Learning Image-Conditioned Dynamics Models for Control of Under-actuated\n Legged Millirobots Article Swipe
Anusha Nagabandi
,
Guangzhao Yang
,
Thomas Asmar
,
Ravi Pandya
,
Gregory Kahn
,
Sergey Levine
,
Ronald S. Fearing
·
YOU?
·
· 2017
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.1711.05253
YOU?
·
· 2017
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.1711.05253
Millirobots are a promising robotic platform for many applications due to\ntheir small size and low manufacturing costs. Legged millirobots, in\nparticular, can provide increased mobility in complex environments and improved\nscaling of obstacles. However, controlling these small, highly dynamic, and\nunderactuated legged systems is difficult. Hand-engineered controllers can\nsometimes control these legged millirobots, but they have difficulties with\ndynamic maneuvers and complex terrains. We present an approach for controlling\na real-world legged millirobot that is based on learned neural network models.\nUsing less than 17 minutes of data, our method can learn a predictive model of\nthe robot's dynamics that can enable effective gaits to be synthesized on the\nfly for following user-specified waypoints on a given terrain. Furthermore, by\nleveraging expressive, high-capacity neural network models, our approach allows\nfor these predictions to be directly conditioned on camera images, endowing the\nrobot with the ability to predict how different terrains might affect its\ndynamics. This enables sample-efficient and effective learning for locomotion\nof a dynamic legged millirobot on various terrains, including gravel, turf,\ncarpet, and styrofoam. Experiment videos can be found at\nhttps://sites.google.com/view/imageconddyn\n
Related Topics
Concepts
Metadata
- Type
- preprint
- Landing Page
- http://arxiv.org/abs/1711.05253
- https://arxiv.org/pdf/1711.05253
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4301886750
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4301886750Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.1711.05253Digital Object Identifier
- Title
-
Learning Image-Conditioned Dynamics Models for Control of Under-actuated\n Legged MillirobotsWork title
- Type
-
preprintOpenAlex work type
- Publication year
-
2017Year of publication
- Publication date
-
2017-11-14Full publication date if available
- Authors
-
Anusha Nagabandi, Guangzhao Yang, Thomas Asmar, Ravi Pandya, Gregory Kahn, Sergey Levine, Ronald S. FearingList of authors in order
- Landing page
-
https://arxiv.org/abs/1711.05253Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/1711.05253Direct 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/1711.05253Direct OA link when available
- Concepts
-
Terrain, Computer science, Legged robot, Robot, Artificial intelligence, Artificial neural network, Underactuation, Control (management), Control engineering, Simulation, Engineering, Ecology, BiologyTop 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/W4301886750 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.1711.05253 |
| ids.openalex | https://openalex.org/W4301886750 |
| fwci | 0.0 |
| type | preprint |
| title | Learning Image-Conditioned Dynamics Models for Control of Under-actuated\n Legged Millirobots |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10879 |
| topics[0].field.id | https://openalex.org/fields/22 |
| topics[0].field.display_name | Engineering |
| topics[0].score | 0.9914000034332275 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2204 |
| topics[0].subfield.display_name | Biomedical Engineering |
| topics[0].display_name | Robotic Locomotion and Control |
| topics[1].id | https://openalex.org/T11227 |
| topics[1].field.id | https://openalex.org/fields/27 |
| topics[1].field.display_name | Medicine |
| topics[1].score | 0.9509000182151794 |
| topics[1].domain.id | https://openalex.org/domains/4 |
| topics[1].domain.display_name | Health Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2712 |
| topics[1].subfield.display_name | Endocrinology, Diabetes and Metabolism |
| topics[1].display_name | Diabetic Foot Ulcer Assessment and Management |
| topics[2].id | https://openalex.org/T11023 |
| topics[2].field.id | https://openalex.org/fields/22 |
| topics[2].field.display_name | Engineering |
| topics[2].score | 0.9121999740600586 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2204 |
| topics[2].subfield.display_name | Biomedical Engineering |
