Machine Learning for Robotics View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2012

AUTHORS

Pieter Abbeel

ABSTRACT

Robots are typically far less capable in autonomous mode than in tele-operated mode. The few exceptions tend to stem from long days (and more often weeks, or even years) of expert engineering for a specific robot and its operating environment. Current control methodology is quite slow and labor intensive. I believe advances in machine learning have the potential to revolutionize robotics. In this talk, I will present new machine learning techniques we have developed that are tailored to robotics. I will describe in depth “Apprenticeship learning”, a new approach to high-performance robot control based on learning for control from ensembles of expert human demonstrations. Our initial work in apprenticeship learning has enabled the most advanced helicopter aerobatics to-date, including maneuvers such as chaos, tic-tocs, and auto-rotation landings which only exceptional expert human pilots can fly. Our most recent work in apprenticeship learning is providing traction on learning to perform challenging robotic manipulation tasks, such as knot-tying. I will also briefly highlight three other machine learning for robotics developments: Inverse reinforcement learning and its application to quadruped locomotion, Safe exploration in reinforcement learning which enables robots to learn on their own, and Learning for perception with application to robotic laundry. More... »

PAGES

1-1

Book

TITLE

Machine Learning and Knowledge Discovery in Databases

ISBN

978-3-642-33459-7
978-3-642-33460-3

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-642-33460-3_1

DOI

http://dx.doi.org/10.1007/978-3-642-33460-3_1

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1045021000


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 California, Berkeley", 
          "id": "https://www.grid.ac/institutes/grid.47840.3f", 
          "name": [
            "University of California, Berkeley, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Abbeel", 
        "givenName": "Pieter", 
        "id": "sg:person.01076711071.23", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01076711071.23"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2012", 
    "datePublishedReg": "2012-01-01", 
    "description": "Robots are typically far less capable in autonomous mode than in tele-operated mode. The few exceptions tend to stem from long days (and more often weeks, or even years) of expert engineering for a specific robot and its operating environment. Current control methodology is quite slow and labor intensive. I believe advances in machine learning have the potential to revolutionize robotics. In this talk, I will present new machine learning techniques we have developed that are tailored to robotics. I will describe in depth \u201cApprenticeship learning\u201d, a new approach to high-performance robot control based on learning for control from ensembles of expert human demonstrations. Our initial work in apprenticeship learning has enabled the most advanced helicopter aerobatics to-date, including maneuvers such as chaos, tic-tocs, and auto-rotation landings which only exceptional expert human pilots can fly. Our most recent work in apprenticeship learning is providing traction on learning to perform challenging robotic manipulation tasks, such as knot-tying. I will also briefly highlight three other machine learning for robotics developments: Inverse reinforcement learning and its application to quadruped locomotion, Safe exploration in reinforcement learning which enables robots to learn on their own, and Learning for perception with application to robotic laundry.", 
    "editor": [
      {
        "familyName": "Flach", 
        "givenName": "Peter A.", 
        "type": "Person"
      }, 
      {
        "familyName": "De Bie", 
        "givenName": "Tijl", 
        "type": "Person"
      }, 
      {
        "familyName": "Cristianini", 
        "givenName": "Nello", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-642-33460-3_1", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-642-33459-7", 
        "978-3-642-33460-3"
      ], 
      "name": "Machine Learning and Knowledge Discovery in Databases", 
      "type": "Book"
    }, 
    "name": "Machine Learning for Robotics", 
    "pagination": "1-1", 
    "productId": [
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-642-33460-3_1"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "d672e67d31aac61802e086df6fdcb02aadca2458d1efc83977d50007cd41330f"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1045021000"
        ]
      }
    ], 
    "publisher": {
      "location": "Berlin, Heidelberg", 
      "name": "Springer Berlin Heidelberg", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-642-33460-3_1", 
      "https://app.dimensions.ai/details/publication/pub.1045021000"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-15T23:41", 
    "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/v90/0000000001_0000000264/records_8697_00000077.jsonl", 
    "type": "Chapter", 
    "url": "http://link.springer.com/10.1007/978-3-642-33460-3_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.10.1007/978-3-642-33460-3_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.10.1007/978-3-642-33460-3_1'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-33460-3_1'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-33460-3_1'


 

