Librarian View
Last updated in SearchWorks on December 4, 2023 10:06am
LEADER 04377nam a22003733i 4500
001
a12741597
003
SIRSI
006
m d
007
cr un
008
180828t20182018cau om 000 0 eng d
035
a| (Sirsi) dorxm179nc3440
040
a| CSt
b| eng
e| rda
c| CSt
100
1
a| Ichter, Brian,
e| author.
245
1
0
a| Massive parallelism and sampling strategies for robust and real-time robotic motion planning /
c| Brian Ichter.
264
1
a| [Stanford, California] :
b| [Stanford University],
c| 2018.
264
4
c| ©2018
300
a| 1 online resource.
336
a| text
2| rdacontent
337
a| computer
2| rdamedia
338
a| online resource
2| rdacarrier
500
a| Submitted to the Department of Aeronautics and Astronautics.
502
g| Thesis
b| Ph.D.
c| Stanford University
d| 2018.
520
3
a| Motion planning is a fundamental problem in robotics, whereby one seeks to compute a low-cost trajectory from an initial state to a goal region that avoids any obstacles. Sampling-based motion planning algorithms have emerged as an effective paradigm for planning with complex, high-dimensional robotic systems. These algorithms maintain only an implicit representation of the state space, constructed by sampling the free state space and locally connecting samples (under the supervision of a collision checking module). This thesis presents approaches towards enabling real-time and robust sampling-based motion planning with improved sampling strategies and massive parallelism. In the first part of this thesis, we discuss algorithms to leverage massively parallel hardware (GPUs) to accelerate planning and to consider robustness during the planning process. We present an algorithm capable of planning at rates amenable to application within control loops, ∼10 ms. This algorithm uses approximate dynamic programming to explore the state space in a massively-parallel, near-optimal manner. We further present two algorithms capable of real-time, uncertainty-aware and perception-aware motion planning that exhaustively explore the state space via a multiobjective search. This search identifies a Pareto set of promising paths (in terms of cost and robustness) and certifies their robustness via Monte Carlo methods. We demonstrate the effectiveness of these algorithm in numerical simulations and a physical experiment on a quadrotor. In the second part of this thesis, we examine sampling-strategies for probing the state space; traditionally this has been uniform, independent, and identically distributed (i.i.d.) random points. We present a methodology for biasing the sample distribution towards regions of the state space in which the solution trajectory is likely to lie. This distribution is learned via a conditional variational autoencoder, allowing a general methodology, which can be used in combination with any sampling- based planner and can effectively exploit the underlying structure of a planning problem while maintaining the theoretical guarantees of sampling-based approaches. We also analyze the use of deterministic, low-dispersion samples instead of i.i.d. random points. We show that this allows deterministic asymptotic optimality (as opposed to probabilistic), a convergence rate bound in terms of the sample dispersion, reduced computational complexity, and improved practical performance. The technical approaches in this work are applicable to general robotic systems and lay the foundations of robustness and algorithmic speed required for robotic systems operating in the world.
700
1
a| Pavone, Marco,
d| 1980-
e| degree supervisor.
4| ths
0| http://id.loc.gov/authorities/names/no2012120124
700
1
a| Olukotun, Oyekunle Ayinde
e| degree committee member.
4| ths
0| http://id.loc.gov/authorities/names/no2007156893
700
1
a| Rock, Stephen M.
e| degree committee member.
4| ths
0| http://id.loc.gov/authorities/names/no2010078141
710
2
a| Stanford University.
b| Department of Aeronautics and Astronautics.