| topics[2].display_name | Prosthetics and Rehabilitation Robotics |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C161840515 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8203660249710083 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q186131 |
| concepts[0].display_name | Terrain |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.70737624168396 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C2779908020 |
| concepts[2].level | 3 |
| concepts[2].score | 0.58516526222229 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q1424704 |
| concepts[2].display_name | Legged robot |
| concepts[3].id | https://openalex.org/C90509273 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5780081152915955 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11012 |
| concepts[3].display_name | Robot |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.55190509557724 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C50644808 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5396822094917297 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[5].display_name | Artificial neural network |
| concepts[6].id | https://openalex.org/C88337583 |
| concepts[6].level | 3 |
| concepts[6].score | 0.4704671800136566 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q7883433 |
| concepts[6].display_name | Underactuation |
| concepts[7].id | https://openalex.org/C2775924081 |
| concepts[7].level | 2 |
| concepts[7].score | 0.42231616377830505 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q55608371 |
| concepts[7].display_name | Control (management) |
| concepts[8].id | https://openalex.org/C133731056 |
| concepts[8].level | 1 |
| concepts[8].score | 0.36619123816490173 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q4917288 |
| concepts[8].display_name | Control engineering |
| concepts[9].id | https://openalex.org/C44154836 |
| concepts[9].level | 1 |
| concepts[9].score | 0.3254263401031494 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q45045 |
| concepts[9].display_name | Simulation |
| concepts[10].id | https://openalex.org/C127413603 |
| concepts[10].level | 0 |
| concepts[10].score | 0.15655693411827087 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[10].display_name | Engineering |
| concepts[11].id | https://openalex.org/C18903297 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q7150 |
| concepts[11].display_name | Ecology |
| concepts[12].id | https://openalex.org/C86803240 |
| concepts[12].level | 0 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[12].display_name | Biology |
| keywords[0].id | https://openalex.org/keywords/terrain |
| keywords[0].score | 0.8203660249710083 |
| keywords[0].display_name | Terrain |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.70737624168396 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/legged-robot |
| keywords[2].score | 0.58516526222229 |
| keywords[2].display_name | Legged robot |
| keywords[3].id | https://openalex.org/keywords/robot |
| keywords[3].score | 0.5780081152915955 |
| keywords[3].display_name | Robot |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.55190509557724 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[5].score | 0.5396822094917297 |
| keywords[5].display_name | Artificial neural network |
| keywords[6].id | https://openalex.org/keywords/underactuation |
| keywords[6].score | 0.4704671800136566 |
| keywords[6].display_name | Underactuation |
| keywords[7].id | https://openalex.org/keywords/control |
| keywords[7].score | 0.42231616377830505 |
| keywords[7].display_name | Control (management) |
| keywords[8].id | https://openalex.org/keywords/control-engineering |
| keywords[8].score | 0.36619123816490173 |
| keywords[8].display_name | Control engineering |
| keywords[9].id | https://openalex.org/keywords/simulation |
| keywords[9].score | 0.3254263401031494 |
| keywords[9].display_name | Simulation |
| keywords[10].id | https://openalex.org/keywords/engineering |
| keywords[10].score | 0.15655693411827087 |
| keywords[10].display_name | Engineering |
| language | |
| locations[0].id | pmh:oai:arXiv.org:1711.05253 |
| 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/1711.05253 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| 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/1711.05253 |
| indexed_in | arxiv |
| authorships[0].author.id | https://openalex.org/A5030973600 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Anusha Nagabandi |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Nagabandi, Anusha |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5101866312 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-3543-9876 |
