose actions and parameters based on their simulated performance, and to monitor their progress by comparing observed to simulated behavior.

This scientific objective is pursued in the context of recycling of electromechanical appliances. Current recycling practices do not automate disassembly, which exposes humans to hazardous materials, encourages illegal disposal, and creates significant threats to environment and health, often in third countries. IMAGINE will develop a TRL-5 prototype that can autonomously disassemble prototypical classes of devices, generate and execute disassembly actions for unseen instances of similar devices, and recover from certain failures. For robotic disassembly, IMAGINE will develop a multi-functional gripper capable of multiple types of manipulation without tool changes.

IMAGINE raises the ability level of robotic systems in core areas of the work programme, including adaptability, manipulation, perception, decisional autonomy, and cognitive ability. Since only one-third of EU e-waste is currently recovered, IMAGINE addresses an area of high economical and ecological impact. '

 Publications

year authors and title journal last update
List of publications.
2019 Timo Lüddecke, Tomas Kulvicius, Florentin Wörgötter
Context-based affordance segmentation from 2D images for robot actions
published pages: 92-107, ISSN: 0921-8890, DOI: 10.1016/j.robot.2019.05.005
Robotics and Autonomous Systems 119 2020-02-24
2019 Mert Imre, Erhan Oztop, Yukie Nagai, Emre Ugur
Affordance-based altruistic robotic architecture for human–robot collaboration
published pages: 223-241, ISSN: 1059-7123, DOI: 10.1177/1059712318824697
Adaptive Behavior 27/4 2020-02-24
2019 Emre Ugur, Hakan Girgin
Compliant Parametric Dynamic Movement Primitives
published pages: 1-18, ISSN: 0263-5747, DOI: 10.1017/S026357471900078X
Robotica 2020-02-24
2019 Alejandro Suarez-Hernandez, Carme Torras, Guillem Alenya
Practical Resolution Methods for MDPs in Robotics Exemplified With Disassembly Planning
published pages: 2282-2288, ISSN: 2377-3766, DOI: 10.1109/LRA.2019.2901905
IEEE Robotics and Automation Letters 4/3 2020-02-24
2019 Philipp Zech, Erwan Renaudo, Simon Haller, Xiang Zhang, Justus Piater
Action representations in robotics: A taxonomy and systematic classification
published pages: 518-562, ISSN: 0278-3649, DOI: 10.1177/0278364919835020
The International Journal of Robotics Research 38/5 2020-02-24
2019 Zhou, You; Gao, Jianfeng; Asfour, Tamim
Learning Via-Point Movement Primitives with Inter- and Extrapolation Capabilities
published pages: , ISSN: , DOI: 10.5281/zenodo.3523144
IEEE/RSJ International Conference on Intelligent Robots and Systems 1 2020-02-24
2019 M. Yunus Seker, Ahmet E. Tekden, Emre Ugur
Deep effect trajectory prediction in robot manipulation
published pages: 173-184, ISSN: 0921-8890, DOI: 10.1016/j.robot.2019.07.003
Robotics and Autonomous Systems 119 2020-02-24
2019 Ferreira, Fabio; Shao, Lin; Asfour, Tamim; Bohg, Jeannette
Learning Visual Dynamics Models of Rigid Objects using Relational Inductive Biases10-30
published pages: , ISSN: , DOI: 10.5281/zenodo.3523161
NeurIPS 2019 Graph Representation Learning workshop 1 2020-02-24
2018 Hakan Girgin; Emre Ugur
Associative Skill Memory Models
published pages: 6043-6048, ISSN: , DOI:
IEEE/RSJ International Conference on Intelligent Robots and Systems 1 2020-02-24
2017 Martinez , David; Alenya , Guillem; Ribeiro , Tony; Inoue , Katsumi; Torras , Carme
Relational reinforcement learning for planning with exogenous effects
published pages: , ISSN: 1533-7928, DOI:
Journal of Machine Learning Research 18 2020-02-24
2018 Rainer Kartmann, Fabian Paus, Markus Grotz, Tamim Asfour
Extraction of Physically Plausible Support Relations to Predict and Validate Manipulation Action Effects
published pages: 3991-3998, ISSN: 2377-3766, DOI: 10.1109/lra.2018.2859448
IEEE Robotics and Automation Letters 3/4 2020-02-24
2018 Clavera, Ignasi; Rothfuss, Jonas; Schulman, John; Fujita, Yasuhiro; Asfour, Tamim; Abbeel, Pieter
Model-Based Reinforcement Learning via Meta-Policy Optimization
published pages: , ISSN: , DOI:
Conference on Robot Learning 1 2020-02-24
2019 M. Yunus Seker; Mert Imre; Justus Piater; Emre Ugur
Conditional Neural Movement Primitives
published pages: , ISSN: , DOI:
Robotics: Science and Systems 1 2020-02-24
2017 Philipp Zech, Simon Haller, Safoura Rezapour Lakani, Barry Ridge, Emre Ugur, Justus Piater
Computational models of affordance in robotics: a taxonomy and systematic classification
published pages: 235-271, ISSN: 1059-7123, DOI: 10.1177/1059712317726357
Adaptive Behavior 25/5 2020-02-24
2017 Hakan Girgin; Emre Ugur
Towards Generalizable Associative Skill Memories
published pages: , ISSN: , DOI: 10.5281/zenodo.1183528
ICRA 2017 Workshop on Learning and control for autonomous manipulation systems: the role of dimensionality reduction 1 2020-02-24

Are you the coordinator (or a participant) of this project? Plaese send me more information about the "IMAGINE" project.

For instance: the website url (it has not provided by EU-opendata yet), the logo, a more detailed description of the project (in plain text as a rtf file or a word file), some pictures (as picture files, not embedded into any word file), twitter account, linkedin page, etc.

Send me an  email (fabio@fabiodisconzi.com) and I put them in your project's page as son as possible.

Thanks. And then put a link of this page into your project's website.

The information about "IMAGINE" are provided by the European Opendata Portal: CORDIS opendata.

More projects from the same programme (H2020-EU.2.1.1.)

PIMCITY (2019)

PIMCITY: BUILDING THE NEXT GENERATION PERSONAL DATA PLATFORMS

Read More  

BeFerroSynaptic (2020)

BEOL technology platform based on ferroelectric synaptic devices for advanced neuromorphic processors

Read More  

Hydroptics (2019)

Photonics sensing platform for process optimisation in the oil industry

Read More