{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:I5NLUQMKEOIRU5QFGMQNKT5AZM","short_pith_number":"pith:I5NLUQMK","schema_version":"1.0","canonical_sha256":"475aba418a23911a76053320d54fa0cb1d1ed26faf618aad5b87f8905d81cbb7","source":{"kind":"arxiv","id":"2603.15013","version":3},"attestation_state":"computed","paper":{"title":"CycleRL: Sim-to-Real Deep Reinforcement Learning for Robust Autonomous Bicycle Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CycleRL trains a PPO policy in simulation that transfers directly to physical bicycle hardware for balance and tracking.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Gelu Liu, Junliang Wu, Songyuan Li, Teng Wang, Xiangwei Zhu, Zhijie Wu","submitted_at":"2026-03-16T09:17:51Z","abstract_excerpt":"Autonomous bicycles offer a promising agile solution for urban mobility and last-mile logistics. However, conventional control strategies often struggle with underactuated nonlinear dynamics, suffering from sensitivity to model mismatches and limited adaptability to real-world uncertainties. To address this, we develop CycleRL, a comprehensive sim-to-real framework for robust autonomous bicycle control. Our approach establishes a direct perception-to-action mapping within the high-fidelity NVIDIA Isaac Sim environment, leveraging Proximal Policy Optimization (PPO) to optimize the control polic"},"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":true},"canonical_record":{"source":{"id":"2603.15013","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-03-16T09:17:51Z","cross_cats_sorted":[],"title_canon_sha256":"d639c6f0d46a0e9d6d17ab963bb7b9172a3c6fb14622b41d94b97b6e92c4930f","abstract_canon_sha256":"e42ff80effcd12cf3ec2c971535605e85c299c658a8d58ed5a2a212454ff789d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:15:18.362163Z","signature_b64":"pcxVjfjAWYO9Wwod0AXU6i6N13IToI3EZiVbcXS3Ue8WzzIPvR1EvcMnqDVZcJw7fvZQzUtWbpLeQ45O+GFCCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"475aba418a23911a76053320d54fa0cb1d1ed26faf618aad5b87f8905d81cbb7","last_reissued_at":"2026-06-26T01:15:18.361625Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:15:18.361625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CycleRL: Sim-to-Real Deep Reinforcement Learning for Robust Autonomous Bicycle Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CycleRL trains a PPO policy in simulation that transfers directly to physical bicycle hardware for balance and tracking.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Gelu Liu, Junliang Wu, Songyuan Li, Teng Wang, Xiangwei Zhu, Zhijie Wu","submitted_at":"2026-03-16T09:17:51Z","abstract_excerpt":"Autonomous bicycles offer a promising agile solution for urban mobility and last-mile logistics. However, conventional control strategies often struggle with underactuated nonlinear dynamics, suffering from sensitivity to model mismatches and limited adaptability to real-world uncertainties. To address this, we develop CycleRL, a comprehensive sim-to-real framework for robust autonomous bicycle control. Our approach establishes a direct perception-to-action mapping within the high-fidelity NVIDIA Isaac Sim environment, leveraging Proximal Policy Optimization (PPO) to optimize the control polic"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"CycleRL achieves a 99.90% balance success rate, 1.15° heading tracking error, and 0.18 m/s velocity tracking error in simulation, with successful hardware deployment that validates DRL as offering superior adaptability over traditional methods.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That systematic domain randomization over a limited set of simulation parameters is sufficient to cover all real-world uncertainties and enable zero-shot transfer to physical hardware without additional adaptation or fine-tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CycleRL trains a PPO policy in Isaac Sim with domain randomization to achieve 99.9% balance success and direct hardware transfer for autonomous bicycle control.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CycleRL trains a PPO policy in simulation that transfers directly to physical bicycle hardware for balance and tracking.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a970ae49f726748f34243f01a428fefa1650167ea5d9ee3a7ae23cff98d93ace"},"source":{"id":"2603.15013","kind":"arxiv","version":3},"verdict":{"id":"ec36a41f-82c1-4726-b4a6-caf623a7545f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T10:41:17.457744Z","strongest_claim":"CycleRL achieves a 99.90% balance success rate, 1.15° heading tracking error, and 0.18 m/s velocity tracking error in simulation, with successful hardware deployment that validates DRL as offering superior adaptability over traditional methods.","one_line_summary":"CycleRL trains a PPO policy in Isaac Sim with domain randomization to achieve 99.9% balance success and direct hardware transfer for autonomous bicycle control.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That systematic domain randomization over a limited set of simulation parameters is sufficient to cover all real-world uncertainties and enable zero-shot transfer to physical hardware without additional adaptation or fine-tuning.","pith_extraction_headline":"CycleRL trains a PPO policy in simulation that transfers directly to physical bicycle hardware for balance and tracking."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.15013/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"5f9cd9c3fd499629b3a9f3042127cedd64ceac46f0af372e23ad2d9aa594d7cc"},"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":"2603.15013","created_at":"2026-06-26T01:15:18.361683+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.15013v3","created_at":"2026-06-26T01:15:18.361683+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.15013","created_at":"2026-06-26T01:15:18.361683+00:00"},{"alias_kind":"pith_short_12","alias_value":"I5NLUQMKEOIR","created_at":"2026-06-26T01:15:18.361683+00:00"},{"alias_kind":"pith_short_16","alias_value":"I5NLUQMKEOIRU5QF","created_at":"2026-06-26T01:15:18.361683+00:00"},{"alias_kind":"pith_short_8","alias_value":"I5NLUQMK","created_at":"2026-06-26T01:15:18.361683+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I5NLUQMKEOIRU5QFGMQNKT5AZM","json":"https://pith.science/pith/I5NLUQMKEOIRU5QFGMQNKT5AZM.json","graph_json":"https://pith.science/api/pith-number/I5NLUQMKEOIRU5QFGMQNKT5AZM/graph.json","events_json":"https://pith.science/api/pith-number/I5NLUQMKEOIRU5QFGMQNKT5AZM/events.json","paper":"https://pith.science/paper/I5NLUQMK"},"agent_actions":{"view_html":"https://pith.science/pith/I5NLUQMKEOIRU5QFGMQNKT5AZM","download_json":"https://pith.science/pith/I5NLUQMKEOIRU5QFGMQNKT5AZM.json","view_paper":"https://pith.science/paper/I5NLUQMK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.15013&json=true","fetch_graph":"https://pith.science/api/pith-number/I5NLUQMKEOIRU5QFGMQNKT5AZM/graph.json","fetch_events":"https://pith.science/api/pith-number/I5NLUQMKEOIRU5QFGMQNKT5AZM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I5NLUQMKEOIRU5QFGMQNKT5AZM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I5NLUQMKEOIRU5QFGMQNKT5AZM/action/storage_attestation","attest_author":"https://pith.science/pith/I5NLUQMKEOIRU5QFGMQNKT5AZM/action/author_attestation","sign_citation":"https://pith.science/pith/I5NLUQMKEOIRU5QFGMQNKT5AZM/action/citation_signature","submit_replication":"https://pith.science/pith/I5NLUQMKEOIRU5QFGMQNKT5AZM/action/replication_record"}},"created_at":"2026-06-26T01:15:18.361683+00:00","updated_at":"2026-06-26T01:15:18.361683+00:00"}