The video shows recent experiments with our bimanual robot to insert a thread into a needle by using active sensing techniques.
Robot Learning & Interaction
From a machine learning perspective, the challenge is to acquire skills from only few demonstrations and interactions, with strong generalization demands. It requires the development of intuitive active learning interfaces to acquire meaningful demonstrations, the development of models that can exploit the structure and geometry of the acquired data in an efficient way, and the development of adaptive control techniques that can exploit the learned task variations and coordination patterns.
The developed models must serve several purposes (recognition, prediction, online synthesis), and be compatible with different learning strategies (imitation, emulation, incremental refinement or exploration). For the reproduction of skills, these models need to be enriched with force and impedance information to enable human-robot collaboration and to generate safe and natural movements.
These models and algorithms can be applied to a wide range of robotic applications, with robots that are either close to us (assistive robots and human-robot collaboration in SMEs), part of us (prosthetic hands and exoskeletons), or far away from us (shared control of remote robots).
Group News
Collaborative robots are the perfect tool to link art and science. Thanks to his visit at Idiap, a researcher from Goldsmiths University of London used this approach to demonstrate the concept with a piano.
The Conference on Robot Learning (CoRL) awarded the best presentation award to Noémie Jaquier. In collaboration with the Bosch Center for Artificial Intelligence (BCAI), she presented a paper which highlights how mathematics and machine learning can help to find solutions to problems in robotics.
Artificial deep neural networks are a powerful tool, able to extract information from large datasets and, using this acquired knowledge, make accurate predictions on previously unseen data. Due to the very large number of parameters required, they are also particularly difficult to understand.
Following a comparable path, robots could learn to move and walk as human being do. The goal of the MEMMO project is to develop a unified approach to motion generation for complex robots with arms and legs.
Group Job Openings
There are currently no items in this folder.
Current Group Members

CALINON, Sylvain
(Senior Researcher)
- website

SILVERIO, João (Pedro Lourenço)
(Postdoctoral Researcher)
- website

SOUSA EWERTON, Marco (Antonio)
(Postdoctoral Researcher)
- website

RACCA, Mattia
(Postdoctoral Researcher)
- website

KULAK, Thibaut
(Research Assistant)
- website

LEMBONO, Teguh (Santoso)
(Research Assistant)
- website

SHETTY, Suhan (N.)
(Research Assistant)
- website

GIRGIN, Hakan
(Research Assistant)
- website

JANKOWSKI, Julius
(Research Assistant)
- website

LÖW, Tobias
(Research Assistant)
- website

RAZMJOO FARD, Amirreza
(Research Assistant)
- website
Alumni
- ABBET, Christian
- BERIO, Daniel
- BOURGEOIS, Dylan
- GAO, Xiao
- GULJELMOVIC, Nikol
- HAVOUTIS, Ioannis
- JAQUIER, Noémie
- KUPCSIK, Andras (Gabor)
- LOKIETKO, Jaroslaw
- MA, Wei
- PAOLILLO, Antonio
- PIGNAT, Emmanuel
- STANDAERT, Florian
- SUOMALAINEN, Markku (Heikki)
- TANWANI, Ajay (Kumar)
- TAO, Dominique
- TROUSSARD, Martin
- VAES, Clément
- WÜTSCHERT, Robin
Active Research Grants
- COBHOOK - COB'HOOK
- CODIMAN - A future that works: Cobotics, digital skills and the re-humanization of the workplace (CODIMAN)
- COLLABORATE - Co-production CeLL performing Human-Robot Collaborative AssEmbly
- HEAP - Human-Guided Learning and Benchmarking of Robotic Heap Sorting
- LEARN-REAL - LEARNing physical manipulation skills with simulators using REAListic variations (LEARN-REAL)
- MEMMO - Memory of Motion
- NATAI - The Nature of Artificial Intelligence
- ROSALIS - Robot skills acquisition through active learning and social interaction strategies
Past Research Grants
- HAPPYGLOVE - Electronic goniometer hAPPy Glove feasibility study
- TACT-HAND - TACT-HAND: Improving control of prosthetic hands using tactile sensors and realistic machine learning
- ROBOCLETTE - Roboclette (Robot racleur)
- I-DRESS - Assistive Interactive robotic system for support in DRESSing
- DEXROV - Effective Dexterous ROV Operations in Presence of Communications Latencies
- INNO-DIGGER - Artificial intelligence assistance for remote controlled excavator
- BAXTER - Démonstrateur Baxter