Norwegian version of this page

Engineering Predictability with Embodied Cognition (EPEC)

How can multimodal systems sense, learn, and predict future events?

EPEC: engineering predictability with embodied cognition

Humans are superior to computers and robots when it comes to perceiving with eyes, ears and other senses as well as combining perception with learned knowledge to choose the best actions. This project aims to develop human-inspired models of behaviour and perception and to show that these models can predict future actions accurately.

Our inspiration comes from embodied cognition, a concept from psychology proposing that our bodies, perceptions, abilities, and form, influences how we think. Our goal is to exploit the form of various systems to develop predictive reasoning models as alternatives to traditional reactive systems. These models will be applied in interdisciplinary fields of music technology and robotics. In music, we aim to provide everyday people new ways to move within musical spaces. Our models learn about their interactions with smartphones to proactively assist with their future actions. In robotics, we are developing robots with dynamic forms that can change their thinking in response to new body shapes.

EPEC explores applications in musical interaction on smartphones and robotics
Musical interaction on smartphones and robotic systems, are EPEC's application areas for new predictive models.

EPEC is directed by Professor Jim Tørresen, who also leads the ROBIN research group in the Department of Informatics. The project employs two post doctoral fellows, Kai Olav Ellefsen and Charles Martin, and PhD researcher Tønnes Nygaard. The project also includes Associate Professor Kyrre Glette, PhD researcher Jørgen Nordmoen, and a number of masters students in machine learning, robotics and music technology.

Objectives

Design, implement and evaluate multimodal systems that are able to sense, learn and predict future events.

Sub-projects

Master Projects

Researchers from the EPEC group supervise master projects in robotics, music technology, and machine learning. Come work with us on predictive models, embodied interactive systems and new robotic interactions! More information available here.

Funding

Supported by The Research Council of Norway under FRINATEK grant agreement 240862 from 2015 to 2019. The grant funds 1 PhD and 2 post-doc positions (10% of prop. funded).

Tags: machine learning, robotics, interactive music
Published May 24, 2016 3:38 PM - Last modified Nov. 22, 2017 10:07 PM