| authorships[1].author.display_name | Guangzhao Yang |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Yang, Guangzhao |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5049084944 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Thomas Asmar |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Asmar, Thomas |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5055091245 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-0258-4604 |
| authorships[3].author.display_name | Ravi Pandya |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Pandya, Ravi |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5064156720 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-1771-6147 |
| authorships[4].author.display_name | Gregory Kahn |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Kahn, Gregory |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5026322200 |
| authorships[5].author.orcid | https://orcid.org/0000-0001-6764-2743 |
| authorships[5].author.display_name | Sergey Levine |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Levine, Sergey |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5073886799 |
| authorships[6].author.orcid | https://orcid.org/0000-0001-6242-5379 |
| authorships[6].author.display_name | Ronald S. Fearing |
| authorships[6].author_position | last |
| authorships[6].raw_author_name | Fearing, Ronald S. |
| authorships[6].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/1711.05253 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2022-10-05T00:00:00 |
| display_name | Learning Image-Conditioned Dynamics Models for Control of Under-actuated\n Legged Millirobots |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-10-27T03:07:04.448195 |
| primary_topic.id | https://openalex.org/T10879 |
| primary_topic.field.id | https://openalex.org/fields/22 |
| primary_topic.field.display_name | Engineering |
| primary_topic.score | 0.9914000034332275 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2204 |
| primary_topic.subfield.display_name | Biomedical Engineering |
| primary_topic.display_name | Robotic Locomotion and Control |
| related_works | https://openalex.org/W587013945, https://openalex.org/W4288862394, https://openalex.org/W3213331859, https://openalex.org/W4226458444, https://openalex.org/W4390637946, https://openalex.org/W4226082913, https://openalex.org/W3005657145, https://openalex.org/W2332067308, https://openalex.org/W2028594013, https://openalex.org/W1643150164 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | pmh:oai:arXiv.org:1711.05253 |
| 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/1711.05253 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| 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/1711.05253 |
| primary_location.id | pmh:oai:arXiv.org:1711.05253 |
| 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/1711.05253 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| 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/1711.05253 |
| publication_date | 2017-11-14 |
| publication_year | 2017 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 2, 85, 106, 149 |
| abstract_inverted_index.17 | 77 |
| abstract_inverted_index.We | 58 |
| abstract_inverted_index.an | 60 |
| abstract_inverted_index.be | 97, 122, 164 |
| abstract_inverted_index.in | 24 |
| abstract_inverted_index.is | 40, 68 |
| abstract_inverted_index.of | 29, 79 |
| abstract_inverted_index.on | 70, 99, 105, 125, 153 |
| abstract_inverted_index.to | 96, 121, 133 |
| abstract_inverted_index.and | 13, 27, 55, 144, 159 |
| abstract_inverted_index.are | 1 |
| abstract_inverted_index.but | 49 |
| abstract_inverted_index.can | 20, 83, 92, 163 |
| abstract_inverted_index.due | 9 |
| abstract_inverted_index.for | 6, 62, 101, 147 |
| abstract_inverted_index.how | 135 |
| abstract_inverted_index.low | 14 |
| abstract_inverted_index.our | 81, 116 |
| abstract_inverted_index.the | 131 |
| abstract_inverted_index.This | 141 |
| abstract_inverted_index.have | 51 |
| abstract_inverted_index.less | 75 |
| abstract_inverted_index.many | 7 |
| abstract_inverted_index.size | 12 |
| abstract_inverted_index.than | 76 |
| abstract_inverted_index.that | 67, 91 |
| abstract_inverted_index.they | 50 |
| abstract_inverted_index.with | 130 |
| abstract_inverted_index.based | 69 |
| abstract_inverted_index.data, | 80 |
| abstract_inverted_index.found | 165 |
