Autonomous Two-Stage Object Retrieval Using Supervised and Reinforcement Learning

Humans have been sending tele-operated robots into hazardous areas in an attempt to preserve life for many years. The task they are presented with is often challenging and requires cognitive abilities, that is, the ability to process information in order to apply it to a different situation. In this...

Full description

Bibliographic Details
Main Authors: Rouillard, T., Howard, Ian, Cui, Lei
Format: Conference Paper
Language:English
Published: IEEE 2019
Subjects:
Online Access:http://purl.org/au-research/grants/arc/DE170101062
http://hdl.handle.net/20.500.11937/80592
_version_ 1848764240885710848
author Rouillard, T.
Howard, Ian
Cui, Lei
author_facet Rouillard, T.
Howard, Ian
Cui, Lei
author_sort Rouillard, T.
building Curtin Institutional Repository
collection Online Access
description Humans have been sending tele-operated robots into hazardous areas in an attempt to preserve life for many years. The task they are presented with is often challenging and requires cognitive abilities, that is, the ability to process information in order to apply it to a different situation. In this work, we proposed an autonomous approach employing both supervised and reinforcement learning for hidden-object retrieval in two stages. Stage 1 used both learning methods to find a hidden object whereas stage 2 only used reinforcement learning to isolate it. The method is targeted towards field robots with reduced computational power hence we explored the viability of tabular reinforcement learning algorithms. We used a convolutional neural network (CNN) to interpret the state of the scene from images and a reinforcement learning agent for each stage of the task. The robot was presented with a workspace containing piles of rubble under one of which an object was buried. The robot must learn to find and isolate it. We compared the performance of four reinforcement learning algorithms over 500 episodes and found that Sarsa (λ) and RMax were most appropriate for stage 1 and 2 respectively. The approach allowed a robot to learn to complete a search and retrieval task by interpreting images. This could lead to the deployment of such robots in disaster areas eliminating the need for tele-operated platforms.
first_indexed 2025-11-14T11:16:13Z
format Conference Paper
id curtin-20.500.11937-80592
institution Curtin University Malaysia
institution_category Local University
language English
last_indexed 2025-11-14T11:16:13Z
publishDate 2019
publisher IEEE
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-805922022-10-06T04:03:51Z Autonomous Two-Stage Object Retrieval Using Supervised and Reinforcement Learning Rouillard, T. Howard, Ian Cui, Lei Science & Technology Technology Automation & Control Systems Engineering, Electrical & Electronic Robotics Engineering Intelligent robots Reinforcement learning Computer vision Robotic Manipulation ALGORITHM Humans have been sending tele-operated robots into hazardous areas in an attempt to preserve life for many years. The task they are presented with is often challenging and requires cognitive abilities, that is, the ability to process information in order to apply it to a different situation. In this work, we proposed an autonomous approach employing both supervised and reinforcement learning for hidden-object retrieval in two stages. Stage 1 used both learning methods to find a hidden object whereas stage 2 only used reinforcement learning to isolate it. The method is targeted towards field robots with reduced computational power hence we explored the viability of tabular reinforcement learning algorithms. We used a convolutional neural network (CNN) to interpret the state of the scene from images and a reinforcement learning agent for each stage of the task. The robot was presented with a workspace containing piles of rubble under one of which an object was buried. The robot must learn to find and isolate it. We compared the performance of four reinforcement learning algorithms over 500 episodes and found that Sarsa (λ) and RMax were most appropriate for stage 1 and 2 respectively. The approach allowed a robot to learn to complete a search and retrieval task by interpreting images. This could lead to the deployment of such robots in disaster areas eliminating the need for tele-operated platforms. 2019 Conference Paper http://hdl.handle.net/20.500.11937/80592 10.1109/ICMA.2019.8816290 English http://purl.org/au-research/grants/arc/DE170101062 IEEE restricted
spellingShingle Science & Technology
Technology
Automation & Control Systems
Engineering, Electrical & Electronic
Robotics
Engineering
Intelligent robots
Reinforcement learning
Computer vision
Robotic Manipulation
ALGORITHM
Rouillard, T.
Howard, Ian
Cui, Lei
Autonomous Two-Stage Object Retrieval Using Supervised and Reinforcement Learning
title Autonomous Two-Stage Object Retrieval Using Supervised and Reinforcement Learning
title_full Autonomous Two-Stage Object Retrieval Using Supervised and Reinforcement Learning
title_fullStr Autonomous Two-Stage Object Retrieval Using Supervised and Reinforcement Learning
title_full_unstemmed Autonomous Two-Stage Object Retrieval Using Supervised and Reinforcement Learning
title_short Autonomous Two-Stage Object Retrieval Using Supervised and Reinforcement Learning
title_sort autonomous two-stage object retrieval using supervised and reinforcement learning
topic Science & Technology
Technology
Automation & Control Systems
Engineering, Electrical & Electronic
Robotics
Engineering
Intelligent robots
Reinforcement learning
Computer vision
Robotic Manipulation
ALGORITHM
url http://purl.org/au-research/grants/arc/DE170101062
http://hdl.handle.net/20.500.11937/80592