Policy iteration-based integral reinforcement learning for online adaptive trajectory tracking of mobile robot
This paper considers trajectory tracking control for a nonholonomic mobile robot using integral reinforcement learning (IRL) based on a value functional represented by integrating a local cost. The tracking error dynamics between the robot and reference trajectories takes the form of time-invariant...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Taylor & Francis Group
2021-01-01
|
Series: | SICE Journal of Control, Measurement, and System Integration |
Subjects: | |
Online Access: | http://dx.doi.org/10.1080/18824889.2021.1972266 |
_version_ | 1797661066622140416 |
---|---|
author | Tatsuki Ashida Hiroyuki Ichihara |
author_facet | Tatsuki Ashida Hiroyuki Ichihara |
author_sort | Tatsuki Ashida |
collection | DOAJ |
description | This paper considers trajectory tracking control for a nonholonomic mobile robot using integral reinforcement learning (IRL) based on a value functional represented by integrating a local cost. The tracking error dynamics between the robot and reference trajectories takes the form of time-invariant input-affine continuous-time nonlinear systems if the reference trajectory counterpart of the translational and angular velocities are constant. This paper applies integral reinforcement learning to the tracking error dynamics by approximating the value functional from the data collected along the robot trajectory. The paper proposes a specific procedure to implement the IRL-based policy iteration online, including a batch least-squares minimization. The approximate value function updates the control policy to compensate for the translational and angular velocities that drive the robot. Numerical examples illustrate to demonstrate the tracking performance of integral reinforcement learning. |
first_indexed | 2024-03-11T18:39:55Z |
format | Article |
id | doaj.art-85cf5f062a804a03bfb4426da9549141 |
institution | Directory Open Access Journal |
issn | 1884-9970 |
language | English |
last_indexed | 2024-03-11T18:39:55Z |
publishDate | 2021-01-01 |
publisher | Taylor & Francis Group |
record_format | Article |
series | SICE Journal of Control, Measurement, and System Integration |
spelling | doaj.art-85cf5f062a804a03bfb4426da95491412023-10-12T13:43:52ZengTaylor & Francis GroupSICE Journal of Control, Measurement, and System Integration1884-99702021-01-0114123324110.1080/18824889.2021.19722661972266Policy iteration-based integral reinforcement learning for online adaptive trajectory tracking of mobile robotTatsuki Ashida0Hiroyuki Ichihara1Meiji UniversityMeiji UniversityThis paper considers trajectory tracking control for a nonholonomic mobile robot using integral reinforcement learning (IRL) based on a value functional represented by integrating a local cost. The tracking error dynamics between the robot and reference trajectories takes the form of time-invariant input-affine continuous-time nonlinear systems if the reference trajectory counterpart of the translational and angular velocities are constant. This paper applies integral reinforcement learning to the tracking error dynamics by approximating the value functional from the data collected along the robot trajectory. The paper proposes a specific procedure to implement the IRL-based policy iteration online, including a batch least-squares minimization. The approximate value function updates the control policy to compensate for the translational and angular velocities that drive the robot. Numerical examples illustrate to demonstrate the tracking performance of integral reinforcement learning.http://dx.doi.org/10.1080/18824889.2021.1972266integral reinforcement learningadaptive dynamic programmingmobile robottrajectory trackingpolicy iterationcontinuous-time system |
spellingShingle | Tatsuki Ashida Hiroyuki Ichihara Policy iteration-based integral reinforcement learning for online adaptive trajectory tracking of mobile robot SICE Journal of Control, Measurement, and System Integration integral reinforcement learning adaptive dynamic programming mobile robot trajectory tracking policy iteration continuous-time system |
title | Policy iteration-based integral reinforcement learning for online adaptive trajectory tracking of mobile robot |
title_full | Policy iteration-based integral reinforcement learning for online adaptive trajectory tracking of mobile robot |
title_fullStr | Policy iteration-based integral reinforcement learning for online adaptive trajectory tracking of mobile robot |
title_full_unstemmed | Policy iteration-based integral reinforcement learning for online adaptive trajectory tracking of mobile robot |
title_short | Policy iteration-based integral reinforcement learning for online adaptive trajectory tracking of mobile robot |
title_sort | policy iteration based integral reinforcement learning for online adaptive trajectory tracking of mobile robot |
topic | integral reinforcement learning adaptive dynamic programming mobile robot trajectory tracking policy iteration continuous-time system |
url | http://dx.doi.org/10.1080/18824889.2021.1972266 |
work_keys_str_mv | AT tatsukiashida policyiterationbasedintegralreinforcementlearningforonlineadaptivetrajectorytrackingofmobilerobot AT hiroyukiichihara policyiterationbasedintegralreinforcementlearningforonlineadaptivetrajectorytrackingofmobilerobot |