Towards Anchoring Self-Learned Representations to Those of Other Agents

File Description SizeFormat 
iros-workshop-anchoring-stamped.pdfAccepted version2.34 MBUnknownDownload
Title: Towards Anchoring Self-Learned Representations to Those of Other Agents
Author(s): 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.
Publication 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:Faculty of Engineering
Electrical and Electronic Engineering



Items in Spiral are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commons