Deep Learning of Neuromuscular Control for Biomechanical Human Animation View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2015-12-18

AUTHORS

Masaki Nakada , Demetri Terzopoulos

ABSTRACT

Increasingly complex physics-based models enhance the realism of character animation in computer graphics, but they pose difficult motor control challenges. This is especially the case when controlling a biomechanically simulated virtual human with an anatomically realistic structure that is actuated in a natural manner by a multitude of contractile muscles. Graphics researchers have pursued machine learning approaches to neuromuscular control, but traditional neural network learning methods suffer limitations when applied to complex biomechanical models and their associated high-dimensional training datasets. We demonstrate that “deep learning” is a useful approach to training neuromuscular controllers for biomechanical character animation. In particular, we propose a deep neural network architecture that can effectively and efficiently control (online) a dynamic musculoskeletal model of the human neck-head-face complex after having learned (offline) a high-dimensional map relating head orientation changes to neck muscle activations. To our knowledge, this is the first application of deep learning to biomechanical human animation with a muscle-driven model. More... »

PAGES

339-348

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-319-27857-5_31

DOI

http://dx.doi.org/10.1007/978-3-319-27857-5_31

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1014487701


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/11", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Medical and Health Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/1106", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Human Movement and Sports Science", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Computer Science Department, University of California, Los Angeles, USA", 
          "id": "http://www.grid.ac/institutes/grid.19006.3e", 
          "name": [
            "Computer Science Department, University of California, Los Angeles, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Nakada", 
        "givenName": "Masaki", 
        "id": "sg:person.013165270522.94", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013165270522.94"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Computer Science Department, University of California, Los Angeles, USA", 
          "id": "http://www.grid.ac/institutes/grid.19006.3e", 
          "name": [
            "Computer Science Department, University of California, Los Angeles, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Terzopoulos", 
        "givenName": "Demetri", 
        "id": "sg:person.016347323445.35", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016347323445.35"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2015-12-18", 
    "datePublishedReg": "2015-12-18", 
    "description": "Increasingly complex physics-based models enhance the realism of character animation in computer graphics, but they pose difficult motor control challenges. This is especially the case when controlling a biomechanically simulated virtual human with an anatomically realistic structure that is actuated in a natural manner by a multitude of contractile muscles. Graphics researchers have pursued machine learning approaches to neuromuscular control, but traditional neural network learning methods suffer limitations when applied to complex biomechanical models and their associated high-dimensional training datasets. We demonstrate that \u201cdeep learning\u201d is a useful approach to training neuromuscular controllers for biomechanical character animation. In particular, we propose a deep neural network architecture that can effectively and efficiently control (online) a dynamic musculoskeletal model of the human neck-head-face complex after having learned (offline) a high-dimensional map relating head orientation changes to neck muscle activations. To our knowledge, this is the first application of deep learning to biomechanical human animation with a muscle-driven model.", 
