Decreasing uncertainty in planning with state prediction

Senka Krivic; Michael  Cashmore; Daniele Magazzeni; Bram Ridder; Sandor Szedmak; Justus Piater

doi:10.24963/ijcai.2017/282

Decreasing uncertainty in planning with state prediction

Senka Krivic, Michael Cashmore, Daniele Magazzeni, Bram Ridder, Sandor Szedmak, Justus Piater

Computer And Information Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

6 Citations (Scopus)

21 Downloads (Pure)

Abstract

In real world environments the state is almost never completely known. Exploration is often expensive. The application of planning in these environments is consequently more difficult and less robust. In this paper we present an approach for predicting new information about a partially-known state. The state is translated into a partially-known multigraph, which can then be extended using machinelearning techniques. We demonstrate the effectiveness of our approach, showing that it enhances the scalability of our planners, and leads to less time spent on sensing actions.

Original language	English
Title of host publication	Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence IJCAI-17
Editors	Carles Sierra
Place of Publication	[US-CA.]
Pages	2032-2038
Number of pages	7
DOIs	https://doi.org/10.24963/ijcai.2017/282
Publication status	Published - 25 Aug 2017
Event	Twenty-Sixth International Joint Conference on Artificial Intelligence IJCAI-17 - Melbourne, Australia Duration: 19 Aug 2017 → 25 Aug 2017

Conference

Conference	Twenty-Sixth International Joint Conference on Artificial Intelligence IJCAI-17
Abbreviated title	IJCAI-17
Country/Territory	Australia
City	Melbourne
Period	19/08/17 → 25/08/17

Keywords

state prediction
uncertainty
machine learning
semi-supervised learning
planning and scheduling
planning under uncertainty
robot planning

Access to Document

10.24963/ijcai.2017/282

Krivic-etal-IJCAI2017-Decreasing-uncertainty-planning-state-predictionAccepted author manuscript, 463 KB

Cite this

@inproceedings{39bc28b5c36e468cbf69103cb659048e,

title = "Decreasing uncertainty in planning with state prediction",

abstract = "In real world environments the state is almost never completely known. Exploration is often expensive. The application of planning in these environments is consequently more difficult and less robust. In this paper we present an approach for predicting new information about a partially-known state. The state is translated into a partially-known multigraph, which can then be extended using machinelearning techniques. We demonstrate the effectiveness of our approach, showing that it enhances the scalability of our planners, and leads to less time spent on sensing actions.",

keywords = "state prediction, uncertainty, machine learning, semi-supervised learning, planning and scheduling, planning under uncertainty, robot planning",

author = "Senka Krivic and Michael Cashmore and Daniele Magazzeni and Bram Ridder and Sandor Szedmak and Justus Piater",

year = "2017",

month = aug,

day = "25",

doi = "10.24963/ijcai.2017/282",

language = "English",

isbn = "9780999241103",

pages = "2032--2038",

editor = "Sierra, {Carles }",

booktitle = "Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence IJCAI-17",

note = "Twenty-Sixth International Joint Conference on Artificial Intelligence IJCAI-17, IJCAI-17 ; Conference date: 19-08-2017 Through 25-08-2017",

}

Krivic, S, Cashmore, M, Magazzeni, D, Ridder, B, Szedmak, S & Piater, J 2017, Decreasing uncertainty in planning with state prediction. in C Sierra (ed.), Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence IJCAI-17. [US-CA.], pp. 2032-2038, Twenty-Sixth International Joint Conference on Artificial Intelligence IJCAI-17, Melbourne, Victoria, Australia, 19/08/17. https://doi.org/10.24963/ijcai.2017/282

TY - GEN

T1 - Decreasing uncertainty in planning with state prediction

AU - Krivic, Senka

AU - Cashmore, Michael

AU - Magazzeni, Daniele

AU - Ridder, Bram

AU - Szedmak, Sandor

AU - Piater, Justus

PY - 2017/8/25

Y1 - 2017/8/25

N2 - In real world environments the state is almost never completely known. Exploration is often expensive. The application of planning in these environments is consequently more difficult and less robust. In this paper we present an approach for predicting new information about a partially-known state. The state is translated into a partially-known multigraph, which can then be extended using machinelearning techniques. We demonstrate the effectiveness of our approach, showing that it enhances the scalability of our planners, and leads to less time spent on sensing actions.

AB - In real world environments the state is almost never completely known. Exploration is often expensive. The application of planning in these environments is consequently more difficult and less robust. In this paper we present an approach for predicting new information about a partially-known state. The state is translated into a partially-known multigraph, which can then be extended using machinelearning techniques. We demonstrate the effectiveness of our approach, showing that it enhances the scalability of our planners, and leads to less time spent on sensing actions.

KW - state prediction

KW - uncertainty

KW - machine learning

KW - semi-supervised learning

KW - planning and scheduling

KW - planning under uncertainty

KW - robot planning

U2 - 10.24963/ijcai.2017/282

DO - 10.24963/ijcai.2017/282

M3 - Conference contribution book

SN - 9780999241103

SP - 2032

EP - 2038

BT - Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence IJCAI-17

A2 - Sierra, Carles

CY - [US-CA.]

T2 - Twenty-Sixth International Joint Conference on Artificial Intelligence IJCAI-17

Y2 - 19 August 2017 through 25 August 2017

ER -

Decreasing uncertainty in planning with state prediction

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this