Learning Deep Dynamical Systems using Stable Neural ODEs Article Swipe
Andreas Sochopoulos
,
Michael Gienger
,
Sethu Vijayakumar
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2404.10622
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2404.10622
Learning complex trajectories from demonstrations in robotic tasks has been effectively addressed through the utilization of Dynamical Systems (DS). State-of-the-art DS learning methods ensure stability of the generated trajectories; however, they have three shortcomings: a) the DS is assumed to have a single attractor, which limits the diversity of tasks it can achieve, b) state derivative information is assumed to be available in the learning process and c) the state of the DS is assumed to be measurable at inference time. We propose a class of provably stable latent DS with possibly multiple attractors, that inherit the training methods of Neural Ordinary Differential Equations, thus, dropping the dependency on state derivative information. A diffeomorphic mapping for the output and a loss that captures time-invariant trajectory similarity are proposed. We validate the efficacy of our approach through experiments conducted on a public dataset of handwritten shapes and within a simulated object manipulation task.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2404.10622
- https://arxiv.org/pdf/2404.10622
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4394906474
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4394906474Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2404.10622Digital Object Identifier
- Title
-
Learning Deep Dynamical Systems using Stable Neural ODEsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-04-16Full publication date if available
- Authors
-
Andreas Sochopoulos, Michael Gienger, Sethu VijayakumarList of authors in order
- Landing page
-
https://arxiv.org/abs/2404.10622Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2404.10622Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2404.10622Direct OA link when available
- Concepts
-
Ode, Dynamical systems theory, Artificial neural network, Deep neural networks, Deep learning, Artificial intelligence, Neural system, Computer science, Mathematics, Applied mathematics, Physics, Psychology, Neuroscience, Quantum mechanicsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4394906474 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2404.10622 |
| ids.doi | https://doi.org/10.48550/arxiv.2404.10622 |
| ids.openalex | https://openalex.org/W4394906474 |
| fwci | |
| type | preprint |
| title | Learning Deep Dynamical Systems using Stable Neural ODEs |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11206 |
| topics[0].field.id | https://openalex.org/fields/31 |
| topics[0].field.display_name | Physics and Astronomy |
| topics[0].score | 0.9939000010490417 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/3109 |
| topics[0].subfield.display_name | Statistical and Nonlinear Physics |
| topics[0].display_name | Model Reduction and Neural Networks |
| topics[1].id | https://openalex.org/T10320 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.90829998254776 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Neural Networks and Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C34862557 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8046501874923706 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q178985 |
| concepts[0].display_name | Ode |
| concepts[1].id | https://openalex.org/C79379906 |
| concepts[1].level | 2 |
| concepts[1].score | 0.5529086589813232 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q3174497 |
| concepts[1].display_name | Dynamical systems theory |
| concepts[2].id | https://openalex.org/C50644808 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5423934459686279 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[2].display_name | Artificial neural network |
| concepts[3].id | https://openalex.org/C2984842247 |
| concepts[3].level | 3 |
| concepts[3].score | 0.5221019983291626 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[3].display_name | Deep neural networks |
| concepts[4].id | https://openalex.org/C108583219 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5195589065551758 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[4].display_name | Deep learning |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.49942445755004883 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C2986949344 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4971487820148468 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q9404 |
| concepts[6].display_name | Neural system |
| concepts[7].id | https://openalex.org/C41008148 |
| concepts[7].level | 0 |
| concepts[7].score | 0.43509548902511597 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[7].display_name | Computer science |
| concepts[8].id | https://openalex.org/C33923547 |
| concepts[8].level | 0 |
| concepts[8].score | 0.3177863359451294 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[8].display_name | Mathematics |
