Challenges in cooperative coevolution of physically heterogeneous robot teams View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2019-03

AUTHORS

Jorge Gomes, Pedro Mariano, Anders Lyhne Christensen

ABSTRACT

Heterogeneous multirobot systems have shown significant potential in many applications. Cooperative coevolutionary algorithms (CCEAs) represent a promising approach to synthesise controllers for such systems, as they can evolve multiple co-adapted components. Although CCEAs allow for an arbitrary level of team heterogeneity, in previous works heterogeneity is typically only addressed at the behavioural level. In this paper, we study the use of CCEAs to evolve control for a heterogeneous multirobot system where the robots have disparate morphologies and capabilities. Our experiments rely on a simulated task where a simple ground robot must cooperate with a complex aerial robot to find and collect items. We first show that CCEAs can evolve successful controllers for physically heterogeneous teams, but find that differences in the complexity of the skills the robots need to learn can impair CCEAs’ effectiveness. We then study how different populations can use different evolutionary algorithms and parameters tuned to the agents’ complexity. Finally, we demonstrate how CCEAs’ effectiveness can be improved using incremental evolution or novelty-driven coevolution. Our study shows that, despite its limitations, coevolution is a viable approach for synthesising control for morphologically heterogeneous systems. More... »

PAGES

29-46

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s11047-016-9582-1

DOI

http://dx.doi.org/10.1007/s11047-016-9582-1

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1053448728


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/2008/0801", 
        "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/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "University of Lisbon", 
          "id": "https://www.grid.ac/institutes/grid.9983.b", 
          "name": [
            "BioMachines Lab, Lisbon, Portugal", 
            "Instituto de Telecomunica\u00e7\u00f5es, Lisbon, Portugal", 
            "BioISI, Faculdade de Ci\u00eancias, Universidade de Lisboa, Lisbon, Portugal"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Gomes", 
        "givenName": "Jorge", 
        "id": "sg:person.013064231132.17", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013064231132.17"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Lisbon", 
          "id": "https://www.grid.ac/institutes/grid.9983.b", 
          "name": [
            "BioISI, Faculdade de Ci\u00eancias, Universidade de Lisboa, Lisbon, Portugal"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Mariano", 
        "givenName": "Pedro", 
        "id": "sg:person.016152305455.28", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016152305455.28"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Lisbon University Institute", 
          "id": "https://www.grid.ac/institutes/grid.45349.3f", 
          "name": [
            "BioMachines Lab, Lisbon, Portugal", 
            "Instituto de Telecomunica\u00e7\u00f5es, Lisbon, Portugal", 
            "Instituto Universit\u00e1rio de Lisboa (ISCTE-IUL), Lisbon, Portugal"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Christensen", 
        "givenName": "Anders Lyhne", 
        "id": "sg:person.01210264126.83", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01210264126.83"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1016/s0921-8890(01)00137-3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1002401658"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-15461-4_37", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1002743966", 
          "https://doi.org/10.1007/978-3-642-15461-4_37"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-15461-4_37", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1002743966", 
          "https://doi.org/10.1007/978-3-642-15461-4_37"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/106365600568086", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1003615653"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s12065-009-0034-z", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1006069121", 
          "https://doi.org/10.1007/s12065-009-0034-z"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s12065-009-0034-z", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1006069121", 
          "https://doi.org/10.1007/s12065-009-0034-z"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11431-010-0122-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1007122021", 
          "https://doi.org/10.1007/s11431-010-0122-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11431-010-0122-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1007122021", 
          "https://doi.org/10.1007/s11431-010-0122-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-69134-1_21", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1012514876", 
          "https://doi.org/10.1007/978-3-540-69134-1_21"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10710-012-9166-5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1015717886", 
          "https://doi.org/10.1007/s10710-012-9166-5"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1830483.1830506", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1016671411"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.robot.2008.09.009", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018654288"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.swevo.2011.08.002", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018730209"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1143997.1144062", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1019142689"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1002/rob.20222", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1019407524"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-18272-3_10", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1019932976", 
          "https://doi.org/10.1007/978-3-642-18272-3_10"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-18272-3_10", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1019932976", 
          "https://doi.org/10.1007/978-3-642-18272-3_10"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/2463372.2463398", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1020121547"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/11840541_39", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1020402544", 
          "https://doi.org/10.1007/11840541_39"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/11840541_39", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1020402544", 
          "https://doi.org/10.1007/11840541_39"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/evco_a_00173", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1021082556"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/b:auro.0000033973.24945.f3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1021773262", 
