137
IRUS TotalDownloads
Towards Anchoring Self-Learned Representations to Those of Other Agents
File | Description | Size | Format | |
---|---|---|---|---|
![]() | Accepted version | 2.34 MB | Unknown | View/Open |
Title: | Towards Anchoring Self-Learned Representations to Those of Other Agents |
Authors: | Zambelli, M Fischer, T Petit, M Chang, HJ Cully, A Demiris, Y |
Item Type: | Conference Paper |
Abstract: | In the future, robots will support humans in their every day activities. One particular challenge that robots will face is understanding and reasoning about the actions of other agents in order to cooperate effectively with humans. We propose to tackle this using a developmental framework, where the robot incrementally acquires knowledge, and in particular 1) self-learns a mapping between motor commands and sensory consequences, 2) rapidly acquires primitives and complex actions by verbal descriptions and instructions from a human partner, 3) discovers correspondences between the robots body and other articulated objects and agents, and 4) employs these correspondences to transfer the knowledge acquired from the robots point of view to the viewpoint of the other agent. We show that our approach requires very little a-priori knowledge to achieve imitation learning, to find correspondent body parts of humans, and allows taking the perspective of another agent. This represents a step towards the emergence of a mirror neuron like system based on self-learned representations. |
Issue Date: | 10-Oct-2016 |
Date of Acceptance: | 1-Sep-2016 |
URI: | http://hdl.handle.net/10044/1/40970 |
ISSN: | 2379-8920 |
Publisher: | Institute of Electrical and Electronics Engineers (IEEE) |
Copyright Statement: | © 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
Sponsor/Funder: | Commission of the European Communities |
Funder's Grant Number: | 612139 |
Conference Name: | Workshop on Bio-inspired Social Robot Learning in Home Scenarios IEEE/RSJ International Conference on Intelligent Robots and Systems |
Publication Status: | Published |
Start Date: | 2016-10-10 |
Finish Date: | 2016-10-10 |
Conference Place: | Daejeon, Korea |
Appears in Collections: | Electrical and Electronic Engineering Faculty of Engineering |