Replanning for situated robots

Michael Cashmore, Andrew Coles, Bence Cserna, Erez Karpas, Daniele Magazzeni, Wheeler Ruml

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

1 Downloads (Pure)

Abstract

Planning enables intelligent agents, such as robots, to act so as to achieve their long term goals. To make the planning process tractable, a relatively low fidelity model of the world is often used, which sometimes leads to the need to replan. The typical view of replanning is that the robot is given the current state, the goal, and possibly some data from the previous planning process. However, for robots (or teams of robots) that exist in continuous physical space, act concurrently, have deadlines, or must otherwise consider durative actions, things are not so simple. In this paper, we address the problem of replanning for situated robots. Relying on previous work on situated temporal planning, we frame the replanning problem as a situated temporal planning problem, where currently executing actions are handled via Timed Initial Literals (TILs), under the assumption that actions cannot be interrupted. We then relax this assumption, and address situated replanning with interruptible actions. We bridge the gap between the low-level model of the robot and the high-level model used for planning by the novel notion of a bail out action generator, which relies on the low-level model to generate highlevel actions that describe possible ways to interrupt currently executing actions. Because actions can be interrupted at different times during their execution, we also propose a novel algorithm to handle temporal planning with time-dependent durations.
Original languageEnglish
Title of host publicationProceedings of the Twenty-Ninth International Conference on Automated Planning and Scheduling (ICAPS) 2019
Place of PublicationMenlo Park, US-CA.
Number of pages9
Publication statusPublished - 11 Jul 2019
Event29th International Conference on Automated Planning and Scheduling - ICAPS 2019 - Berkeley, United States
Duration: 11 Jul 201915 Jul 2019

Conference

Conference29th International Conference on Automated Planning and Scheduling - ICAPS 2019
Abbreviated titleICAPS 2019
CountryUnited States
CityBerkeley
Period11/07/1915/07/19

Fingerprint

Robots
Planning
Intelligent agents

Keywords

  • replanning
  • robots
  • intelligent agents
  • situated temporal planning

Cite this

Cashmore, M., Coles, A., Cserna, B., Karpas, E., Magazzeni, D., & Ruml, W. (2019). Replanning for situated robots. In Proceedings of the Twenty-Ninth International Conference on Automated Planning and Scheduling (ICAPS) 2019 Menlo Park, US-CA..
Cashmore, Michael ; Coles, Andrew ; Cserna, Bence ; Karpas, Erez ; Magazzeni, Daniele ; Ruml, Wheeler. / Replanning for situated robots. Proceedings of the Twenty-Ninth International Conference on Automated Planning and Scheduling (ICAPS) 2019. Menlo Park, US-CA., 2019.
@inproceedings{dc042d223ad44c5e9c60945d4e4cb59c,
title = "Replanning for situated robots",
abstract = "Planning enables intelligent agents, such as robots, to act so as to achieve their long term goals. To make the planning process tractable, a relatively low fidelity model of the world is often used, which sometimes leads to the need to replan. The typical view of replanning is that the robot is given the current state, the goal, and possibly some data from the previous planning process. However, for robots (or teams of robots) that exist in continuous physical space, act concurrently, have deadlines, or must otherwise consider durative actions, things are not so simple. In this paper, we address the problem of replanning for situated robots. Relying on previous work on situated temporal planning, we frame the replanning problem as a situated temporal planning problem, where currently executing actions are handled via Timed Initial Literals (TILs), under the assumption that actions cannot be interrupted. We then relax this assumption, and address situated replanning with interruptible actions. We bridge the gap between the low-level model of the robot and the high-level model used for planning by the novel notion of a bail out action generator, which relies on the low-level model to generate highlevel actions that describe possible ways to interrupt currently executing actions. Because actions can be interrupted at different times during their execution, we also propose a novel algorithm to handle temporal planning with time-dependent durations.",
keywords = "replanning, robots, intelligent agents, situated temporal planning",
author = "Michael Cashmore and Andrew Coles and Bence Cserna and Erez Karpas and Daniele Magazzeni and Wheeler Ruml",
year = "2019",
month = "7",
day = "11",
language = "English",
booktitle = "Proceedings of the Twenty-Ninth International Conference on Automated Planning and Scheduling (ICAPS) 2019",