          "https://doi.org/10.1023/b:auro.0000033973.24945.f3"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/a:1008933826411", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1022068396", 
          "https://doi.org/10.1023/a:1008933826411"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/evco_a_00025", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1022319433"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/2739480.2754736", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1023554939"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-14743-2_35", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1024351871", 
          "https://doi.org/10.1007/978-3-642-14743-2_35"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-14743-2_35", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1024351871", 
          "https://doi.org/10.1007/978-3-642-14743-2_35"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/s0166-4115(97)80111-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1025845834"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/evco_a_00004", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1029055082"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1177/105971239700500305", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1030498648"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1177/105971239700500305", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1030498648"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/2001576.2001708", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1032890822"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/106365602320169811", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1033705757"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1177/0278364906065378", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1035405028"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1177/0278364906065378", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1035405028"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s12065-014-0110-x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1036849838", 
          "https://doi.org/10.1007/s12065-014-0110-x"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11047-006-9000-1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1037856621", 
          "https://doi.org/10.1007/s11047-006-9000-1"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/evco_a_00048", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1043746503"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-319-45823-6_55", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045641266", 
          "https://doi.org/10.1007/978-3-319-45823-6_55"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1371/journal.pone.0136406", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045649287"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11721-011-0053-0", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1051267304", 
          "https://doi.org/10.1007/s11721-011-0053-0"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/4235.996017", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061172126"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/jproc.2006.876918", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061296619"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/mra.2013.2252996", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061419702"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tamd.2009.2037732", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061488121"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.5772/53089", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1073125581"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iros.2004.1389486", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093192538"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iros.1998.724656", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093243946"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/robot.2006.1641771", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094042413"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cec.2010.5586100", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094920641"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.7551/978-0-262-33027-5-ch059", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099482595"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2019-03", 
    "datePublishedReg": "2019-03-01", 
    "description": "Heterogeneous multirobot systems have shown significant potential in many applications. Cooperative coevolutionary algorithms (CCEAs) represent a promising approach to synthesise controllers for such systems, as they can evolve multiple co-adapted components. Although CCEAs allow for an arbitrary level of team heterogeneity, in previous works heterogeneity is typically only addressed at the behavioural level. In this paper, we study the use of CCEAs to evolve control for a heterogeneous multirobot system where the robots have disparate morphologies and capabilities. Our experiments rely on a simulated task where a simple ground robot must cooperate with a complex aerial robot to find and collect items. We first show that CCEAs can evolve successful controllers for physically heterogeneous teams, but find that differences in the complexity of the skills the robots need to learn can impair CCEAs\u2019 effectiveness. We then study how different populations can use different evolutionary algorithms and parameters tuned to the agents\u2019 complexity. Finally, we demonstrate how CCEAs\u2019 effectiveness can be improved using incremental evolution or novelty-driven coevolution. Our study shows that, despite its limitations, coevolution is a viable approach for synthesising control for morphologically heterogeneous systems.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1007/s11047-016-9582-1", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1033918", 
        "issn": [
          "1567-7818", 
          "1572-9796"
        ], 
        "name": "Natural Computing", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "1", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "18"
      }
    ], 
    "name": "Challenges in cooperative coevolution of physically heterogeneous robot teams", 
    "pagination": "29-46", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "fe9521c3e0d194661c8578c6223e76cccb96b2e9eefdfdcc4824ee464f223a1b"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s11047-016-9582-1"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1053448728"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s11047-016-9582-1", 
      "https://app.dimensions.ai/details/publication/pub.1053448728"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-11T09:10", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000338_0000000338/records_47967_00000001.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://link.springer.com/10.1007%2Fs11047-016-9582-1"
  }
]
 

