2022
DOI: 10.1007/s10514-022-10039-8
|View full text |Cite
|
Sign up to set email alerts
|

Motion planning and control for mobile robot navigation using machine learning: a survey

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
53
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
3
3
2

Relationship

2
6

Authors

Journals

citations
Cited by 136 publications
(53 citation statements)
references
References 84 publications
0
53
0
Order By: Relevance
“…Recently, several algorithms have emerged that show the potential of applying learning to address challenges in robot navigation [2]. Broadly speaking, in the robot navigation literature, learning-based approaches have been shown to be successful in problems such as adaptive planner parameter learning [16], overcoming viewpoint invariance in demonstrations [13], and end-to-end learning for autonomous driving [14], [17], [18].…”
Section: A Learning For Robot Navigationmentioning
confidence: 99%
See 1 more Smart Citation
“…Recently, several algorithms have emerged that show the potential of applying learning to address challenges in robot navigation [2]. Broadly speaking, in the robot navigation literature, learning-based approaches have been shown to be successful in problems such as adaptive planner parameter learning [16], overcoming viewpoint invariance in demonstrations [13], and end-to-end learning for autonomous driving [14], [17], [18].…”
Section: A Learning For Robot Navigationmentioning
confidence: 99%
“…1, can be a valuable resource. For instance, such 1 The University of Texas at Austin, Department of Mechanical Engineering haresh.miriyala@utexas.edu 2 The University of Texas at Austin, Department of Computer Science, ani.nair@utexas.edu, {xiao, joydeepb, hart, pstone}@cs.utexas.edu 3 Robotics@Google {toshev, pirk}@google.com 4 Sony AI 5 Computational and Information Sciences Directorate, Army Research Laboratory garrett.a.warnell.civ@army.mil demonstration information can be used to learn socially compliant robot navigation using the paradigm of Learning from Demonstrations (LfD) [6], [7] or understanding human navigation in the presence of autonomous robots [8]. Datasets for social navigation, generally used for learning and benchmarking, include data collected both in the realworld [9] and in simulated environments [10], [11].…”
Section: Introductionmentioning
confidence: 99%
“…The use of machine learning methods in the design of autonomous navigation systems goes back several decades, though recent years have seen a spike in interest from the research community [2], [3], [11], [12]. One of the earliest successes was reported by Pomerleau [13], in which a system called ALVINN used imitation learning to train an artificial neural network that could perform lane keeping based on demonstration data generated in simulation.…”
Section: A Machine Learning For Autonomous Navigationmentioning
confidence: 99%
“…One candidate approach to learning and navigation is to replace the traditionally engineered system with an end-to-end sensor to decision neural network [3]- [6]. Empirical and limited benchmarking show some promise on this front.…”
Section: A Research Context 1) Navigation and Machine Learningmentioning
confidence: 99%
“…Overall, there is no substantive benchmarking of learning based methods with traditional navigation schemes [6]. Thus, the assertions that learning can overcome sensitivity to environmental conditions and can outperform traditionally engineered systems remains unconfirmed.…”
mentioning
confidence: 99%