ICRA'09 Paper Abstract


Paper FrB7.5

Kollar, Thomas (MIT), Roy, Nicholas (Massachusetts Institute of Technology)

Utilizing object-object and object-scene context when planning to find things

Scheduled for presentation during the Regular Sessions "Robot Companions and Social Robots in Home Environments" (FrB7), Friday, May 15, 2009, 11:50−12:10, Room: 405

2009 IEEE International Conference on Robotics and Automation, May 12 - 17, 2009, Kobe, Japan

This information is tentative and subject to change. Compiled on January 21, 2022

Keywords Robot Companions and Social Robots in Home Environments, Motion and Path Planning, Social Human-Robot Interaction


In this paper, our goal is to search for a novel object, where we have a prior map of the environment and knowledge of some of the objects in it, but no information about the location of the specific novel object. We develop a probabilistic model over possible object locations that utilizes object-object and object-scene context. This model can be queried for any of the over 25,000 naturally occurring objects in the world and is trained from labeled data acquired from photos downloaded from the Flickr website. We show that even these simple models perform surprisingly well at localizing arbitrary objects in an office setting. In addition, we show how to compute paths that will minimize the expected distance to the query object and show that this approach performs better than the greedy approach. Finally, we will give preliminary results for grounding our approach in object classifiers.



Technical Content © IEEE Robotics & Automation Society

This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2022 PaperCept, Inc.
Page generated 2022-01-21  08:46:22 PST  Terms of use