{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:JO4GITG5USSQNMT46HEHBAA3OQ","short_pith_number":"pith:JO4GITG5","schema_version":"1.0","canonical_sha256":"4bb8644cdda4a506b27cf1c870801b74261c2a7d976b970f0c26dfb0d00472f5","source":{"kind":"arxiv","id":"1503.07619","version":2},"attestation_state":"computed","paper":{"title":"Shared Autonomy via Hindsight Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"J. Andrew Bagnell, Shervin Javdani, Siddhartha S. Srinivasa","submitted_at":"2015-03-26T04:50:49Z","abstract_excerpt":"In shared autonomy, user input and robot autonomy are combined to control a robot to achieve a goal. Often, the robot does not know a priori which goal the user wants to achieve, and must both predict the user's intended goal, and assist in achieving that goal. We formulate the problem of shared autonomy as a Partially Observable Markov Decision Process with uncertainty over the user's goal. We utilize maximum entropy inverse optimal control to estimate a distribution over the user's goal based on the history of inputs. Ideally, the robot assists the user by solving for an action which minimiz"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1503.07619","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2015-03-26T04:50:49Z","cross_cats_sorted":[],"title_canon_sha256":"a79a8b87c31dcb5665bc779b2b10a6e050d3850a5545dd686a2572b15ebbde6a","abstract_canon_sha256":"275fe6aaaefc6b5e7af6ea53dba043649d213af4e65701c344986173c7859a18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:18:31.024294Z","signature_b64":"d4PWJETSlmX7SVfnnBkke7ja/PgjLFr1PYNbb4rpzTJjD7DcwdhiwPIe4D4QAojWoDsBSicV31RKTSeTeSp6AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bb8644cdda4a506b27cf1c870801b74261c2a7d976b970f0c26dfb0d00472f5","last_reissued_at":"2026-05-18T02:18:31.023888Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:18:31.023888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Shared Autonomy via Hindsight Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"J. Andrew Bagnell, Shervin Javdani, Siddhartha S. Srinivasa","submitted_at":"2015-03-26T04:50:49Z","abstract_excerpt":"In shared autonomy, user input and robot autonomy are combined to control a robot to achieve a goal. Often, the robot does not know a priori which goal the user wants to achieve, and must both predict the user's intended goal, and assist in achieving that goal. We formulate the problem of shared autonomy as a Partially Observable Markov Decision Process with uncertainty over the user's goal. We utilize maximum entropy inverse optimal control to estimate a distribution over the user's goal based on the history of inputs. Ideally, the robot assists the user by solving for an action which minimiz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.07619","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1503.07619","created_at":"2026-05-18T02:18:31.023948+00:00"},{"alias_kind":"arxiv_version","alias_value":"1503.07619v2","created_at":"2026-05-18T02:18:31.023948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.07619","created_at":"2026-05-18T02:18:31.023948+00:00"},{"alias_kind":"pith_short_12","alias_value":"JO4GITG5USSQ","created_at":"2026-05-18T12:29:27.538025+00:00"},{"alias_kind":"pith_short_16","alias_value":"JO4GITG5USSQNMT4","created_at":"2026-05-18T12:29:27.538025+00:00"},{"alias_kind":"pith_short_8","alias_value":"JO4GITG5","created_at":"2026-05-18T12:29:27.538025+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.08928","citing_title":"Learning Reward Functions by Integrating Human Demonstrations and Preferences","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JO4GITG5USSQNMT46HEHBAA3OQ","json":"https://pith.science/pith/JO4GITG5USSQNMT46HEHBAA3OQ.json","graph_json":"https://pith.science/api/pith-number/JO4GITG5USSQNMT46HEHBAA3OQ/graph.json","events_json":"https://pith.science/api/pith-number/JO4GITG5USSQNMT46HEHBAA3OQ/events.json","paper":"https://pith.science/paper/JO4GITG5"},"agent_actions":{"view_html":"https://pith.science/pith/JO4GITG5USSQNMT46HEHBAA3OQ","download_json":"https://pith.science/pith/JO4GITG5USSQNMT46HEHBAA3OQ.json","view_paper":"https://pith.science/paper/JO4GITG5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1503.07619&json=true","fetch_graph":"https://pith.science/api/pith-number/JO4GITG5USSQNMT46HEHBAA3OQ/graph.json","fetch_events":"https://pith.science/api/pith-number/JO4GITG5USSQNMT46HEHBAA3OQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JO4GITG5USSQNMT46HEHBAA3OQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JO4GITG5USSQNMT46HEHBAA3OQ/action/storage_attestation","attest_author":"https://pith.science/pith/JO4GITG5USSQNMT46HEHBAA3OQ/action/author_attestation","sign_citation":"https://pith.science/pith/JO4GITG5USSQNMT46HEHBAA3OQ/action/citation_signature","submit_replication":"https://pith.science/pith/JO4GITG5USSQNMT46HEHBAA3OQ/action/replication_record"}},"created_at":"2026-05-18T02:18:31.023948+00:00","updated_at":"2026-05-18T02:18:31.023948+00:00"}