| concepts[9].id | https://openalex.org/C28826006 |
| concepts[9].level | 1 |
| concepts[9].score | 0.21791070699691772 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q33521 |
| concepts[9].display_name | Applied mathematics |
| concepts[10].id | https://openalex.org/C121332964 |
| concepts[10].level | 0 |
| concepts[10].score | 0.15422654151916504 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[10].display_name | Physics |
| concepts[11].id | https://openalex.org/C15744967 |
| concepts[11].level | 0 |
| concepts[11].score | 0.13275033235549927 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[11].display_name | Psychology |
| concepts[12].id | https://openalex.org/C169760540 |
| concepts[12].level | 1 |
| concepts[12].score | 0.12387469410896301 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q207011 |
| concepts[12].display_name | Neuroscience |
| concepts[13].id | https://openalex.org/C62520636 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q944 |
| concepts[13].display_name | Quantum mechanics |
| keywords[0].id | https://openalex.org/keywords/ode |
| keywords[0].score | 0.8046501874923706 |
| keywords[0].display_name | Ode |
| keywords[1].id | https://openalex.org/keywords/dynamical-systems-theory |
| keywords[1].score | 0.5529086589813232 |
| keywords[1].display_name | Dynamical systems theory |
| keywords[2].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[2].score | 0.5423934459686279 |
| keywords[2].display_name | Artificial neural network |
| keywords[3].id | https://openalex.org/keywords/deep-neural-networks |
| keywords[3].score | 0.5221019983291626 |
| keywords[3].display_name | Deep neural networks |
| keywords[4].id | https://openalex.org/keywords/deep-learning |
| keywords[4].score | 0.5195589065551758 |
| keywords[4].display_name | Deep learning |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.49942445755004883 |
| keywords[5].display_name | Artificial intelligence |
| keywords[6].id | https://openalex.org/keywords/neural-system |
| keywords[6].score | 0.4971487820148468 |
| keywords[6].display_name | Neural system |
| keywords[7].id | https://openalex.org/keywords/computer-science |
| keywords[7].score | 0.43509548902511597 |
| keywords[7].display_name | Computer science |
| keywords[8].id | https://openalex.org/keywords/mathematics |
| keywords[8].score | 0.3177863359451294 |
| keywords[8].display_name | Mathematics |
| keywords[9].id | https://openalex.org/keywords/applied-mathematics |
| keywords[9].score | 0.21791070699691772 |
| keywords[9].display_name | Applied mathematics |
| keywords[10].id | https://openalex.org/keywords/physics |
| keywords[10].score | 0.15422654151916504 |
| keywords[10].display_name | Physics |
| keywords[11].id | https://openalex.org/keywords/psychology |
| keywords[11].score | 0.13275033235549927 |
| keywords[11].display_name | Psychology |
| keywords[12].id | https://openalex.org/keywords/neuroscience |
| keywords[12].score | 0.12387469410896301 |
| keywords[12].display_name | Neuroscience |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2404.10622 |
| 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/2404.10622 |
| 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/2404.10622 |
| locations[1].id | doi:10.48550/arxiv.2404.10622 |
| 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.2404.10622 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5045043372 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Andreas Sochopoulos |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Sochopoulos, Andreas |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5025560073 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-8036-2519 |
| authorships[1].author.display_name | Michael Gienger |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Gienger, Michael |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5069715982 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-0649-7241 |
| authorships[2].author.display_name | Sethu Vijayakumar |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Vijayakumar, Sethu |
| authorships[2].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2404.10622 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Learning Deep Dynamical Systems using Stable Neural ODEs |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11206 |
| primary_topic.field.id | https://openalex.org/fields/31 |
| primary_topic.field.display_name | Physics and Astronomy |
| primary_topic.score | 0.9939000010490417 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/3109 |
| primary_topic.subfield.display_name | Statistical and Nonlinear Physics |
| primary_topic.display_name | Model Reduction and Neural Networks |
| related_works | https://openalex.org/W2371448224, https://openalex.org/W3134495997, https://openalex.org/W4377865163, https://openalex.org/W3193857078, https://openalex.org/W2888956734, https://openalex.org/W3000197790, https://openalex.org/W4315865067, https://openalex.org/W2979433843, https://openalex.org/W3208304128, https://openalex.org/W1593626288 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2404.10622 |
