Metraipolis › archive › dc_ec135fed776e

LEAP: Learning Emergent Active Perception for Quadruped Navigation — arXiv:2609.17628

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.17628
License (as archived): CC0-1.0
Archived: 2026-10-15T16:16:48.115Z
SHA-256 of the archived text: 57067ec8829b0d9993e5eb562cd85fdd3ce159e12cc1ee751bb251cb9d69ba39
Stable URL of this page: https://metraipolis.com/documento/dc_ec135fed776e

How to cite

LEAP: Learning Emergent Active Perception for Quadruped Navigation — arXiv:2609.17628 — arXiv (en), https://arxiv.org/abs/2609.17628 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ec135fed776e (Metraipolis archive dc_ec135fed776e, sha256 57067ec8829b0d9993e5eb562cd85fdd3ce159e12cc1ee751bb251cb9d69ba39)

BibTeX

@misc{dcec135fed776e,
  title = {LEAP: Learning Emergent Active Perception for Quadruped Navigation — arXiv:2609.17628},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.17628},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ec135fed776e; sha256 57067ec8829b0d9993e5eb562cd85fdd3ce159e12cc1ee751bb251cb9d69ba39},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17628. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Active perception allows autonomous agents to select their viewpoints rather than passively process the viewpoints given to them, enabling them to target where to reduce uncertainty about their environment. Learned systems typically encourage this behavior with hand-designed proxy objectives, such as coverage or curiosity bonuses, that may conflict with the task. In this work, we propose a method to learn emergent active perception (LEAP) without augmentation of the task objective. We formulate the problem of goal-oriented navigation over hazardous terrains with goals that must be discovered visually. We then propose an architecture for navigation policies with active perception, and train them on a terrain curriculum where task pressure alone leads to the emergence of gaze control. Key to this emergence, LEAP works on a gaze-invariant representation that integrates depth images into egocentric belief maps. We validate its performance in held-out evaluation scenarios, where it achieves a 92.7% success rate, compared to 74.2% for scripted or 34.5% for passive perception, and comes within 4.6 points of a privileged oracle. We validate that LEAP navigation policies, unchanged, can be directly applied to steering quadrupedal locomotion policies in physics simulation.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-17 in cs.CV).
Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.17628 — 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 2026-10-15T15:45:19.839Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).