Metraipolis › archive › dc_746d03e03ea4

VLX-Go: Robust Embodied Tracking through Multi-Stage Learning and On-Policy Refinement — arXiv:2610.19361

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.19361
License (as archived)
CC0-1.0
Archived
2026-10-15T20:39:05.386Z
SHA-256 of the archived text
4a678dc369dd54756af9e5480ef5a9d9c347cf93afd25edb2439315de1447daa
Stable URL of this page
https://metraipolis.com/documento/dc_746d03e03ea4

How to cite

VLX-Go: Robust Embodied Tracking through Multi-Stage Learning and On-Policy Refinement — arXiv:2610.19361 — arXiv (en), https://arxiv.org/abs/2610.19361 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_746d03e03ea4 (Metraipolis archive dc_746d03e03ea4, sha256 4a678dc369dd54756af9e5480ef5a9d9c347cf93afd25edb2439315de1447daa)
BibTeX
@misc{dc746d03e03ea4,
  title = {VLX-Go: Robust Embodied Tracking through Multi-Stage Learning and On-Policy Refinement — arXiv:2610.19361},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19361},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_746d03e03ea4; sha256 4a678dc369dd54756af9e5480ef5a9d9c347cf93afd25edb2439315de1447daa},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19361. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Embodied visual tracking requires a robot to identify a designated target from visual observations and control its own motion to follow that target through an environment. Following an isolated person is a comparatively simple demonstration of embodied visual tracking, but following the intended person among distractors remains challenging. Existing methods exhibit a substantial drop in success from single-target to distractor tracking, motivating a focus on the shared spaces that person-following robots must navigate. We present \method{}, a vision--language waypoint policy built around the hypothesis that visual and language representations should be aligned before tracking-specific motion is learned. The policy combines complementary frozen visual encoders, multiscale temporal context, a transformer backbone, and a lightweight head for robot-centric waypoint prediction. Its training progresses through vision--language alignment, multimodal reasoning mid-training, and tracking specialization on 19,532 oracle episodes. Compared with 41.54\% distractor-tracking success for our earlier OmTrackVLA model, the complete multi-stage recipe achieves 55.80\%. We then explore on-policy refinement using filtered oracle labels for states visited by the policy. This preliminary study adds 2.42 percentage points of distractor-tracking success, reaching 58.22\%, while reducing collision rate by 1.99 pts. The final policy records the highest distractor- and ambiguous-tracking success rates among the compared methods. These results support staged multimodal learning as a promising direction for tracking among distractors and motivate further study of on-policy refinement for person following in shared spaces.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Computation and Language (cs.CL); Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.19361 — 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 2026-10-15T19:36:18.288Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).