0| http://id.loc.gov/authorities/names/n82229395
596
a| 21 22
035
a| (OCoLC-M)1050752173
856
4
0
u| http://purl.stanford.edu/xm179nc3440
x| SDR-PURL
x| item
035
a| (Sirsi) dorxm179nc3440
999
f
f
i| c0de698e-cd1d-5513-90b2-d4559de59ae4
s| b70f7451-e446-53e7-860e-88ab3cba4dba
Holdings JSON
{ "holdings": [ { "id": "6dbecd20-234a-5389-8795-51092810ac6e", "hrid": "ah12741597_2", "notes": [ ], "_version": 1, "metadata": { "createdDate": "2023-08-21T18:53:50.325Z", "updatedDate": "2023-08-21T18:53:50.325Z", "createdByUserId": "58d0aaf6-dcda-4d5e-92da-012e6b7dd766", "updatedByUserId": "58d0aaf6-dcda-4d5e-92da-012e6b7dd766" }, "sourceId": "f32d531e-df79-46b3-8932-cdd35f7a2264", "boundWith": null, "formerIds": [ ], "illPolicy": null, "instanceId": "c0de698e-cd1d-5513-90b2-d4559de59ae4", "holdingsType": { "id": "996f93e2-5b5e-4cf2-9168-33ced1f95eed", "name": "Electronic", "source": "folio" }, "holdingsItems": [ ], "callNumberType": null, "holdingsTypeId": "996f93e2-5b5e-4cf2-9168-33ced1f95eed", "electronicAccess": [ ], "bareHoldingsItems": [ ], "holdingsStatements": [ ], "statisticalCodeIds": [ ], "administrativeNotes": [ ], "effectiveLocationId": "1b14e21c-8d47-45c7-bc49-456a0086422b", "permanentLocationId": "1b14e21c-8d47-45c7-bc49-456a0086422b", "suppressFromDiscovery": false, "holdingsStatementsForIndexes": [ ], "holdingsStatementsForSupplements": [ ], "location": { "effectiveLocation": { "id": "1b14e21c-8d47-45c7-bc49-456a0086422b", "code": "SUL-SDR", "name": "Stanford Digital Repository", "campus": { "id": "c365047a-51f2-45ce-8601-e421ca3615c5", "code": "SUL", "name": "Stanford Libraries" }, "details": { }, "library": { "id": "c1a86906-ced0-46cb-8f5b-8cef542bdd00", "code": "SUL", "name": "SUL" }, "isActive": true, "institution": { "id": "8d433cdd-4e8f-4dc1-aa24-8a4ddb7dc929", "code": "SU", "name": "Stanford University" } }, "permanentLocation": { "id": "1b14e21c-8d47-45c7-bc49-456a0086422b", "code": "SUL-SDR", "name": "Stanford Digital Repository", "campus": { "id": "c365047a-51f2-45ce-8601-e421ca3615c5", "code": "SUL", "name": "Stanford Libraries" }, "details": { }, "library": { "id": "c1a86906-ced0-46cb-8f5b-8cef542bdd00", "code": "SUL", "name": "SUL" }, "isActive": true, "institution": { "id": "8d433cdd-4e8f-4dc1-aa24-8a4ddb7dc929", "code": "SU", "name": "Stanford University" } } } }, { "id": "a2861779-64c4-5711-91e0-3dbbb7c9fa70", "hrid": "ah12741597_1", "notes": [ ], "_version": 1, "metadata": { "createdDate": "2023-08-21T18:53:45.591Z", "updatedDate": "2023-08-21T18:53:45.591Z", "createdByUserId": "58d0aaf6-dcda-4d5e-92da-012e6b7dd766", "updatedByUserId": "58d0aaf6-dcda-4d5e-92da-012e6b7dd766" }, "sourceId": "f32d531e-df79-46b3-8932-cdd35f7a2264", "boundWith": null, "formerIds": [ ], "illPolicy": null, "callNumber": "3781 2018 I", "instanceId": "c0de698e-cd1d-5513-90b2-d4559de59ae4", "holdingsType": { "id": "5684e4a3-9279-4463-b6ee-20ae21bbec07", "name": "Book", "source": "local" }, "holdingsItems": [ ], "callNumberType": { "id": "28927d76-e097-4f63-8510-e56f2b7a3ad0", "name": "Shelving control number", "source": "folio" }, "holdingsTypeId": "5684e4a3-9279-4463-b6ee-20ae21bbec07", "callNumberTypeId": "28927d76-e097-4f63-8510-e56f2b7a3ad0", "electronicAccess": [ ], "bareHoldingsItems": [ ], "holdingsStatements": [ ], "statisticalCodeIds": [ ], "administrativeNotes": [ ], "effectiveLocationId": "150b8273-b10b-4907-b43f-a3d4f89bc79f", "permanentLocationId": "150b8273-b10b-4907-b43f-a3d4f89bc79f", "suppressFromDiscovery": false, "holdingsStatementsForIndexes": [ ], "holdingsStatementsForSupplements": [ ], "location": { "effectiveLocation": { "id": "150b8273-b10b-4907-b43f-a3d4f89bc79f", "code": "SPEC-SAL3-U-ARCHIVES", "name": "University Archives", "campus": { "id": "c365047a-51f2-45ce-8601-e421ca3615c5", "code": "SUL", "name": "Stanford Libraries" }, "details": { "pageAeonSite": "SPECUA" }, "library": { "id": "5b61a365-6b39-408c-947d-f8861a7ba8ae", "code": "SPEC-COLL", "name": "Special Collections" }, "isActive": true, "institution": { "id": "8d433cdd-4e8f-4dc1-aa24-8a4ddb7dc929", "code": "SU", "name": "Stanford University" } }, "permanentLocation": { "id": "150b8273-b10b-4907-b43f-a3d4f89bc79f", "code": "SPEC-SAL3-U-ARCHIVES", "name": "University Archives", "campus": { "id": "c365047a-51f2-45ce-8601-e421ca3615c5", "code": "SUL", "name": "Stanford Libraries" }, "details": { "pageAeonSite": "SPECUA" }, "library": { "id": "5b61a365-6b39-408c-947d-f8861a7ba8ae", "code": "SPEC-COLL", "name": "Special Collections" }, "isActive": true, "institution": { "id": "8d433cdd-4e8f-4dc1-aa24-8a4ddb7dc929", "code": "SU", "name": "Stanford University" } } } } ], "items": [ { "id": "23ff775f-9e69-531f-90a6-576e29e356dc", "hrid": "ai12741597_1_1", "notes": [ ], "status": "Available", "barcode": "36105227900466", "request": null, "_version": 1, "metadata": { "createdDate": "2023-08-21T18:54:35.888Z", "updatedDate": "2023-08-21T18:54:35.888Z", "createdByUserId": "58d0aaf6-dcda-4d5e-92da-012e6b7dd766", "updatedByUserId": "58d0aaf6-dcda-4d5e-92da-012e6b7dd766" }, "formerIds": [ ], "callNumber": { "typeId": "28927d76-e097-4f63-8510-e56f2b7a3ad0", "typeName": "Shelving control number", "callNumber": "3781 2018 I" }, "copyNumber": "1", "yearCaption": [ ], "materialType": "book", "callNumberType": { "id": "28927d76-e097-4f63-8510-e56f2b7a3ad0", "name": "Shelving control number", "source": "folio" }, "materialTypeId": "1a54b431-2e4f-452d-9cae-9cee66c9a892", "numberOfPieces": "1", "circulationNotes": [ ], "electronicAccess": [ ], "holdingsRecordId": "a2861779-64c4-5711-91e0-3dbbb7c9fa70", "discoverySuppress": false, "itemDamagedStatus": null, "permanentLoanType": "Non-circulating", "temporaryLoanType": null, "statisticalCodeIds": [ ], "administrativeNotes": [ ], "effectiveLocationId": "150b8273-b10b-4907-b43f-a3d4f89bc79f", "permanentLoanTypeId": "52d7b849-b6d8-4fb3-b2ab-a9b0eb41b6fd", "suppressFromDiscovery": false, "effectiveShelvingOrder": "43781 42018 I 11", "effectiveCallNumberComponents": { "typeId": "28927d76-e097-4f63-8510-e56f2b7a3ad0", "callNumber": "3781 2018 I" }, "location": { "effectiveLocation": { "id": "150b8273-b10b-4907-b43f-a3d4f89bc79f", "code": "SPEC-SAL3-U-ARCHIVES", "name": "University Archives", "campus": { "id": "c365047a-51f2-45ce-8601-e421ca3615c5", "code": "SUL", "name": "Stanford Libraries" }, "details": { "pageAeonSite": "SPECUA" }, "library": { "id": "5b61a365-6b39-408c-947d-f8861a7ba8ae", "code": "SPEC-COLL", "name": "Special Collections" }, "isActive": true, "institution": { "id": "8d433cdd-4e8f-4dc1-aa24-8a4ddb7dc929", "code": "SU", "name": "Stanford University" } } }, "courses": [ ] } ] }
FOLIO JSON
