Distributed Koopman Learning using Partial Trajectories for Control Article Swipe

PDF

Wenjian Hao , Zehui Lu , Devesh Upadhyay , Shaoshuai Mou ·

YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2412.07212

This paper proposes a distributed data-driven framework for dynamics learning, termed distributed deep Koopman learning using partial trajectories (DDKL-PT). In this framework, each agent in a multi-agent system is assigned a partial trajectory offline and locally approximates the unknown dynamics using a deep neural network within the Koopman operator framework. By exchanging local estimated dynamics rather than training data, agents achieve consensus on a global dynamics model without sharing their private training trajectories. Simulation studies on a surface vehicle demonstrate that DDKL-PT attains consensus with respect to the learned dynamics, with each agent achieving reasonably small approximation errors over the testing data. Furthermore, a model predictive control scheme is developed by integrating the learned Koopman dynamics with known kinematic relations. Results on goal-tracking and station-keeping tasks support that the distributedly learned dynamics are sufficiently accurate for model-based optimal control.

Related Topics

Computer Science

Algorithm

Artificial Intelligence

Deep Learning

Concepts

Computer science Algorithm Control (management) Artificial intelligence Deep learning

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2412.07212
PDF: https://arxiv.org/pdf/2412.07212
OA Status: green
Related Works: 10
OpenAlex ID: https://openalex.org/W4405255164

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4405255164

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2412.07212

Digital Object Identifier
Title: Distributed Koopman Learning using Partial Trajectories for Control

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2024

Year of publication
Publication date: 2024-12-10

Full publication date if available
Authors: Wenjian Hao, Zehui Lu, Devesh Upadhyay, Shaoshuai Mou

List of authors in order
Landing page: https://arxiv.org/abs/2412.07212

Publisher landing page
PDF URL: https://arxiv.org/pdf/2412.07212

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2412.07212

Direct OA link when available
Concepts: Computer science, Algorithm, Control (management), Artificial intelligence, Deep learning

