Food & Paper: Introducing Predictive and Intuitive Properties in Robots – a new Research Council of Norway project (Jim Tørresen)

Professor Jim Tørresen (RITMO/IFI) will give this week's Food & Paper.

Jim Tørresen

Abstract

Predictive and Intuitive Robot Companion (PIRC) is a newly funded Research Council of Norway project that is integrated with RITMO. Three PhD/researchers are to be hired within the project period 2020-2025. The Food and Paper talk will introduce the project and background work for the concepts and applications to be studied in the project.

Project Summary

PIRC targets a psychology-inspired computing breakthrough through research combining insight from cognitive psychology with computational intelligence to build models that forecast future events and respond dynamically. The systems will be aware and alert for how to best act given their knowledge about themselves and perception of their environment. Humans anticipate future events more effectively than computers. We combine sensing across multiple modalities with learned knowledge to predict outcomes and choose the best actions. Can we transfer these skills to intelligent systems in human-interactive scenarios? In PIRC, we will apply our machine learning and robotics expertise, and collaborate with researchers in cognitive psychology, to apply recent models of human prediction to perception-action loops of future intelligent robot companions. Our work will allow such robots to adapt and act more seamlessly with their environment than the current technology. We will equip the robRobot giving pen to womanots with these new skills and in addition, provide them with the knowledge that users they are interacting with, apply the same mechanisms. This will include mechanisms for adaptive response time from quick and intuitive to slower and well-reasoned. The models will be applied in two robotics applications with potential for very wide impact: physical rehabilitation and home care robot support for older people. 

Published Sep. 23, 2020 1:58 PM - Last modified Nov. 6, 2020 7:48 AM