{ "pieces": [ null ], "instance": { "id": "c0de698e-cd1d-5513-90b2-d4559de59ae4", "hrid": "a12741597", "notes": [ { "note": "Submitted to the Department of Aeronautics and Astronautics", "staffOnly": false, "instanceNoteTypeId": "6a2533a7-4de2-4e64-8466-074c2fa9308c" }, { "note": "Thesis Ph.D. Stanford University 2018", "staffOnly": false, "instanceNoteTypeId": "b73cc9c2-c9fa-49aa-964f-5ae1aa754ecd" }, { "note": "Motion planning is a fundamental problem in robotics, whereby one seeks to compute a low-cost trajectory from an initial state to a goal region that avoids any obstacles. Sampling-based motion planning algorithms have emerged as an effective paradigm for planning with complex, high-dimensional robotic systems. These algorithms maintain only an implicit representation of the state space, constructed by sampling the free state space and locally connecting samples (under the supervision of a collision checking module). This thesis presents approaches towards enabling real-time and robust sampling-based motion planning with improved sampling strategies and massive parallelism. In the first part of this thesis, we discuss algorithms to leverage massively parallel hardware (GPUs) to accelerate planning and to consider robustness during the planning process. We present an algorithm capable of planning at rates amenable to application within control loops, ∼10 ms. This algorithm uses approximate dynamic programming to explore the state space in a massively-parallel, near-optimal manner. We further present two algorithms capable of real-time, uncertainty-aware and perception-aware motion planning that exhaustively explore the state space via a multiobjective search. This search identifies a Pareto set of promising paths (in terms of cost and robustness) and certifies their robustness via Monte Carlo methods. We demonstrate the effectiveness of these algorithm in numerical simulations and a physical experiment on a quadrotor. In the second part of this thesis, we examine sampling-strategies for probing the state space; traditionally this has been uniform, independent, and identically distributed (i.i.d.) random points. We present a methodology for biasing the sample distribution towards regions of the state space in which the solution trajectory is likely to lie. This distribution is learned via a conditional variational autoencoder, allowing a general methodology, which can be used in combination with any sampling- based planner and can effectively exploit the underlying structure of a planning problem while maintaining the theoretical guarantees of sampling-based approaches. We also analyze the use of deterministic, low-dispersion samples instead of i.i.d. random points. We show that this allows deterministic asymptotic optimality (as opposed to probabilistic), a convergence rate bound in terms of the sample dispersion, reduced computational complexity, and improved practical performance. The technical approaches in this work are applicable to general robotic systems and lay the foundations of robustness and algorithmic speed required for robotic systems operating in the world", "staffOnly": false, "instanceNoteTypeId": "10e2e11b-450f-45c8-b09b-0f819999966e" } ], "title": "Massive parallelism and sampling strategies for robust and real-time robotic motion planning / Brian Ichter.", "series": [ ], "source": "MARC", "_version": 1, "editions": [ ], "metadata": { "createdDate": "2023-08-21T18:52:16.700Z", "updatedDate": "2023-08-21T18:52:16.700Z", "createdByUserId": "58d0aaf6-dcda-4d5e-92da-012e6b7dd766", "updatedByUserId": "58d0aaf6-dcda-4d5e-92da-012e6b7dd766" }, "statusId": "9634a5ab-9228-4703-baf2-4d12ebc77d56", "subjects": [ ], "languages": [ "eng" ], "indexTitle": "Massive parallelism and sampling strategies for robust and real-time robotic motion planning", "identifiers": [ { "value": "(Sirsi) dorxm179nc3440", "identifierTypeId": "7e591197-f335-4afb-bc6d-a6d76ca3bace" }, { "value": "(OCoLC-M)1050752173", "identifierTypeId": "439bfbae-75bc-4f74-9fc7-b2a2d47ce3ef" } ], "publication": [ { "role": "Publication", "place": "[Stanford, California]", "publisher": "[Stanford University]", "dateOfPublication": "2018" }, { "role": "Copyright notice date", "place": "", "publisher": "", "dateOfPublication": "©2018" } ], "contributors": [ { "name": "Ichter, Brian", "primary": true, "contributorTypeId": "6e09d47d-95e2-4d8a-831b-f777b8ef6d81", "contributorTypeText": "author.", "contributorNameTypeId": "2b94c631-fca9-4892-a730-03ee529ffe2a" }, { "name": "Pavone, Marco, 1980-", "primary": false, "contributorTypeId": "cce475f7-ccfa-4e15-adf8-39f907788515", "contributorTypeText": "Thesis advisor", "contributorNameTypeId": "2b94c631-fca9-4892-a730-03ee529ffe2a" }, { "name": "Olukotun, Oyekunle Ayinde", "primary": false, "contributorTypeId": "cce475f7-ccfa-4e15-adf8-39f907788515", "contributorTypeText": "Thesis advisor", "contributorNameTypeId": "2b94c631-fca9-4892-a730-03ee529ffe2a" }, { "name": "Rock, Stephen M", "primary": false, "contributorTypeId": "cce475f7-ccfa-4e15-adf8-39f907788515", "contributorTypeText": "Thesis advisor", "contributorNameTypeId": "2b94c631-fca9-4892-a730-03ee529ffe2a" }, { "name": "Stanford University. Department of Aeronautics and Astronautics", "primary": false, "contributorTypeId": "9f0a2cf0-7a9b-45a2-a403-f68d2850d07c", "contributorNameTypeId": "2e48e713-17f3-4c13-a9f8-23845bb210aa" } ], "catalogedDate": "2018-08-30", "staffSuppress": false, "instanceTypeId": "6312d172-f0cf-40f6-b27d-9fa8feaf332f", "previouslyHeld": false, "classifications": [ ], "instanceFormats": [ ], "electronicAccess": [ { "uri": "http://purl.stanford.edu/xm179nc3440", "name": "Resource", "relationshipId": "f5d0068e-6272-458e-8a81-b85e7b9a14aa" } ], "holdingsRecords2": [ ], "modeOfIssuanceId": "9d18a02f-5897-4c31-9106-c9abb5c7ae8b", "publicationRange": [ ], "statisticalCodes": [ ], "alternativeTitles": [ ], "discoverySuppress": false, "instanceFormatIds": [ "f5e8210f-7640-459b-a71f-552567f92369" ], "publicationPeriod": { "start": 2018 }, "statusUpdatedDate": "2023-08-21T18:52:16.499+0000", "statisticalCodeIds": [ "0f328803-cd6a-47c0-8e76-f3a775d56884" ], "administrativeNotes": [ ], "physicalDescriptions": [ "1 online resource." ], "publicationFrequency": [ ], "suppressFromDiscovery": false, "natureOfContentTermIds": [ ] }, "holdingSummaries": [ { "poLineId": null, "orderType": null, "orderStatus": null, "poLineNumber": null, "orderSentDate": null, "orderCloseReason": null, "polReceiptStatus": null } ] }
Circulation rules
group: any material-type: any loan-type: any location-library: RUMSEY-MAP or SPEC-COLL or HILA or CLASSICS => loan: No loan => request: No requests allowed => notice: Default notice => overdue: No fines => lost-item: $100 lost fee (line 533)
https://searchworks.stanford.edu/view/12741597,12741597,SPEC-SAL3-U-ARCHIVES,36105227900466,Available,any,any,any,,,RUMSEY-MAP or SPEC-COLL or HILA or CLASSICS,,No loan,No requests allowed,Default notice,No fines,$100 lost fee,533,5