2021
DOI: 10.1109/access.2021.3053396
|View full text |Cite
|
Sign up to set email alerts
|

A Hybrid Tracking Control Strategy for Nonholonomic Wheeled Mobile Robot Incorporating Deep Reinforcement Learning Approach

Abstract: Tracking control is an essential capability for nonholonomic wheeled mobile robots (NWMR) to achieve autonomous navigation. This paper presents a novel hybrid control strategy combined modebased control and actor-critic based deep reinforcement learning method. Based on the Lyapunov method, a kinematics control law named given control is obtained with pose errors. Then, the tracking control problem is converted to a finite Markov decision process, in which the defined state contains current tracking errors, gi… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4

Citation Types

0
9
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
8
2

Relationship

0
10

Authors

Journals

citations
Cited by 19 publications
(9 citation statements)
references
References 31 publications
(29 reference statements)
0
9
0
Order By: Relevance
“…Not all planning algorithms are appropriate for every situation and include many factors affected by the site. How to plan the safety process quickly and efficiently is the key to completing the project [3]. Currently, a lot of research has been done in the field of mobile robot planning at home and abroad, and good results have been achieved.…”
Section: Introductionmentioning
confidence: 99%
“…Not all planning algorithms are appropriate for every situation and include many factors affected by the site. How to plan the safety process quickly and efficiently is the key to completing the project [3]. Currently, a lot of research has been done in the field of mobile robot planning at home and abroad, and good results have been achieved.…”
Section: Introductionmentioning
confidence: 99%
“…shows an example of agent action space based on grid representation. Since space has been quantified as tiny grid units, the action of the agent only needs to decide which direction of the adjacent grid to move in the next moment [14]. At this time, the action of the agent at time t can be represented by a discrete value, for example, α t = 1 represents up, α t = 2 represents right, α t = 3 represents down, and α t = 4 represents left.…”
mentioning
confidence: 99%
“…Control feedback based on multiple tracking error inputs has been investigated in refs. [15][16][17][18], whereas alternative methods such as direct utilization of camera feeds or LiDAR measurements as inputs have also been explored in refs. [19][20][21][22][23][24].…”
Section: Introductionmentioning
confidence: 99%