PROJECTS

AI Hub Tampere

AI Hub Tampere is a new artificial intelligence research center hosted by Tampere University and funded by public instruments. The center organizes workshops, helpdesk sessions, experimental piloting and other support for adopting artificial intelligence in local companies. Our principle is to make AI easy to reach, affordable and all our services are free of charge, neutral and equal for all.

@AI_Hub_Tampere

Augmented monitoring with intelligent machines at CERN (AMIM, 2018-2019)

Recent advances in robotics and AI have opened up new possibilities to develop intelligent machines that are able to perform tasks with very little human involvement. The goal of AMIM is the explore robotics, AI and VR in the context of remote tele-operation in the harsh environments of the Large Hadron Collider (LHC, CERN).

UNITY - Seamless Human-Robot Collaboration (2016-2018)

UNITY enhances industrial robotics with the latest machine learning and machine vision techniques, in order to enable safe interaction and collaboration. Objectives of Unity are:

  • To define what human-robot collaboration means in Finnish heavy industry
  • To build technologies for seamless and safe human-robot interaction using modern robotics and artificial intelligence
  • Increase the human-robot collaboration technology acceptance
  • Educate and motivate future experts into robotics
  • Robot design for trust

    Society is looking ahead in a time when robots are going to be increasingly involved in our lives. For small and toy robots this might seem unintimidating, but when robots get larger and enter our personal space measures have to be taken that convey trust from robot to human. In this project, we aim to build and assess trust in robotic systems in two ways: 1. Trust by physical design: how does the appearance of a robot contribute to the perception people have on its trust? 2. Trust by behavioral design: how do the actions and behavior of a robot contribute to trust?

    Details here

    Human-Robot Interactive Learning

    Programming in advance all possible communication means and synonyms, and integrating fall back mechanisms when confusion arises is tedious and decreases the ease of use, and ease of access to robots. In this work we propose a solution to this communication problem. In particular, we develop a system that can handle new concepts, relate unknown concepts to already existing concepts, and handle synonym concepts. The scenarios we envision are typical service robot queries from human to robot.

    contact Alexandre Angleraud : alexandre.angleraud@tut.fi

    More information

    Autonomous exploration and skills Learning

    The idea here is to investigate the learning of new skills based on autonomous exploration. To do so, we are focusing on Exogenous Attention and taking inspiration from the Sense of Agency emerging in babies. We believe that the Sense of Agency could be the starting point of a good exploration mechanism, and Attention will help to modulates the learning of new skills.

    contact Quentin Houbre : quentin.houbre@tut.fi