Metraipolis › archive › dc_d54ff9aaeb9f

INTERACT: Interactive Planning for Autonomous Driving via Anchor-Conditioned Prediction and Trust-Region Refinement — arXiv:2609.31137

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31137
License (as archived)
CC0-1.0
Archived
2026-10-08T03:14:59.782Z
SHA-256 of the archived text
fca3472b2e56f49fab1b05cf7dc177321b0be89f9c33cee17571d4cf1437bdc0
Stable URL of this page
https://metraipolis.com/documento/dc_d54ff9aaeb9f

How to cite

INTERACT: Interactive Planning for Autonomous Driving via Anchor-Conditioned Prediction and Trust-Region Refinement — arXiv:2609.31137 — arXiv (en), https://arxiv.org/abs/2609.31137 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d54ff9aaeb9f (Metraipolis archive dc_d54ff9aaeb9f, sha256 fca3472b2e56f49fab1b05cf7dc177321b0be89f9c33cee17571d4cf1437bdc0)
BibTeX
@misc{dcd54ff9aaeb9f,
  title = {INTERACT: Interactive Planning for Autonomous Driving via Anchor-Conditioned Prediction and Trust-Region Refinement — arXiv:2609.31137},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31137},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d54ff9aaeb9f; sha256 fca3472b2e56f49fab1b05cf7dc177321b0be89f9c33cee17571d4cf1437bdc0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31137. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Driving in dense urban traffic is interactive: whether a merge or an unprotected turn succeeds depends on how surrounding agents respond to the ego vehicle. Conventional planners predict first and plan second and, therefore, cannot account for this dependency. Methods that integrate prediction and planning either train both jointly, which introduces task interference, or keep them separate and are restricted to a predefined set of proposals. We present INTERACT: Interactive Planning for Autonomous Driving via Anchor-Conditioned Prediction and Trust-Region Refinement. Our key insight is that surrounding agents react to the intent a trajectory expresses rather than to its exact realization, so a single reactive prediction stays valid across an entire family of plans. INTERACT therefore decomposes interactive planning into prediction across driving intents and optimization within each intent. We derive a small set of diverse intents, which we call anchors, from map geometry, query a dedicated ego-conditioned prediction model once per anchor, and refine every anchor with the Cross-Entropy Method under a trust-region penalty that keeps the refined plan close enough to its anchor for the conditioned reaction to still apply. Prediction thus remains a separate model, avoiding task interference, while conditioning on anchors preserves the dependency. Because each anchor is refined continuously, the final plan is not restricted to the anchor set, yet INTERACT requires only one predictor query per anchor rather than one per candidate plan, with all anchors processed in parallel. On the nuPlan and interPlan closed-loop benchmarks, INTERACT sets a new state of the art, with the largest gains precisely in the interactive scenarios that motivate the method. The code will be released upon acceptance.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-28 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.31137 — 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 2026-10-08T02:58:08.925Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).