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/s11047-016-9582-1'

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/s11047-016-9582-1'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s11047-016-9582-1'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s11047-016-9582-1'


 

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

225 TRIPLES      21 PREDICATES      70 URIs      19 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s11047-016-9582-1 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Nee4f31252cf44011b2532ff208511817
4 schema:citation sg:pub.10.1007/11840541_39
5 sg:pub.10.1007/978-3-319-45823-6_55
6 sg:pub.10.1007/978-3-540-69134-1_21
7 sg:pub.10.1007/978-3-642-14743-2_35
8 sg:pub.10.1007/978-3-642-15461-4_37
9 sg:pub.10.1007/978-3-642-18272-3_10
10 sg:pub.10.1007/s10710-012-9166-5
11 sg:pub.10.1007/s11047-006-9000-1
12 sg:pub.10.1007/s11431-010-0122-4
13 sg:pub.10.1007/s11721-011-0053-0
14 sg:pub.10.1007/s12065-009-0034-z
15 sg:pub.10.1007/s12065-014-0110-x
16 sg:pub.10.1023/a:1008933826411
17 sg:pub.10.1023/b:auro.0000033973.24945.f3
18 https://doi.org/10.1002/rob.20222
19 https://doi.org/10.1016/j.robot.2008.09.009
20 https://doi.org/10.1016/j.swevo.2011.08.002
21 https://doi.org/10.1016/s0166-4115(97)80111-2
22 https://doi.org/10.1016/s0921-8890(01)00137-3
23 https://doi.org/10.1109/4235.996017
24 https://doi.org/10.1109/cec.2010.5586100
25 https://doi.org/10.1109/iros.1998.724656
26 https://doi.org/10.1109/iros.2004.1389486
27 https://doi.org/10.1109/jproc.2006.876918
28 https://doi.org/10.1109/mra.2013.2252996
29 https://doi.org/10.1109/robot.2006.1641771
30 https://doi.org/10.1109/tamd.2009.2037732
31 https://doi.org/10.1145/1143997.1144062
32 https://doi.org/10.1145/1830483.1830506
33 https://doi.org/10.1145/2001576.2001708
34 https://doi.org/10.1145/2463372.2463398
35 https://doi.org/10.1145/2739480.2754736
36 https://doi.org/10.1162/106365600568086
37 https://doi.org/10.1162/106365602320169811
38 https://doi.org/10.1162/evco_a_00004
39 https://doi.org/10.1162/evco_a_00025
40 https://doi.org/10.1162/evco_a_00048
41 https://doi.org/10.1162/evco_a_00173
42 https://doi.org/10.1177/0278364906065378
43 https://doi.org/10.1177/105971239700500305
44 https://doi.org/10.1371/journal.pone.0136406
45 https://doi.org/10.5772/53089
46 https://doi.org/10.7551/978-0-262-33027-5-ch059
47 schema:datePublished 2019-03
48 schema:datePublishedReg 2019-03-01
49 schema:description Heterogeneous multirobot systems have shown significant potential in many applications. Cooperative coevolutionary algorithms (CCEAs) represent a promising approach to synthesise controllers for such systems, as they can evolve multiple co-adapted components. Although CCEAs allow for an arbitrary level of team heterogeneity, in previous works heterogeneity is typically only addressed at the behavioural level. In this paper, we study the use of CCEAs to evolve control for a heterogeneous multirobot system where the robots have disparate morphologies and capabilities. Our experiments rely on a simulated task where a simple ground robot must cooperate with a complex aerial robot to find and collect items. We first show that CCEAs can evolve successful controllers for physically heterogeneous teams, but find that differences in the complexity of the skills the robots need to learn can impair CCEAs’ effectiveness. We then study how different populations can use different evolutionary algorithms and parameters tuned to the agents’ complexity. Finally, we demonstrate how CCEAs’ effectiveness can be improved using incremental evolution or novelty-driven coevolution. Our study shows that, despite its limitations, coevolution is a viable approach for synthesising control for morphologically heterogeneous systems.
