{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.11901", "kind": "paper", "url": "https://arxiv.org/abs/2606.11901"}, {"id": "gh:robotcontrolstack/duobench", "kind": "repo", "url": "https://github.com/RobotControlStack/duobench"}, {"kind": "website", "url": "https://duobench.github.io/"}], "authors": ["Tobias Jülg", "Seongjin Bien", "Simon Hilber", "Yannik Blei", "Pierre Krack", "Maximilian Li", "Sven Parusel", "Rudolf Lioutikov", "Florian Walter", "Wolfram Burgard"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.11901", "source_url": "https://arxiv.org/abs/2606.11901"}, "categories": ["Robot manipulation", "Robotics", "Robotics & Embodied AI"], "description": {"en": "DuoBench is a benchmarking framework for bimanual manipulation policies on the FR3 Duo platform, with eleven tasks across four coordination categories, simulated and partially real-world, plus human-teleoperated datasets. It proposes stage-based evaluation beyond binary success."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.11901", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.11901", "title": "DuoBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Technology Nuremberg", "Karlsruhe Institute of Technology", "Robotics Research (United States)", "Technical University of Munich"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.11901", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.11901", "source_url": "https://openalex.org/W7164420839"}, "key": "claire-radar:2606.11901", "modality": null, "name": "DuoBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_duobench_6c56fbaf", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "19e244967b07c481ee62f61ab2a75a80c802093bd4fd5f3ffe49413f898140c5", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.11901"}, "publisher": null, "released": "2026-06-10", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.11901", "source_url": "https://arxiv.org/abs/2606.11901"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-11901", "source": "claire_radar", "source_benchmark_id": "2606.11901", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Robotics & Embodied AI"], "area": "Robotics & Embodied AI", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/RobotControlStack/duobench", "githubScope": "benchmark_repo", "githubStars": 21, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.11901", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-10-01", "state": "stale"}}, "status": "fresh"}, "capabilities": ["Robot manipulation"], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "91b39f668a6ea3e7139246b4a6f3a126742af454aa3488105b80f5fc8faa4fc8", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "DuoBench is a benchmarking framework for bimanual manipulation policies on the FR3 Duo platform, with eleven tasks across four coordination categories, simulated and partially real-world, plus human-teleoperated datasets. It proposes stage-based evaluation beyond binary success.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We introduce DuoBench, an extensible benchmarking framework for bimanual manipulation policies on the FR3 Duo platform."}, "familyId": "bmf_bd016e251030", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "linked-from-project", "linkedUrl": "https://github.com/RobotControlStack/duobench", "url": "https://duobench.github.io/"}], "scope": "benchmark_repo", "url": "https://github.com/RobotControlStack/duobench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_duobench_6c56fbaf", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Robotics"], "links": {"code": "https://github.com/RobotControlStack/duobench", "data": null, "hfPaper": "https://huggingface.co/papers/2606.11901", "paper": "https://arxiv.org/abs/2606.11901", "pdf": "https://arxiv.org/pdf/2606.11901", "project": "https://duobench.github.io/", "report": "https://arxiv.org/abs/2606.11901"}, "metrics": [], "motivation": "Bimanual robot systems substantially expand manipulation capabilities, but coordinating two arms introduces additional control complexity and failure modes that are not well captured by existing benchmarks.", "name": "DuoBench", "oneLine": "DuoBench is a benchmarking framework for bimanual manipulation policies on the FR3 Duo platform, with eleven tasks across four coordination categories, simulated and partially real-world, plus human-teleoperated datasets. It proposes stage-based evaluation beyond binary success.", "paperTitle": "DuoBench: A Reproducible Benchmark for Bimanual Manipulation in Simulation and the Real World", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.11901", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-10", "source": {"authors": ["Tobias J\\\"ulg", "Seongjin Bien", "Simon Hilber", "Yannik Blei", "Pierre Krack", "Maximilian Li", "Sven Parusel", "Rudolf Lioutikov", "Florian Walter", "Wolfram Burgard"], "categories": ["cs.RO", "cs.AI"], "id": "2606.11901", "title": "DuoBench: A Reproducible Benchmark for Bimanual Manipulation in Simulation and the Real World", "type": "arxiv", "url": "https://arxiv.org/abs/2606.11901"}, "sourceUpdatedAt": "2026-06-10T10:28:04Z", "topics": ["Robotics"], "venueAttempts": [], "whyItMatters": "Provides a reproducible testbed for diagnosing failures in dual-arm policy learning, covering coordination challenges not captured by existing benchmarks. Useful for robotics researchers working on bimanual manipulation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