}

Cashmore, M, Coles, A, Cserna, B, Karpas, E, Magazzeni, D & Ruml, W 2019, Replanning for situated robots. in Proceedings of the Twenty-Ninth International Conference on Automated Planning and Scheduling (ICAPS) 2019. Menlo Park, US-CA., 29th International Conference on Automated Planning and Scheduling - ICAPS 2019, Berkeley, United States, 11/07/19.

Replanning for situated robots. / Cashmore, Michael; Coles, Andrew; Cserna, Bence; Karpas, Erez; Magazzeni, Daniele; Ruml, Wheeler.

Proceedings of the Twenty-Ninth International Conference on Automated Planning and Scheduling (ICAPS) 2019. Menlo Park, US-CA., 2019.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - Replanning for situated robots

AU - Cashmore, Michael

AU - Coles, Andrew

AU - Cserna, Bence

AU - Karpas, Erez

AU - Magazzeni, Daniele

AU - Ruml, Wheeler

PY - 2019/7/11

Y1 - 2019/7/11

N2 - Planning enables intelligent agents, such as robots, to act so as to achieve their long term goals. To make the planning process tractable, a relatively low fidelity model of the world is often used, which sometimes leads to the need to replan. The typical view of replanning is that the robot is given the current state, the goal, and possibly some data from the previous planning process. However, for robots (or teams of robots) that exist in continuous physical space, act concurrently, have deadlines, or must otherwise consider durative actions, things are not so simple. In this paper, we address the problem of replanning for situated robots. Relying on previous work on situated temporal planning, we frame the replanning problem as a situated temporal planning problem, where currently executing actions are handled via Timed Initial Literals (TILs), under the assumption that actions cannot be interrupted. We then relax this assumption, and address situated replanning with interruptible actions. We bridge the gap between the low-level model of the robot and the high-level model used for planning by the novel notion of a bail out action generator, which relies on the low-level model to generate highlevel actions that describe possible ways to interrupt currently executing actions. Because actions can be interrupted at different times during their execution, we also propose a novel algorithm to handle temporal planning with time-dependent durations.

AB - Planning enables intelligent agents, such as robots, to act so as to achieve their long term goals. To make the planning process tractable, a relatively low fidelity model of the world is often used, which sometimes leads to the need to replan. The typical view of replanning is that the robot is given the current state, the goal, and possibly some data from the previous planning process. However, for robots (or teams of robots) that exist in continuous physical space, act concurrently, have deadlines, or must otherwise consider durative actions, things are not so simple. In this paper, we address the problem of replanning for situated robots. Relying on previous work on situated temporal planning, we frame the replanning problem as a situated temporal planning problem, where currently executing actions are handled via Timed Initial Literals (TILs), under the assumption that actions cannot be interrupted. We then relax this assumption, and address situated replanning with interruptible actions. We bridge the gap between the low-level model of the robot and the high-level model used for planning by the novel notion of a bail out action generator, which relies on the low-level model to generate highlevel actions that describe possible ways to interrupt currently executing actions. Because actions can be interrupted at different times during their execution, we also propose a novel algorithm to handle temporal planning with time-dependent durations.

KW - replanning

KW - robots

KW - intelligent agents

KW - situated temporal planning

M3 - Conference contribution book

BT - Proceedings of the Twenty-Ninth International Conference on Automated Planning and Scheduling (ICAPS) 2019

CY - Menlo Park, US-CA.

ER -

Cashmore M, Coles A, Cserna B, Karpas E, Magazzeni D, Ruml W. Replanning for situated robots. In Proceedings of the Twenty-Ninth International Conference on Automated Planning and Scheduling (ICAPS) 2019. Menlo Park, US-CA. 2019