| 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/2404.10622 |
| 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/2404.10622 |
| primary_location.id | pmh:oai:arXiv.org:2404.10622 |
| 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/2404.10622 |
| 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/2404.10622 |
| publication_date | 2024-04-16 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.A | 112 |
| abstract_inverted_index.a | 41, 83, 119, 139, 147 |
| abstract_inverted_index.DS | 20, 36, 72, 89 |
| abstract_inverted_index.We | 81, 128 |
| abstract_inverted_index.a) | 34 |
| abstract_inverted_index.at | 78 |
| abstract_inverted_index.b) | 53 |
| abstract_inverted_index.be | 60, 76 |
| abstract_inverted_index.c) | 67 |
| abstract_inverted_index.in | 5, 62 |
| abstract_inverted_index.is | 37, 57, 73 |
| abstract_inverted_index.it | 50 |
| abstract_inverted_index.of | 15, 25, 48, 70, 85, 99, 132, 142 |
| abstract_inverted_index.on | 108, 138 |
| abstract_inverted_index.to | 39, 59, 75 |
| abstract_inverted_index.and | 66, 118, 145 |
| abstract_inverted_index.are | 126 |
| abstract_inverted_index.can | 51 |
| abstract_inverted_index.for | 115 |
| abstract_inverted_index.has | 8 |
| abstract_inverted_index.our | 133 |
| abstract_inverted_index.the | 13, 26, 35, 46, 63, 68, 71, 96, 106, 116, 130 |
| abstract_inverted_index.been | 9 |
| abstract_inverted_index.from | 3 |
| abstract_inverted_index.have | 31, 40 |
| abstract_inverted_index.loss | 120 |
| abstract_inverted_index.that | 94, 121 |
| abstract_inverted_index.they | 30 |
| abstract_inverted_index.with | 90 |
| abstract_inverted_index.(DS). | 18 |
| abstract_inverted_index.class | 84 |
| abstract_inverted_index.state | 54, 69, 109 |
| abstract_inverted_index.task. | 151 |
| abstract_inverted_index.tasks | 7, 49 |
| abstract_inverted_index.three | 32 |
| abstract_inverted_index.thus, | 104 |
| abstract_inverted_index.time. | 80 |
| abstract_inverted_index.which | 44 |
| abstract_inverted_index.Neural | 100 |
| abstract_inverted_index.ensure | 23 |
| abstract_inverted_index.latent | 88 |
| abstract_inverted_index.limits | 45 |
| abstract_inverted_index.object | 149 |
| abstract_inverted_index.output | 117 |
| abstract_inverted_index.public | 140 |
| abstract_inverted_index.shapes | 144 |
| abstract_inverted_index.single | 42 |
| abstract_inverted_index.stable | 87 |
| abstract_inverted_index.within | 146 |
| abstract_inverted_index.Systems | 17 |
| abstract_inverted_index.assumed | 38, 58, 74 |
| abstract_inverted_index.complex | 1 |
| abstract_inverted_index.dataset | 141 |
| abstract_inverted_index.inherit | 95 |
| abstract_inverted_index.mapping | 114 |
| abstract_inverted_index.methods | 22, 98 |
| abstract_inverted_index.process | 65 |
| abstract_inverted_index.propose | 82 |
| abstract_inverted_index.robotic | 6 |
| abstract_inverted_index.through | 12, 135 |
| abstract_inverted_index.Learning | 0 |
| abstract_inverted_index.Ordinary | 101 |
| abstract_inverted_index.achieve, | 52 |
| abstract_inverted_index.approach | 134 |
| abstract_inverted_index.captures | 122 |
| abstract_inverted_index.dropping | 105 |
| abstract_inverted_index.efficacy | 131 |
| abstract_inverted_index.however, | 29 |
| abstract_inverted_index.learning | 21, 64 |
| abstract_inverted_index.multiple | 92 |
| abstract_inverted_index.possibly | 91 |
| abstract_inverted_index.provably | 86 |
| abstract_inverted_index.training | 97 |
| abstract_inverted_index.validate | 129 |
| abstract_inverted_index.Dynamical | 16 |
| abstract_inverted_index.addressed | 11 |
| abstract_inverted_index.available | 61 |
| abstract_inverted_index.conducted | 137 |
| abstract_inverted_index.diversity | 47 |
| abstract_inverted_index.generated | 27 |
| abstract_inverted_index.inference | 79 |
| abstract_inverted_index.proposed. | 127 |
| abstract_inverted_index.simulated | 148 |
| abstract_inverted_index.stability | 24 |
| abstract_inverted_index.Equations, | 103 |
| abstract_inverted_index.attractor, | 43 |
| abstract_inverted_index.dependency | 107 |
| abstract_inverted_index.derivative | 55, 110 |
| abstract_inverted_index.measurable | 77 |
| abstract_inverted_index.similarity | 125 |
| abstract_inverted_index.trajectory | 124 |
| abstract_inverted_index.attractors, | 93 |
| abstract_inverted_index.effectively | 10 |
| abstract_inverted_index.experiments | 136 |
| abstract_inverted_index.handwritten | 143 |
| abstract_inverted_index.information | 56 |
| abstract_inverted_index.utilization | 14 |
| abstract_inverted_index.Differential | 102 |
| abstract_inverted_index.information. | 111 |
| abstract_inverted_index.manipulation | 150 |
| abstract_inverted_index.trajectories | 2 |
| abstract_inverted_index.diffeomorphic | 113 |
| abstract_inverted_index.shortcomings: | 33 |
| abstract_inverted_index.trajectories; | 28 |
| abstract_inverted_index.demonstrations | 4 |
| abstract_inverted_index.time-invariant | 123 |
| abstract_inverted_index.State-of-the-art | 19 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile |