cs.RONov 18, 2026

Worth Another Look:Constrained World-Model Planning for Visual Inspection

Authors: Ziyue Kang, Zixi Qi, Yuchen Dai, Nana Lv, Xirong Cheng, Liang Liu, Ying Li, Haoyan Wei, 

Organizations: Shaanxi University of Science and Technology, Xi’an, Shaanxi, China

Abstract

Visual inspection in field robotics and environmental monitoring must localize multiple targets under strict compute and sensing caps. Exhaustive sweeps waste calls on absent classes, while myopic and search-free policies stumble over heterogeneous tariff cliffs or discard viewport edits whose value emerges only after re-querying. We formulate inspection over frozen detectors as neuro-symbolic observation planning under partial observability, decoupling a compact recurrent world model (WM) from exact symbolic feasibility and tariff rules. Receding-horizon beam search with online replanning jointly schedules class queries, crops, enhancements, and termination (stop), paired with slack-aware shadow pricing and legal fallback at larger budgets. Across eight terrestrial, optical, and sonar benchmarks, multi-step lookahead outperforms static schedules and search-free offline RL under tight budgets -- gaining up to 28.4 AP percentage points over static priority on RUOD and 15.1 on ARIS -- while dynamic pricing lifts large-budget performance on all eight domains at 11 ms planning cost. Ultimately, pairing lightweight learned dynamics with exact symbolic constraints turns frozen detectors into adaptive, budget-aware inspection agents without retraining.

Figures & tables

Explore similar work

CardsList
  1. How Much Planning Is Enough? Reducing Search and Computation in World-Model Planning

    Oct 6, 2026Changbai Li, Sirui Li, Yichen Yang +4World Model-Based PlanningEfficient Inference for World Action Models

  2. Scope-WM: Scoped Computation for Efficient Visual World Models

    Sep 27, 2026Chunzheng Li, Zesheng Jia, Hongda Zhang +4World Models for RoboticsWorld Models

  3. Write Once, Plan Many: Building Reusable Visual Planning Systems from One Scene

    Oct 13, 2026Ruixiao Yang, Yilun Hao, Mingxin Yu +2Program SynthesisModel-Based Planning