Using Simplified Models and Limited-Horizon Planning to React to Time-Critical Problems

<p> A longstanding goal of robotics is to use robots to perform tasks that require physically interacting with humans. These tasks often require robots to physically manipulate humans, for example in the task of guiding an elderly human and preventing the human from falling. This particular ta...

Full description

Bibliographic Details
Main Author: Lurz, Joshua Paul
Language:EN
Published: The George Washington University 2018
Subjects:
Online Access:http://pqdtopen.proquest.com/#viewpdf?dispub=13419796
id ndltd-PROQUEST-oai-pqdtoai.proquest.com-13419796
record_format oai_dc
spelling ndltd-PROQUEST-oai-pqdtoai.proquest.com-134197962018-12-21T04:24:58Z Using Simplified Models and Limited-Horizon Planning to React to Time-Critical Problems Lurz, Joshua Paul Robotics <p> A longstanding goal of robotics is to use robots to perform tasks that require physically interacting with humans. These tasks often require robots to physically manipulate humans, for example in the task of guiding an elderly human and preventing the human from falling. This particular task is of significant importance due to the prevalence of falls and the expanding need for elderly care as the elderly cohort expands in many developed countries. At present, robots have very limited capabilities to support these types of tasks. Current planning approaches are challenged by the intrinsic features of these problems: the control policies of the dynamic agent are unknown, the state information is incomplete, and a rapid reaction time is required. </p><p> This thesis describes an approach to solving these challenges by using simplified models of the dynamic agents and environments that are reasonably accurate over brief time frames. It couples these models with limited-horizon planning. My approach allows for rapid updates of execution plans, which are required due to the short time horizons over which the plans are accurate. This dissertation validates my approach using a series of tasks that require robots to interact with dynamic agents, including a simulation of catching a falling human.</p><p> The George Washington University 2018-12-20 00:00:00.0 thesis http://pqdtopen.proquest.com/#viewpdf?dispub=13419796 EN
collection NDLTD
language EN
sources NDLTD
topic Robotics
spellingShingle Robotics
Lurz, Joshua Paul
Using Simplified Models and Limited-Horizon Planning to React to Time-Critical Problems
description <p> A longstanding goal of robotics is to use robots to perform tasks that require physically interacting with humans. These tasks often require robots to physically manipulate humans, for example in the task of guiding an elderly human and preventing the human from falling. This particular task is of significant importance due to the prevalence of falls and the expanding need for elderly care as the elderly cohort expands in many developed countries. At present, robots have very limited capabilities to support these types of tasks. Current planning approaches are challenged by the intrinsic features of these problems: the control policies of the dynamic agent are unknown, the state information is incomplete, and a rapid reaction time is required. </p><p> This thesis describes an approach to solving these challenges by using simplified models of the dynamic agents and environments that are reasonably accurate over brief time frames. It couples these models with limited-horizon planning. My approach allows for rapid updates of execution plans, which are required due to the short time horizons over which the plans are accurate. This dissertation validates my approach using a series of tasks that require robots to interact with dynamic agents, including a simulation of catching a falling human.</p><p>
author Lurz, Joshua Paul
author_facet Lurz, Joshua Paul
author_sort Lurz, Joshua Paul
title Using Simplified Models and Limited-Horizon Planning to React to Time-Critical Problems
title_short Using Simplified Models and Limited-Horizon Planning to React to Time-Critical Problems
title_full Using Simplified Models and Limited-Horizon Planning to React to Time-Critical Problems
title_fullStr Using Simplified Models and Limited-Horizon Planning to React to Time-Critical Problems
title_full_unstemmed Using Simplified Models and Limited-Horizon Planning to React to Time-Critical Problems
title_sort using simplified models and limited-horizon planning to react to time-critical problems
publisher The George Washington University
publishDate 2018
url http://pqdtopen.proquest.com/#viewpdf?dispub=13419796
work_keys_str_mv AT lurzjoshuapaul usingsimplifiedmodelsandlimitedhorizonplanningtoreacttotimecriticalproblems
_version_ 1718804043864735744