50 schema:genre research_article
51 schema:inLanguage en
52 schema:isAccessibleForFree false
53 schema:isPartOf N0c1c5203f9c64c89a38cb77afa5633b2
54 Nfaa0a329abf4441390c7f3ba62751518
55 sg:journal.1033918
56 schema:name Challenges in cooperative coevolution of physically heterogeneous robot teams
57 schema:pagination 29-46
58 schema:productId N1f7f1460095b443aacaea9edf053b791
59 N3077adf852dc4960ba15f55568164094
60 N3e502033408442cbb3c3668ae41751aa
61 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053448728
62 https://doi.org/10.1007/s11047-016-9582-1
63 schema:sdDatePublished 2019-04-11T09:10
64 schema:sdLicense https://scigraph.springernature.com/explorer/license/
65 schema:sdPublisher Ne1f45536b39c42dfb9754455da14e1ab
66 schema:url https://link.springer.com/10.1007%2Fs11047-016-9582-1
67 sgo:license sg:explorer/license/
68 sgo:sdDataset articles
69 rdf:type schema:ScholarlyArticle
70 N0a1835b4d42749859f49ba6397149c4e rdf:first sg:person.01210264126.83
71 rdf:rest rdf:nil
72 N0c1c5203f9c64c89a38cb77afa5633b2 schema:issueNumber 1
73 rdf:type schema:PublicationIssue
74 N1f7f1460095b443aacaea9edf053b791 schema:name dimensions_id
75 schema:value pub.1053448728
76 rdf:type schema:PropertyValue
77 N3077adf852dc4960ba15f55568164094 schema:name readcube_id
78 schema:value fe9521c3e0d194661c8578c6223e76cccb96b2e9eefdfdcc4824ee464f223a1b
79 rdf:type schema:PropertyValue
80 N3e502033408442cbb3c3668ae41751aa schema:name doi
81 schema:value 10.1007/s11047-016-9582-1
82 rdf:type schema:PropertyValue
83 N867646f0dc0d48fdb97a223f9c5c938a rdf:first sg:person.016152305455.28
84 rdf:rest N0a1835b4d42749859f49ba6397149c4e
85 Ne1f45536b39c42dfb9754455da14e1ab schema:name Springer Nature - SN SciGraph project
86 rdf:type schema:Organization
87 Nee4f31252cf44011b2532ff208511817 rdf:first sg:person.013064231132.17
88 rdf:rest N867646f0dc0d48fdb97a223f9c5c938a
89 Nfaa0a329abf4441390c7f3ba62751518 schema:volumeNumber 18
90 rdf:type schema:PublicationVolume
91 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
92 schema:name Information and Computing Sciences
93 rdf:type schema:DefinedTerm
94 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
95 schema:name Artificial Intelligence and Image Processing
96 rdf:type schema:DefinedTerm
97 sg:journal.1033918 schema:issn 1567-7818
98 1572-9796
99 schema:name Natural Computing
100 rdf:type schema:Periodical
101 sg:person.01210264126.83 schema:affiliation https://www.grid.ac/institutes/grid.45349.3f
102 schema:familyName Christensen
103 schema:givenName Anders Lyhne
104 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01210264126.83
105 rdf:type schema:Person
106 sg:person.013064231132.17 schema:affiliation https://www.grid.ac/institutes/grid.9983.b
107 schema:familyName Gomes
108 schema:givenName Jorge
109 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013064231132.17
110 rdf:type schema:Person
111 sg:person.016152305455.28 schema:affiliation https://www.grid.ac/institutes/grid.9983.b
112 schema:familyName Mariano
113 schema:givenName Pedro
114 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016152305455.28
115 rdf:type schema:Person
116 sg:pub.10.1007/11840541_39 schema:sameAs https://app.dimensions.ai/details/publication/pub.1020402544
117 https://doi.org/10.1007/11840541_39
118 rdf:type schema:CreativeWork
119 sg:pub.10.1007/978-3-319-45823-6_55 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045641266
