{
  "id": 384,
  "url": "https://arxiv.org/abs/2606.31919v1",
  "title": "MVP-Nav: Multi-layer Value Map Planner Navigator",
  "summary": "Zero-shot Object Goal Navigation (ZSON) with RGB-only perception poses a fundamental challenge for embodied agents, as the absence of explicit depth information introduces severe physical uncertainty and semantic-physical misalignment. Existing approaches either rely on high-level semantic reasoning without geometric grounding or learn end-to-end policies that lack explicit physical constraints, often resulting in semantically plausible but physically unsafe behaviors. In this paper, we propose ",
  "authors": "Wenyuan Xie, Shaokai Wu, Yijin Zhou, Yanbiao Ji, Guodong Zhang, Bayram Bayramli et al.",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-30T16:25:47.000Z",
  "fetched_at": "2026-07-14T14:14:28.438Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/384",
  "original_url": "https://arxiv.org/abs/2606.31919v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}