Metraipolis › archive › dc_030b0baae9e8

Evolving Dexterous Robots from Scratch — arXiv:2609.33101

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33101
License (as archived)
CC0-1.0
Archived
2026-10-07T22:39:55.088Z
SHA-256 of the archived text
2e19279df148173ce7590f99a88f44718d0747fa415f7c580d28c03da99d5360
Stable URL of this page
https://metraipolis.com/documento/dc_030b0baae9e8

How to cite

Evolving Dexterous Robots from Scratch — arXiv:2609.33101 — arXiv (en), https://arxiv.org/abs/2609.33101 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_030b0baae9e8 (Metraipolis archive dc_030b0baae9e8, sha256 2e19279df148173ce7590f99a88f44718d0747fa415f7c580d28c03da99d5360)
BibTeX
@misc{dc030b0baae9e8,
  title = {Evolving Dexterous Robots from Scratch — arXiv:2609.33101},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33101},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_030b0baae9e8; sha256 2e19279df148173ce7590f99a88f44718d0747fa415f7c580d28c03da99d5360},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33101. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Little is known about how to manually design agents capable of dexterous manipulation. Some design principles have been inferred from close examination of how animals manipulate objects, but these structures and behaviors have so far resisted biomimicry and may not be optimal for artificial machines. Here we evolve freeform robots to pick up, hold, rotate, and use diverse objects. Unlike other approaches to optimizing robot hands, we do not presuppose the presence, articulation, or geometry of any part of the body. Although familiar prehensile forms such as tails, beaks, paws and claws may emerge spontaneously under certain conditions--and while such conditions could be of interest to evolutionary biologists--de novo manipulator design can also reveal whole new solutions, overlooked or unknown structures which may be better suited for the task at hand. We use contrastive learning to create a highly searchable genetic embedding of design space, an autoregressive developmental model to decode designs, evolutionary strategies to find good designs, and reinforcement learning to train each evolved design. Winning designs were automatically converted into a manufacturable blueprint, printed, assembled and tested in the real world in a zero-shot manner. The results represent the state-of-the-art in evolutionary robotics in terms of performance, diversity and complexity.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Robotics (cs.RO) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.33101 — 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 2026-10-07T22:14:28.687Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).