120 https://doi.org/10.1007/978-3-319-45823-6_55
121 rdf:type schema:CreativeWork
122 sg:pub.10.1007/978-3-540-69134-1_21 schema:sameAs https://app.dimensions.ai/details/publication/pub.1012514876
123 https://doi.org/10.1007/978-3-540-69134-1_21
124 rdf:type schema:CreativeWork
125 sg:pub.10.1007/978-3-642-14743-2_35 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024351871
126 https://doi.org/10.1007/978-3-642-14743-2_35
127 rdf:type schema:CreativeWork
128 sg:pub.10.1007/978-3-642-15461-4_37 schema:sameAs https://app.dimensions.ai/details/publication/pub.1002743966
129 https://doi.org/10.1007/978-3-642-15461-4_37
130 rdf:type schema:CreativeWork
131 sg:pub.10.1007/978-3-642-18272-3_10 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019932976
132 https://doi.org/10.1007/978-3-642-18272-3_10
133 rdf:type schema:CreativeWork
134 sg:pub.10.1007/s10710-012-9166-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1015717886
135 https://doi.org/10.1007/s10710-012-9166-5
136 rdf:type schema:CreativeWork
137 sg:pub.10.1007/s11047-006-9000-1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037856621
138 https://doi.org/10.1007/s11047-006-9000-1
139 rdf:type schema:CreativeWork
140 sg:pub.10.1007/s11431-010-0122-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007122021
141 https://doi.org/10.1007/s11431-010-0122-4
142 rdf:type schema:CreativeWork
143 sg:pub.10.1007/s11721-011-0053-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1051267304
144 https://doi.org/10.1007/s11721-011-0053-0
145 rdf:type schema:CreativeWork
146 sg:pub.10.1007/s12065-009-0034-z schema:sameAs https://app.dimensions.ai/details/publication/pub.1006069121
147 https://doi.org/10.1007/s12065-009-0034-z
148 rdf:type schema:CreativeWork
149 sg:pub.10.1007/s12065-014-0110-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1036849838
150 https://doi.org/10.1007/s12065-014-0110-x
151 rdf:type schema:CreativeWork
152 sg:pub.10.1023/a:1008933826411 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022068396
153 https://doi.org/10.1023/a:1008933826411
154 rdf:type schema:CreativeWork
155 sg:pub.10.1023/b:auro.0000033973.24945.f3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1021773262
156 https://doi.org/10.1023/b:auro.0000033973.24945.f3
157 rdf:type schema:CreativeWork
158 https://doi.org/10.1002/rob.20222 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019407524
159 rdf:type schema:CreativeWork
160 https://doi.org/10.1016/j.robot.2008.09.009 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018654288
161 rdf:type schema:CreativeWork
162 https://doi.org/10.1016/j.swevo.2011.08.002 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018730209
163 rdf:type schema:CreativeWork
164 https://doi.org/10.1016/s0166-4115(97)80111-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025845834
165 rdf:type schema:CreativeWork
166 https://doi.org/10.1016/s0921-8890(01)00137-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1002401658
167 rdf:type schema:CreativeWork
168 https://doi.org/10.1109/4235.996017 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061172126
169 rdf:type schema:CreativeWork
170 https://doi.org/10.1109/cec.2010.5586100 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094920641
171 rdf:type schema:CreativeWork
172 https://doi.org/10.1109/iros.1998.724656 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093243946
173 rdf:type schema:CreativeWork
174 https://doi.org/10.1109/iros.2004.1389486 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093192538
175 rdf:type schema:CreativeWork