| abstract_inverted_index.gaits | 95 |
| abstract_inverted_index.given | 107 |
| abstract_inverted_index.learn | 84 |
| abstract_inverted_index.might | 138 |
| abstract_inverted_index.model | 87 |
| abstract_inverted_index.small | 11 |
| abstract_inverted_index.these | 33, 46, 119 |
| abstract_inverted_index.Legged | 17 |
| abstract_inverted_index.affect | 139 |
| abstract_inverted_index.camera | 126 |
| abstract_inverted_index.costs. | 16 |
| abstract_inverted_index.enable | 93 |
| abstract_inverted_index.highly | 35 |
| abstract_inverted_index.legged | 38, 47, 65, 151 |
| abstract_inverted_index.method | 82 |
| abstract_inverted_index.neural | 72, 113 |
| abstract_inverted_index.small, | 34 |
| abstract_inverted_index.videos | 162 |
| abstract_inverted_index.ability | 132 |
| abstract_inverted_index.complex | 25, 56 |
| abstract_inverted_index.control | 45 |
| abstract_inverted_index.dynamic | 150 |
| abstract_inverted_index.enables | 142 |
| abstract_inverted_index.gravel, | 157 |
| abstract_inverted_index.images, | 127 |
| abstract_inverted_index.learned | 71 |
| abstract_inverted_index.minutes | 78 |
| abstract_inverted_index.models, | 115 |
| abstract_inverted_index.network | 73, 114 |
| abstract_inverted_index.of\nthe | 88 |
| abstract_inverted_index.predict | 134 |
| abstract_inverted_index.present | 59 |
| abstract_inverted_index.provide | 21 |
| abstract_inverted_index.robot's | 89 |
| abstract_inverted_index.robotic | 4 |
| abstract_inverted_index.systems | 39 |
| abstract_inverted_index.various | 154 |
| abstract_inverted_index.However, | 31 |
| abstract_inverted_index.approach | 61, 117 |
| abstract_inverted_index.directly | 123 |
| abstract_inverted_index.dynamic, | 36 |
| abstract_inverted_index.dynamics | 90 |
| abstract_inverted_index.endowing | 128 |
| abstract_inverted_index.learning | 146 |
| abstract_inverted_index.mobility | 23 |
| abstract_inverted_index.platform | 5 |
| abstract_inverted_index.terrain. | 108 |
| abstract_inverted_index.terrains | 137 |
| abstract_inverted_index.the\nfly | 100 |
| abstract_inverted_index.different | 136 |
| abstract_inverted_index.effective | 94, 145 |
| abstract_inverted_index.following | 102 |
| abstract_inverted_index.including | 156 |
| abstract_inverted_index.increased | 22 |
| abstract_inverted_index.maneuvers | 54 |
| abstract_inverted_index.promising | 3 |
| abstract_inverted_index.terrains, | 155 |
| abstract_inverted_index.terrains. | 57 |
| abstract_inverted_index.to\ntheir | 10 |
| abstract_inverted_index.waypoints | 104 |
| abstract_inverted_index.Experiment | 161 |
| abstract_inverted_index.difficult. | 41 |
| abstract_inverted_index.millirobot | 66, 152 |
| abstract_inverted_index.obstacles. | 30 |
| abstract_inverted_index.predictive | 86 |
| abstract_inverted_index.real-world | 64 |
| abstract_inverted_index.styrofoam. | 160 |
| abstract_inverted_index.the\nrobot | 129 |
| abstract_inverted_index.Millirobots | 0 |
| abstract_inverted_index.allows\nfor | 118 |
| abstract_inverted_index.conditioned | 124 |
| abstract_inverted_index.controllers | 43 |
| abstract_inverted_index.controlling | 32 |
| abstract_inverted_index.expressive, | 111 |
| abstract_inverted_index.predictions | 120 |
| abstract_inverted_index.synthesized | 98 |
| abstract_inverted_index.Furthermore, | 109 |
| abstract_inverted_index.applications | 8 |
| abstract_inverted_index.difficulties | 52 |
| abstract_inverted_index.environments | 26 |
| abstract_inverted_index.millirobots, | 18, 48 |
| abstract_inverted_index.high-capacity | 112 |
| abstract_inverted_index.manufacturing | 15 |
| abstract_inverted_index.with\ndynamic | 53 |
| abstract_inverted_index.by\nleveraging | 110 |
| abstract_inverted_index.can\nsometimes | 44 |
| abstract_inverted_index.controlling\na | 63 |
| abstract_inverted_index.its\ndynamics. | 140 |
| abstract_inverted_index.locomotion\nof | 148 |
| abstract_inverted_index.models.\nUsing | 74 |
| abstract_inverted_index.turf,\ncarpet, | 158 |
| abstract_inverted_index.user-specified | 103 |
| abstract_inverted_index.Hand-engineered | 42 |
| abstract_inverted_index.in\nparticular, | 19 |
| abstract_inverted_index.sample-efficient | 143 |
| abstract_inverted_index.improved\nscaling | 28 |
| abstract_inverted_index.and\nunderactuated | 37 |
| abstract_inverted_index.at\nhttps://sites.google.com/view/imageconddyn\n | 166 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 7 |
| citation_normalized_percentile.value | 0.31456666 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |