Using classical planners for tasks with continuous operators in robotics

Siddharth Srivastava, Lorenzo Riano, Stuart Russell, Pieter Abbeel

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

6 Citations (Scopus)

Abstract

The need for high-level task planning in robotics is well understood. However, interfacing discrete planning with continuous actions often requires extensive engineering of the solution. For instance, picking up an object may require removing many others that obstruct it. Identifying the exact obstructions requires geometric reasoning which is prohibitively expensive to precompute, with results that are difficult to represent efficiently at the level of a discrete planner. We propose a new approach that utilizes representation techniques from first-order logic and provides a method for synchronizing between continuous and discrete planning layers. We evaluate the approach and illustrate its robustness through a number of experiments using a state-of-the-art robotics simulator, accomplishing a variety of challenging tasks like picking objects from cluttered environments, where the planner needs to figure out which other objects need to be moved first to be able to reach the target object, and laying out a table for dinner, where the planner figures out effective tray-loading, navigation and unloading strategies.

Original languageEnglish (US)
Title of host publicationIntelligent Robotic Systems - Papers from the 2013 AAAI Workshop, Technical Report
PublisherAI Access Foundation
Pages85-91
Number of pages7
VolumeWS-13-10
ISBN (Print)9781577356219
StatePublished - Jan 1 2013
Externally publishedYes
Event2013 AAAI Workshop - Bellevue, WA, United States
Duration: Jul 14 2013Jul 15 2013

Other

Other2013 AAAI Workshop
CountryUnited States
CityBellevue, WA
Period7/14/137/15/13

Fingerprint

Robotics
Planning
Unloading
Navigation
Simulators
Experiments

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Srivastava, S., Riano, L., Russell, S., & Abbeel, P. (2013). Using classical planners for tasks with continuous operators in robotics. In Intelligent Robotic Systems - Papers from the 2013 AAAI Workshop, Technical Report (Vol. WS-13-10, pp. 85-91). AI Access Foundation.

Using classical planners for tasks with continuous operators in robotics. / Srivastava, Siddharth; Riano, Lorenzo; Russell, Stuart; Abbeel, Pieter.

Intelligent Robotic Systems - Papers from the 2013 AAAI Workshop, Technical Report. Vol. WS-13-10 AI Access Foundation, 2013. p. 85-91.

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

Srivastava, S, Riano, L, Russell, S & Abbeel, P 2013, Using classical planners for tasks with continuous operators in robotics. in Intelligent Robotic Systems - Papers from the 2013 AAAI Workshop, Technical Report. vol. WS-13-10, AI Access Foundation, pp. 85-91, 2013 AAAI Workshop, Bellevue, WA, United States, 7/14/13.
Srivastava S, Riano L, Russell S, Abbeel P. Using classical planners for tasks with continuous operators in robotics. In Intelligent Robotic Systems - Papers from the 2013 AAAI Workshop, Technical Report. Vol. WS-13-10. AI Access Foundation. 2013. p. 85-91
Srivastava, Siddharth ; Riano, Lorenzo ; Russell, Stuart ; Abbeel, Pieter. / Using classical planners for tasks with continuous operators in robotics. Intelligent Robotic Systems - Papers from the 2013 AAAI Workshop, Technical Report. Vol. WS-13-10 AI Access Foundation, 2013. pp. 85-91
@inproceedings{ff419aaf56c04082b3c359d36497d4a3,
title = "Using classical planners for tasks with continuous operators in robotics",
abstract = "The need for high-level task planning in robotics is well understood. However, interfacing discrete planning with continuous actions often requires extensive engineering of the solution. For instance, picking up an object may require removing many others that obstruct it. Identifying the exact obstructions requires geometric reasoning which is prohibitively expensive to precompute, with results that are difficult to represent efficiently at the level of a discrete planner. We propose a new approach that utilizes representation techniques from first-order logic and provides a method for synchronizing between continuous and discrete planning layers. We evaluate the approach and illustrate its robustness through a number of experiments using a state-of-the-art robotics simulator, accomplishing a variety of challenging tasks like picking objects from cluttered environments, where the planner needs to figure out which other objects need to be moved first to be able to reach the target object, and laying out a table for dinner, where the planner figures out effective tray-loading, navigation and unloading strategies.",
author = "Siddharth Srivastava and Lorenzo Riano and Stuart Russell and Pieter Abbeel",
year = "2013",
month = "1",
day = "1",
language = "English (US)",
isbn = "9781577356219",
volume = "WS-13-10",
pages = "85--91",
booktitle = "Intelligent Robotic Systems - Papers from the 2013 AAAI Workshop, Technical Report",
publisher = "AI Access Foundation",
address = "United States",

}

TY - GEN

T1 - Using classical planners for tasks with continuous operators in robotics

AU - Srivastava, Siddharth

AU - Riano, Lorenzo

AU - Russell, Stuart

AU - Abbeel, Pieter

PY - 2013/1/1

Y1 - 2013/1/1

N2 - The need for high-level task planning in robotics is well understood. However, interfacing discrete planning with continuous actions often requires extensive engineering of the solution. For instance, picking up an object may require removing many others that obstruct it. Identifying the exact obstructions requires geometric reasoning which is prohibitively expensive to precompute, with results that are difficult to represent efficiently at the level of a discrete planner. We propose a new approach that utilizes representation techniques from first-order logic and provides a method for synchronizing between continuous and discrete planning layers. We evaluate the approach and illustrate its robustness through a number of experiments using a state-of-the-art robotics simulator, accomplishing a variety of challenging tasks like picking objects from cluttered environments, where the planner needs to figure out which other objects need to be moved first to be able to reach the target object, and laying out a table for dinner, where the planner figures out effective tray-loading, navigation and unloading strategies.

AB - The need for high-level task planning in robotics is well understood. However, interfacing discrete planning with continuous actions often requires extensive engineering of the solution. For instance, picking up an object may require removing many others that obstruct it. Identifying the exact obstructions requires geometric reasoning which is prohibitively expensive to precompute, with results that are difficult to represent efficiently at the level of a discrete planner. We propose a new approach that utilizes representation techniques from first-order logic and provides a method for synchronizing between continuous and discrete planning layers. We evaluate the approach and illustrate its robustness through a number of experiments using a state-of-the-art robotics simulator, accomplishing a variety of challenging tasks like picking objects from cluttered environments, where the planner needs to figure out which other objects need to be moved first to be able to reach the target object, and laying out a table for dinner, where the planner figures out effective tray-loading, navigation and unloading strategies.

UR - http://www.scopus.com/inward/record.url?scp=84898879871&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898879871&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84898879871

SN - 9781577356219

VL - WS-13-10

SP - 85

EP - 91

BT - Intelligent Robotic Systems - Papers from the 2013 AAAI Workshop, Technical Report

PB - AI Access Foundation

ER -