    "editor": [
      {
        "familyName": "Bebis", 
        "givenName": "George", 
        "type": "Person"
      }, 
      {
        "familyName": "Boyle", 
        "givenName": "Richard", 
        "type": "Person"
      }, 
      {
        "familyName": "Parvin", 
        "givenName": "Bahram", 
        "type": "Person"
      }, 
      {
        "familyName": "Koracin", 
        "givenName": "Darko", 
        "type": "Person"
      }, 
      {
        "familyName": "Pavlidis", 
        "givenName": "Ioannis", 
        "type": "Person"
      }, 
      {
        "familyName": "Feris", 
        "givenName": "Rogerio", 
        "type": "Person"
      }, 
      {
        "familyName": "McGraw", 
        "givenName": "Tim", 
        "type": "Person"
      }, 
      {
        "familyName": "Elendt", 
        "givenName": "Mark", 
        "type": "Person"
      }, 
      {
        "familyName": "Kopper", 
        "givenName": "Regis", 
        "type": "Person"
      }, 
      {
        "familyName": "Ragan", 
        "givenName": "Eric", 
        "type": "Person"
      }, 
      {
        "familyName": "Ye", 
        "givenName": "Zhao", 
        "type": "Person"
      }, 
      {
        "familyName": "Weber", 
        "givenName": "Gunther", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-319-27857-5_31", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-319-27856-8", 
        "978-3-319-27857-5"
      ], 
      "name": "Advances in Visual Computing", 
      "type": "Book"
    }, 
    "keywords": [
      "deep learning", 
      "human animation", 
      "character animation", 
      "deep neural network architecture", 
      "neural network architecture", 
      "traditional neural network", 
      "complex physics-based models", 
      "graphics researchers", 
      "virtual humans", 
      "network architecture", 
      "computer graphics", 
      "neural network", 
      "training dataset", 
      "animation", 
      "complex biomechanical models", 
      "high-dimensional map", 
      "head orientation changes", 
      "natural manner", 
      "physics-based model", 
      "learning", 
      "neuromuscular controller", 
      "control challenges", 
      "graphics", 
      "architecture", 
      "datasets", 
      "machine", 
      "network", 
      "first application", 
      "controller", 
      "dynamic musculoskeletal model", 
      "model", 
      "musculoskeletal model", 
      "orientation changes", 
      "applications", 
      "maps", 
      "challenges", 
      "researchers", 
      "realistic structures", 
      "realism", 
      "multitude", 
      "knowledge", 
      "biomechanical model", 
      "limitations", 
      "method", 
      "useful approach", 
      "control", 
      "manner", 
      "face complexes", 
      "humans", 
      "structure", 
      "cases", 
      "contractile muscle", 
      "neck muscle activation", 
      "approach", 
      "neuromuscular control", 
      "muscle activation", 
      "changes", 
      "activation", 
      "complexes", 
      "muscle", 
      "difficult motor control challenges", 
      "motor control challenges", 
      "high-dimensional training datasets", 
      "biomechanical character animation", 
      "biomechanical human animation", 
      "muscle-driven model"
    ], 
    "name": "Deep Learning of Neuromuscular Control for Biomechanical Human Animation", 
    "pagination": "339-348", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1014487701"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-319-27857-5_31"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-319-27857-5_31", 
      "https://app.dimensions.ai/details/publication/pub.1014487701"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-01-01T19:20", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220101/entities/gbq_results/chapter/chapter_365.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-319-27857-5_31"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-27857-5_31'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-27857-5_31'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-27857-5_31'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-27857-5_31'