Top concepts (fields/topics) attached by OpenAlex
Cited by: 0

Total citation count in OpenAlex
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4405255164
doi	https://doi.org/10.48550/arxiv.2412.07212
ids.doi	https://doi.org/10.48550/arxiv.2412.07212
ids.openalex	https://openalex.org/W4405255164
fwci
type	preprint
title	Distributed Koopman Learning using Partial Trajectories for Control
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T10320
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.7562999725341797
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1702
topics[0].subfield.display_name	Artificial Intelligence
topics[0].display_name	Neural Networks and Applications
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C41008148
concepts[0].level	0
concepts[0].score	0.5643995404243469
concepts[0].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[0].display_name	Computer science
concepts[1].id	https://openalex.org/C11413529
concepts[1].level	1
concepts[1].score	0.5215808749198914
concepts[1].wikidata	https://www.wikidata.org/wiki/Q8366
concepts[1].display_name	Algorithm
concepts[2].id	https://openalex.org/C2775924081
concepts[2].level	2
concepts[2].score	0.5053256154060364
concepts[2].wikidata	https://www.wikidata.org/wiki/Q55608371
concepts[2].display_name	Control (management)
concepts[3].id	https://openalex.org/C154945302
concepts[3].level	1
concepts[3].score	0.4465835690498352
concepts[3].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[3].display_name	Artificial intelligence
concepts[4].id	https://openalex.org/C108583219
concepts[4].level	2
concepts[4].score	0.43961483240127563
concepts[4].wikidata	https://www.wikidata.org/wiki/Q197536
concepts[4].display_name	Deep learning
keywords[0].id	https://openalex.org/keywords/computer-science
keywords[0].score	0.5643995404243469
keywords[0].display_name	Computer science
keywords[1].id	https://openalex.org/keywords/algorithm
keywords[1].score	0.5215808749198914
keywords[1].display_name	Algorithm
keywords[2].id	https://openalex.org/keywords/control
keywords[2].score	0.5053256154060364
keywords[2].display_name	Control (management)
keywords[3].id	https://openalex.org/keywords/artificial-intelligence
keywords[3].score	0.4465835690498352
keywords[3].display_name	Artificial intelligence
keywords[4].id	https://openalex.org/keywords/deep-learning
keywords[4].score	0.43961483240127563
keywords[4].display_name	Deep learning
language	en
locations[0].id	pmh:oai:arXiv.org:2412.07212
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2412.07212
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2412.07212
locations[1].id	doi:10.48550/arxiv.2412.07212
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2412.07212
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5030939982
authorships[0].author.orcid
authorships[0].author.display_name	Wenjian Hao
authorships[0].author_position	first
authorships[0].raw_author_name	Hao, Wenjian
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5018784148
authorships[1].author.orcid	https://orcid.org/0000-0002-7312-7075
authorships[1].author.display_name	Zehui Lu
authorships[1].author_position	middle
authorships[1].raw_author_name	Lu, Zehui
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5029516882
authorships[2].author.orcid	https://orcid.org/0000-0002-3758-0585
authorships[2].author.display_name	Devesh Upadhyay
authorships[2].author_position	middle
authorships[2].raw_author_name	Upadhyay, Devesh
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5070733769
authorships[3].author.orcid	https://orcid.org/0000-0002-3698-4238
authorships[3].author.display_name	Shaoshuai Mou
authorships[3].author_position	last
authorships[3].raw_author_name	Mou, Shaoshuai
authorships[3].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2412.07212
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2024-12-12T00:00:00
display_name	Distributed Koopman Learning using Partial Trajectories for Control
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T10320
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.7562999725341797
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1702
primary_topic.subfield.display_name	Artificial Intelligence
primary_topic.display_name	Neural Networks and Applications
related_works	https://openalex.org/W2731899572, https://openalex.org/W3215138031, https://openalex.org/W3009238340, https://openalex.org/W4360585206, https://openalex.org/W4321369474, https://openalex.org/W4285208911, https://openalex.org/W3082895349, https://openalex.org/W4213079790, https://openalex.org/W2248239756, https://openalex.org/W3086377361
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2412.07212
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2412.07212
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2412.07212
primary_location.id	pmh:oai:arXiv.org:2412.07212
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2412.07212
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2412.07212
publication_date	2024-12-10
publication_year	2024
referenced_works_count	0
abstract_inverted_index.a	3, 25, 30, 41, 63, 76, 103
abstract_inverted_index.By	50
abstract_inverted_index.In	19
abstract_inverted_index.by	110
abstract_inverted_index.in	24
abstract_inverted_index.is	28, 108
abstract_inverted_index.on	62, 75, 121
abstract_inverted_index.to	86
abstract_inverted_index.and	34, 123
abstract_inverted_index.are	132
abstract_inverted_index.for	7, 135
abstract_inverted_index.the	37, 46, 87, 99, 112, 128
abstract_inverted_index.This	0
abstract_inverted_index.deep	12, 42
abstract_inverted_index.each	22, 91
abstract_inverted_index.over	98
abstract_inverted_index.than	56
abstract_inverted_index.that	80, 127
abstract_inverted_index.this	20
abstract_inverted_index.with	84, 90, 116
abstract_inverted_index.agent	23, 92
abstract_inverted_index.data,	58
abstract_inverted_index.data.	101
abstract_inverted_index.known	117
abstract_inverted_index.local	52
abstract_inverted_index.model	66, 104
abstract_inverted_index.paper	1
abstract_inverted_index.small	95
abstract_inverted_index.tasks	125
abstract_inverted_index.their	69
abstract_inverted_index.using	15, 40
abstract_inverted_index.agents	59
abstract_inverted_index.errors	97
abstract_inverted_index.global	64
abstract_inverted_index.neural	43
abstract_inverted_index.rather	55
abstract_inverted_index.scheme	107
abstract_inverted_index.system	27
abstract_inverted_index.termed	10
abstract_inverted_index.within	45
abstract_inverted_index.DDKL-PT	81
abstract_inverted_index.Koopman	13, 47, 114
abstract_inverted_index.Results	120
abstract_inverted_index.achieve	60
abstract_inverted_index.attains	82
abstract_inverted_index.control	106
abstract_inverted_index.learned	88, 113, 130
abstract_inverted_index.locally	35
abstract_inverted_index.network	44
abstract_inverted_index.offline	33
abstract_inverted_index.optimal	137
abstract_inverted_index.partial	16, 31
abstract_inverted_index.private	70
abstract_inverted_index.respect	85
abstract_inverted_index.sharing	68
abstract_inverted_index.studies	74
abstract_inverted_index.support	126
abstract_inverted_index.surface	77
abstract_inverted_index.testing	100
abstract_inverted_index.unknown	38
abstract_inverted_index.vehicle	78
abstract_inverted_index.without	67
abstract_inverted_index.accurate	134
abstract_inverted_index.assigned	29
abstract_inverted_index.control.	138
abstract_inverted_index.dynamics	8, 39, 54, 65, 115, 131
abstract_inverted_index.learning	14
abstract_inverted_index.operator	48
abstract_inverted_index.proposes	2
abstract_inverted_index.training	57, 71
abstract_inverted_index.achieving	93
abstract_inverted_index.consensus	61, 83
abstract_inverted_index.developed	109
abstract_inverted_index.dynamics,	89
abstract_inverted_index.estimated	53
abstract_inverted_index.framework	6
abstract_inverted_index.kinematic	118
abstract_inverted_index.learning,	9
abstract_inverted_index.(DDKL-PT).	18
abstract_inverted_index.Simulation	73
abstract_inverted_index.exchanging	51
abstract_inverted_index.framework,	21
abstract_inverted_index.framework.	49
abstract_inverted_index.predictive	105
abstract_inverted_index.reasonably	94
abstract_inverted_index.relations.	119
abstract_inverted_index.trajectory	32
abstract_inverted_index.data-driven	5
abstract_inverted_index.demonstrate	79
abstract_inverted_index.distributed	4, 11
abstract_inverted_index.integrating	111
abstract_inverted_index.model-based	136
abstract_inverted_index.multi-agent	26
abstract_inverted_index.Furthermore,	102
abstract_inverted_index.approximates	36
abstract_inverted_index.sufficiently	133
abstract_inverted_index.trajectories	17
abstract_inverted_index.approximation	96
abstract_inverted_index.distributedly	129
abstract_inverted_index.goal-tracking	122
abstract_inverted_index.trajectories.	72
abstract_inverted_index.station-keeping	124
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	4
citation_normalized_percentile