176 https://doi.org/10.1109/jproc.2006.876918 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061296619
177 rdf:type schema:CreativeWork
178 https://doi.org/10.1109/mra.2013.2252996 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061419702
179 rdf:type schema:CreativeWork
180 https://doi.org/10.1109/robot.2006.1641771 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094042413
181 rdf:type schema:CreativeWork
182 https://doi.org/10.1109/tamd.2009.2037732 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061488121
183 rdf:type schema:CreativeWork
184 https://doi.org/10.1145/1143997.1144062 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019142689
185 rdf:type schema:CreativeWork
186 https://doi.org/10.1145/1830483.1830506 schema:sameAs https://app.dimensions.ai/details/publication/pub.1016671411
187 rdf:type schema:CreativeWork
188 https://doi.org/10.1145/2001576.2001708 schema:sameAs https://app.dimensions.ai/details/publication/pub.1032890822
189 rdf:type schema:CreativeWork
190 https://doi.org/10.1145/2463372.2463398 schema:sameAs https://app.dimensions.ai/details/publication/pub.1020121547
191 rdf:type schema:CreativeWork
192 https://doi.org/10.1145/2739480.2754736 schema:sameAs https://app.dimensions.ai/details/publication/pub.1023554939
193 rdf:type schema:CreativeWork
194 https://doi.org/10.1162/106365600568086 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003615653
195 rdf:type schema:CreativeWork
196 https://doi.org/10.1162/106365602320169811 schema:sameAs https://app.dimensions.ai/details/publication/pub.1033705757
197 rdf:type schema:CreativeWork
198 https://doi.org/10.1162/evco_a_00004 schema:sameAs https://app.dimensions.ai/details/publication/pub.1029055082
199 rdf:type schema:CreativeWork
200 https://doi.org/10.1162/evco_a_00025 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022319433
201 rdf:type schema:CreativeWork
202 https://doi.org/10.1162/evco_a_00048 schema:sameAs https://app.dimensions.ai/details/publication/pub.1043746503
203 rdf:type schema:CreativeWork
204 https://doi.org/10.1162/evco_a_00173 schema:sameAs https://app.dimensions.ai/details/publication/pub.1021082556
205 rdf:type schema:CreativeWork
206 https://doi.org/10.1177/0278364906065378 schema:sameAs https://app.dimensions.ai/details/publication/pub.1035405028
207 rdf:type schema:CreativeWork
208 https://doi.org/10.1177/105971239700500305 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030498648
209 rdf:type schema:CreativeWork
210 https://doi.org/10.1371/journal.pone.0136406 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045649287
211 rdf:type schema:CreativeWork
212 https://doi.org/10.5772/53089 schema:sameAs https://app.dimensions.ai/details/publication/pub.1073125581
213 rdf:type schema:CreativeWork
214 https://doi.org/10.7551/978-0-262-33027-5-ch059 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099482595
215 rdf:type schema:CreativeWork
216 https://www.grid.ac/institutes/grid.45349.3f schema:alternateName Lisbon University Institute
217 schema:name BioMachines Lab, Lisbon, Portugal
218 Instituto Universitário de Lisboa (ISCTE-IUL), Lisbon, Portugal
219 Instituto de Telecomunicações, Lisbon, Portugal
220 rdf:type schema:Organization
221 https://www.grid.ac/institutes/grid.9983.b schema:alternateName University of Lisbon
222 schema:name BioISI, Faculdade de Ciências, Universidade de Lisboa, Lisbon, Portugal
223 BioMachines Lab, Lisbon, Portugal
224 Instituto de Telecomunicações, Lisbon, Portugal
225 rdf:type schema:Organization
 




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


...