 

This table displays all metadata directly associated to this object as RDF triples.

196 TRIPLES      23 PREDICATES      93 URIs      84 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-319-27857-5_31 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 anzsrc-for:11
4 anzsrc-for:1106
5 schema:author Nc3cf11b1697340b9a43a2fd18810b013
6 schema:datePublished 2015-12-18
7 schema:datePublishedReg 2015-12-18
8 schema:description Increasingly complex physics-based models enhance the realism of character animation in computer graphics, but they pose difficult motor control challenges. This is especially the case when controlling a biomechanically simulated virtual human with an anatomically realistic structure that is actuated in a natural manner by a multitude of contractile muscles. Graphics researchers have pursued machine learning approaches to neuromuscular control, but traditional neural network learning methods suffer limitations when applied to complex biomechanical models and their associated high-dimensional training datasets. We demonstrate that “deep learning” is a useful approach to training neuromuscular controllers for biomechanical character animation. In particular, we propose a deep neural network architecture that can effectively and efficiently control (online) a dynamic musculoskeletal model of the human neck-head-face complex after having learned (offline) a high-dimensional map relating head orientation changes to neck muscle activations. To our knowledge, this is the first application of deep learning to biomechanical human animation with a muscle-driven model.
9 schema:editor Nc6a9cb40ba62482b906250d5d816ddc4
10 schema:genre chapter
11 schema:inLanguage en
12 schema:isAccessibleForFree false
13 schema:isPartOf Ndbc41af4f59b4166aab84743e17bba98
14 schema:keywords activation
15 animation
16 applications
17 approach
18 architecture
19 biomechanical character animation
20 biomechanical human animation
21 biomechanical model
22 cases
23 challenges
24 changes
25 character animation
26 complex biomechanical models
27 complex physics-based models
28 complexes
29 computer graphics
30 contractile muscle
31 control
32 control challenges
33 controller
34 datasets
35 deep learning
36 deep neural network architecture
37 difficult motor control challenges
38 dynamic musculoskeletal model
39 face complexes
40 first application
41 graphics
42 graphics researchers
43 head orientation changes
44 high-dimensional map
45 high-dimensional training datasets
46 human animation
47 humans
48 knowledge
49 learning
50 limitations
51 machine
52 manner
53 maps
54 method
55 model
56 motor control challenges
57 multitude
58 muscle
59 muscle activation
60 muscle-driven model
61 musculoskeletal model
62 natural manner
63 neck muscle activation
64 network
65 network architecture
66 neural network
67 neural network architecture
68 neuromuscular control
69 neuromuscular controller
70 orientation changes
71 physics-based model
72 realism
73 realistic structures
74 researchers
75 structure
76 traditional neural network
77 training dataset
78 useful approach
79 virtual humans
80 schema:name Deep Learning of Neuromuscular Control for Biomechanical Human Animation
81 schema:pagination 339-348
82 schema:productId N953af1df937943678fac0d39bc5e8a17
83 Ne9f3c02c29544bee8f07386d5593f552
84 schema:publisher Ncc72013154124ceb8f0a6aa76080114f
85 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014487701
86 https://doi.org/10.1007/978-3-319-27857-5_31
87 schema:sdDatePublished 2022-01-01T19:20
88 schema:sdLicense https://scigraph.springernature.com/explorer/license/
89 schema:sdPublisher N9dc6d2f003444f3c8ac82402444d72fd
90 schema:url https://doi.org/10.1007/978-3-319-27857-5_31
91 sgo:license sg:explorer/license/
92 sgo:sdDataset chapters
93 rdf:type schema:Chapter
94 N07186995098f47dca59fbb0f75fcb266 schema:familyName McGraw
95 schema:givenName Tim
96 rdf:type schema:Person
97 N0bce648f06184e10b89851bdb363ebe9 schema:familyName Boyle
98 schema:givenName Richard
99 rdf:type schema:Person
100 N1c3f1f0e3b4f434899f5f0ee3d05c2cc rdf:first N287f8711d5c0467b8a5f4cd111c72739
101 rdf:rest rdf:nil
102 N229213614fd04c88b102702eb858de70 schema:familyName Bebis
103 schema:givenName George
104 rdf:type schema:Person
105 N287f8711d5c0467b8a5f4cd111c72739 schema:familyName Weber
106 schema:givenName Gunther
107 rdf:type schema:Person
108 N2db2fd5ff75e4ce6aac2311165c9d350 rdf:first Nb038cfdb97eb4d13940bde9aed8fce4f