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

75 TRIPLES      22 PREDICATES      27 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-642-33460-3_1 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N8d5e40e86855449fb8c79e8a16f4b349
4 schema:datePublished 2012
5 schema:datePublishedReg 2012-01-01
6 schema:description Robots are typically far less capable in autonomous mode than in tele-operated mode. The few exceptions tend to stem from long days (and more often weeks, or even years) of expert engineering for a specific robot and its operating environment. Current control methodology is quite slow and labor intensive. I believe advances in machine learning have the potential to revolutionize robotics. In this talk, I will present new machine learning techniques we have developed that are tailored to robotics. I will describe in depth “Apprenticeship learning”, a new approach to high-performance robot control based on learning for control from ensembles of expert human demonstrations. Our initial work in apprenticeship learning has enabled the most advanced helicopter aerobatics to-date, including maneuvers such as chaos, tic-tocs, and auto-rotation landings which only exceptional expert human pilots can fly. Our most recent work in apprenticeship learning is providing traction on learning to perform challenging robotic manipulation tasks, such as knot-tying. I will also briefly highlight three other machine learning for robotics developments: Inverse reinforcement learning and its application to quadruped locomotion, Safe exploration in reinforcement learning which enables robots to learn on their own, and Learning for perception with application to robotic laundry.
7 schema:editor Nef860e0d1ac64074bc55da11f3f44906
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree true
11 schema:isPartOf N2b8b77bd827e42428b6931c7eef00643
12 schema:name Machine Learning for Robotics
13 schema:pagination 1-1
14 schema:productId N7ec08fc98b644f5ea30829c7abda71ed
15 N9df087c97f4b494bb2355b60d6bd1851
16 Nb6d6acc2cd2d441e91112ef4eb5288a4
17 schema:publisher N44248392ce524cd7a4d3d88e7427e070
18 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045021000
19 https://doi.org/10.1007/978-3-642-33460-3_1
20 schema:sdDatePublished 2019-04-15T23:41
21 schema:sdLicense https://scigraph.springernature.com/explorer/license/
22 schema:sdPublisher N502b040d4d344b808eb711a9f6ab5a01
23 schema:url http://link.springer.com/10.1007/978-3-642-33460-3_1
24 sgo:license sg:explorer/license/
25 sgo:sdDataset chapters
26 rdf:type schema:Chapter
27 N2b8b77bd827e42428b6931c7eef00643 schema:isbn 978-3-642-33459-7
28 978-3-642-33460-3
29 schema:name Machine Learning and Knowledge Discovery in Databases
30 rdf:type schema:Book
31 N44248392ce524cd7a4d3d88e7427e070 schema:location Berlin, Heidelberg
32 schema:name Springer Berlin Heidelberg
33 rdf:type schema:Organisation
34 N461dcc7db8b2479aad94ddda9b947dac schema:familyName Cristianini
35 schema:givenName Nello
36 rdf:type schema:Person
37 N4819263841bb4ae5a8821c044aaced9a rdf:first Nf5b6c2c3b82e4cd4bfc94bcd5953acde
38 rdf:rest Nb835c31f203141d78b855c61c3348d04
39 N502b040d4d344b808eb711a9f6ab5a01 schema:name Springer Nature - SN SciGraph project
40 rdf:type schema:Organization
41 N594dc34897b54f33b5dfebb08e356803 schema:familyName Flach
42 schema:givenName Peter A.
43 rdf:type schema:Person
44 N7ec08fc98b644f5ea30829c7abda71ed schema:name readcube_id
45 schema:value d672e67d31aac61802e086df6fdcb02aadca2458d1efc83977d50007cd41330f
46 rdf:type schema:PropertyValue
47 N8d5e40e86855449fb8c79e8a16f4b349 rdf:first sg:person.01076711071.23
48 rdf:rest rdf:nil
49 N9df087c97f4b494bb2355b60d6bd1851 schema:name doi
50 schema:value 10.1007/978-3-642-33460-3_1
51 rdf:type schema:PropertyValue
52 Nb6d6acc2cd2d441e91112ef4eb5288a4 schema:name dimensions_id
53 schema:value pub.1045021000
54 rdf:type schema:PropertyValue
55 Nb835c31f203141d78b855c61c3348d04 rdf:first N461dcc7db8b2479aad94ddda9b947dac
56 rdf:rest rdf:nil
57 Nef860e0d1ac64074bc55da11f3f44906 rdf:first N594dc34897b54f33b5dfebb08e356803
58 rdf:rest N4819263841bb4ae5a8821c044aaced9a
59 Nf5b6c2c3b82e4cd4bfc94bcd5953acde schema:familyName De Bie
60 schema:givenName Tijl
61 rdf:type schema:Person
62 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
63 schema:name Information and Computing Sciences
64 rdf:type schema:DefinedTerm
65 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
66 schema:name Artificial Intelligence and Image Processing
67 rdf:type schema:DefinedTerm
68 sg:person.01076711071.23 schema:affiliation https://www.grid.ac/institutes/grid.47840.3f
69 schema:familyName Abbeel
70 schema:givenName Pieter
71 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01076711071.23
72 rdf:type schema:Person
73 https://www.grid.ac/institutes/grid.47840.3f schema:alternateName University of California, Berkeley
74 schema:name University of California, Berkeley, USA
75 rdf:type schema:Organization
 




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


...