News | Jobs | Team | Grants

Robot Learning & Interaction

The Robot Learning & Interaction group focuses on human-centered robotic applications in which the robots can learn new skills by interacting with the end-users.

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

COB'HOOK project featured on IEEE spectrum website

research — last modified Nov 17, 2020

The video shows recent experiments with our bimanual robot to insert a thread into a needle by using active sensing techniques.

Robots and humans collaborate to play music together

research — Jan 22, 2020

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 best presentation award of the Conference on Robot Learning goes to Noémie Jaquier, PhD student at Idiap

research — Nov 07, 2019

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.

"Deep neural networks remain for the most part black boxes"

research — May 08, 2019

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.

Like humans, robots can learn to walk

research — Feb 06, 2019

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.

More News