Metraipolis › archive › dc_bb9566ddcd73

Knowledge-Guided Hierarchical Policy Learning for High-Precision Cylindrical Assembly under Tight Tolerances — arXiv:2609.06522

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.06522
License (as archived): CC0-1.0
Archived: 2026-10-16T15:30:56.788Z
SHA-256 of the archived text: e5e7446d92655a52f05b45ec2aa59cf11e538dffa7937ffe17621bb1d0e08a69
Stable URL of this page: https://metraipolis.com/documento/dc_bb9566ddcd73

How to cite

Knowledge-Guided Hierarchical Policy Learning for High-Precision Cylindrical Assembly under Tight Tolerances — arXiv:2609.06522 — arXiv (en), https://arxiv.org/abs/2609.06522 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bb9566ddcd73 (Metraipolis archive dc_bb9566ddcd73, sha256 e5e7446d92655a52f05b45ec2aa59cf11e538dffa7937ffe17621bb1d0e08a69)

BibTeX

@misc{dcbb9566ddcd73,
  title = {Knowledge-Guided Hierarchical Policy Learning for High-Precision Cylindrical Assembly under Tight Tolerances — arXiv:2609.06522},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.06522},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bb9566ddcd73; sha256 e5e7446d92655a52f05b45ec2aa59cf11e538dffa7937ffe17621bb1d0e08a69},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06522. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A hybrid hierarchical learning framework is proposed to achieve high-precision assembly of 170mm cylindrical components with tolerance of 0.1mm. The lower-level network integrates expert experience through Behavior Cloning (BC), giving the robot human-like intuition, and incorporates the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm to enhance training stability and robustness. The upper-level network dynamically adjusts the lower-level decisions based on heuristic rules, ensuring flexibility in operations. A simulated model is constructed to learn before transferring to real world. An efficient and safe training is allowed. Comparisons show that the reward curve converges within 500 episodes, indicating high learning efficiency. It also demonstrates better adaptability to initial conditions and pose errors, achieving satisfactory success rates even under extreme conditions. Moreover, the method exhibits good stability under Gaussian noise interference. In the real world, the assembly trajectory of the cylindrical segment shows smoother motion and less fluctuation.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.06522 — 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 2026-10-16T15:11:47.540Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).