Metraipolis › archive › dc_8e2ce6399641
GraspBench: Execution-Aware Cross-Robot Evaluation of 6-DoF Grasp Generation in MuJoCo — arXiv:2611.07651
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.07651
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-06T14:42:32.670Z
- SHA-256 of the archived text
3c5bda322c39eb0e66370d079eeb950e89abfb8bb9d3996c8f23266d9b330d24- Stable URL of this page
https://metraipolis.com/documento/dc_8e2ce6399641
How to cite
GraspBench: Execution-Aware Cross-Robot Evaluation of 6-DoF Grasp Generation in MuJoCo — arXiv:2611.07651 — arXiv (en), https://arxiv.org/abs/2611.07651 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8e2ce6399641 (Metraipolis archive dc_8e2ce6399641, sha256 3c5bda322c39eb0e66370d079eeb950e89abfb8bb9d3996c8f23266d9b330d24)
BibTeX
@misc{dc8e2ce6399641,
title = {GraspBench: Execution-Aware Cross-Robot Evaluation of 6-DoF Grasp Generation in MuJoCo — arXiv:2611.07651},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.07651},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8e2ce6399641; sha256 3c5bda322c39eb0e66370d079eeb950e89abfb8bb9d3996c8f23266d9b330d24},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07651. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Modern 6-DoF grasp generators are often evaluated using grasp scores, dataset-level metrics, or single-robot demonstrations, yet proposal quality alone does not determine whether a grasp is executable by a particular robot. We present GraspBench, a controlled MuJoCo protocol for evaluating complete grasp-generation pipelines after robot-specific inverse-kinematics filtering, motion planning, and fixed approach-close-lift execution. GraspBench evaluates six configured pipelines across four robot embodiments, five diagnostic objects, and a structured tabletop pose grid, yielding 540 scenarios per method and 3,240 method-scenario evaluations in total. Missing outputs are conservatively counted as failures, and success follows the binary lift criterion produced by each method's execution runner. GraspGen achieves the highest overall success rate (73.1%), followed by EconomicGrasp (63.5%), while robot- and object-conditioned analyses reveal substantial variation across embodiments and object geometries. GPG produces the largest native candidate sets but achieves 44.3% success, indicating that proposal volume alone does not guarantee robot-executable grasps. Cluster-aware paired intervals support the principal method differences while not estimating repeated-execution uncertainty. The results characterize complete configured pipelines on fixed scenarios rather than intrinsic model quality or stochastic repeatability, showing that grasping performance depends jointly on the generator, robot embodiment, scene, and execution protocol. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.07651 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-06T14:18:42.683Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).