{"paper":{"title":"ShapeGrasp: Simultaneous Visuo-Haptic Shape Completion and Grasping for Improved Robot Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"ShapeGrasp updates object shape models with tactile data from real grasps to improve subsequent planning and success rates.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Lukas Rustler, Matej Hoffmann","submitted_at":"2026-05-04T08:49:52Z","abstract_excerpt":"Humans grasp unfamiliar objects by combining an initial visual estimate with tactile and proprioceptive feedback during interaction. We present ShapeGrasp, a robotic implementation of this approach. The proposed method is an iterative grasp-and-complete pipeline that couples implicit surface visuo-haptic shape completion (creation of full 3D shape from partial information) with physics-based grasp planning. From a single RGB-D view, ShapeGrasp infers a complete shape (point cloud or triangular mesh), generates candidate grasps via rigid-body simulation, and executes the best feasible grasp. Ea"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"To the best of our knowledge, this is the first approach that updates shape representations following a real-world grasp. We achieved superior results over baselines for both grippers (grasp success rate of 84% with a three-finger gripper and 91% with a two-finger gripper), while improving the 3D shape reconstruction quality in all evaluation metrics used.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the fusion of tactile surface contacts and gripper body occupancy with the initial visual estimate produces a sufficiently accurate updated shape model to enable reliable subsequent grasp planning in real-world conditions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ShapeGrasp improves grasp success on unknown objects to 84-91% by iteratively updating a 3D shape model with visuo-haptic feedback during real-world grasp attempts.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"ShapeGrasp updates object shape models with tactile data from real grasps to improve subsequent planning and success rates.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2631e13a28df592dc85732d13cc7216f402a313019d27a220740317e6f3a9ae1"},"source":{"id":"2605.02347","kind":"arxiv","version":2},"verdict":{"id":"ba61310f-375b-499a-9ace-c2d68b63462f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T18:32:12.940231Z","strongest_claim":"To the best of our knowledge, this is the first approach that updates shape representations following a real-world grasp. We achieved superior results over baselines for both grippers (grasp success rate of 84% with a three-finger gripper and 91% with a two-finger gripper), while improving the 3D shape reconstruction quality in all evaluation metrics used.","one_line_summary":"ShapeGrasp improves grasp success on unknown objects to 84-91% by iteratively updating a 3D shape model with visuo-haptic feedback during real-world grasp attempts.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the fusion of tactile surface contacts and gripper body occupancy with the initial visual estimate produces a sufficiently accurate updated shape model to enable reliable subsequent grasp planning in real-world conditions.","pith_extraction_headline":"ShapeGrasp updates object shape models with tactile data from real grasps to improve subsequent planning and success rates."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.02347/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T16:33:44.563807Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-20T03:31:22.605563Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T16:27:57.101676Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"fe086c51c45ccd2e970256f18f6fc79a1b0d2a7821bd49bb62ee44ae8d9d7589"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":3,"snapshot_sha256":"8276d92db5b56346f94f355156d3c4565f5b8f7fde5a5b44d2df0313527c1654"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}