109 rdf:rest Nab73b5a13aed44ff8e2a83b9372aec08
110 N2eb76b363cfb4df08ae14a8957523165 rdf:first N07186995098f47dca59fbb0f75fcb266
111 rdf:rest Nf5748edb0010453381447d16eb9252dc
112 N3c8232003d31407387d514641eadc7bb schema:familyName Pavlidis
113 schema:givenName Ioannis
114 rdf:type schema:Person
115 N5850bdb565154915a125e58f9e610d7e schema:familyName Elendt
116 schema:givenName Mark
117 rdf:type schema:Person
118 N70ac9a22ba8c40589d2551c99455140a schema:familyName Ye
119 schema:givenName Zhao
120 rdf:type schema:Person
121 N732e4cb81394478f866dee4db19ed2a3 schema:familyName Feris
122 schema:givenName Rogerio
123 rdf:type schema:Person
124 N953af1df937943678fac0d39bc5e8a17 schema:name doi
125 schema:value 10.1007/978-3-319-27857-5_31
126 rdf:type schema:PropertyValue
127 N98f2930ef2004896b4f09ae92c93c8b1 rdf:first N70ac9a22ba8c40589d2551c99455140a
128 rdf:rest N1c3f1f0e3b4f434899f5f0ee3d05c2cc
129 N9dc6d2f003444f3c8ac82402444d72fd schema:name Springer Nature - SN SciGraph project
130 rdf:type schema:Organization
131 N9e7f0c2b651b40a7a70990bb31b62671 rdf:first Nead2439e609543159e60af8925711f93
132 rdf:rest N98f2930ef2004896b4f09ae92c93c8b1
133 Na779dca29ff7490c906dfb664fe9a7b9 rdf:first Ncd4487cf0d744036a7958880062c3f22
134 rdf:rest N2db2fd5ff75e4ce6aac2311165c9d350
135 Nab73b5a13aed44ff8e2a83b9372aec08 rdf:first N3c8232003d31407387d514641eadc7bb
136 rdf:rest Nf6f93554d32345b38d0a154398f7d92f
137 Nb038cfdb97eb4d13940bde9aed8fce4f schema:familyName Koracin
138 schema:givenName Darko
139 rdf:type schema:Person
140 Nc3cf11b1697340b9a43a2fd18810b013 rdf:first sg:person.013165270522.94
141 rdf:rest Ne025bd9e459e499a8231e9a02646b881
142 Nc6a9cb40ba62482b906250d5d816ddc4 rdf:first N229213614fd04c88b102702eb858de70
143 rdf:rest Nf4d5aa4f2e8a4152871deae4f9ff827d
144 Ncc72013154124ceb8f0a6aa76080114f schema:name Springer Nature
145 rdf:type schema:Organisation
146 Ncd4487cf0d744036a7958880062c3f22 schema:familyName Parvin
147 schema:givenName Bahram
148 rdf:type schema:Person
149 Ndbc41af4f59b4166aab84743e17bba98 schema:isbn 978-3-319-27856-8
150 978-3-319-27857-5
151 schema:name Advances in Visual Computing
152 rdf:type schema:Book
153 Ndef39e58d1e44dedb23b95075be57912 rdf:first Nfe33ddce244d46e1aa22b6a029d6b2da
154 rdf:rest N9e7f0c2b651b40a7a70990bb31b62671
155 Ne025bd9e459e499a8231e9a02646b881 rdf:first sg:person.016347323445.35
156 rdf:rest rdf:nil
157 Ne9f3c02c29544bee8f07386d5593f552 schema:name dimensions_id
158 schema:value pub.1014487701
159 rdf:type schema:PropertyValue
160 Nead2439e609543159e60af8925711f93 schema:familyName Ragan
161 schema:givenName Eric
162 rdf:type schema:Person
163 Nf4d5aa4f2e8a4152871deae4f9ff827d rdf:first N0bce648f06184e10b89851bdb363ebe9
164 rdf:rest Na779dca29ff7490c906dfb664fe9a7b9
165 Nf5748edb0010453381447d16eb9252dc rdf:first N5850bdb565154915a125e58f9e610d7e
166 rdf:rest Ndef39e58d1e44dedb23b95075be57912
167 Nf6f93554d32345b38d0a154398f7d92f rdf:first N732e4cb81394478f866dee4db19ed2a3
168 rdf:rest N2eb76b363cfb4df08ae14a8957523165
169 Nfe33ddce244d46e1aa22b6a029d6b2da schema:familyName Kopper
170 schema:givenName Regis
171 rdf:type schema:Person
172 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
173 schema:name Information and Computing Sciences
174 rdf:type schema:DefinedTerm
175 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
176 schema:name Artificial Intelligence and Image Processing
177 rdf:type schema:DefinedTerm
178 anzsrc-for:11 schema:inDefinedTermSet anzsrc-for:
179 schema:name Medical and Health Sciences
180 rdf:type schema:DefinedTerm
181 anzsrc-for:1106 schema:inDefinedTermSet anzsrc-for:
182 schema:name Human Movement and Sports Science
183 rdf:type schema:DefinedTerm
184 sg:person.013165270522.94 schema:affiliation grid-institutes:grid.19006.3e
185 schema:familyName Nakada
186 schema:givenName Masaki
187 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013165270522.94
188 rdf:type schema:Person
189 sg:person.016347323445.35 schema:affiliation grid-institutes:grid.19006.3e
190 schema:familyName Terzopoulos
191 schema:givenName Demetri
192 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016347323445.35
193 rdf:type schema:Person
194 grid-institutes:grid.19006.3e schema:alternateName Computer Science Department, University of California, Los Angeles, USA
195 schema:name Computer Science Department, University of California, Los Angeles, USA
196 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...