Driving · 2026-10-09

Acting from Belief, Looking When Needed: A Bayesian Spatial World Model for Navigation under Intermittent Perception

Feihong Yang, Xiang Long, Jincheng Yu, Jianfei Zhang, Guangjun Ge, Chao Wang, Yu Wang

AI-assisted summary based on the paper. Consult the linked source for methods and limitations. Benchmark numbers appear after editor verification.

TL;DR

ALONE is a Bayesian spatial world model for navigation under intermittent perception. It propagates a structured spatial belief between depth observations and requests a new observation only when a reliability map indicates insufficient support for action selection and the relevant region is expected to be visible. On drone navigation with intermittent single-camera depth, it reports 98%/97% closed-loop success at 10 Hz, with median depth requests at 0.9% and 1.3% of decision steps (successful trials), and all 10 real-world trials successful.

Why it matters

Robots often assume sensing stays focused on navigation, but other tasks can interrupt sensor access. ALONE addresses this by maintaining an internal spatial belief for action selection during perception gaps and using query-space reliability to decide when new observations are actually needed, aiming to reduce observation demand without sacrificing navigation performance.

Method

Maintains a structured categorical spatial belief: action-conditioned propagation (learned spatial completion) and observation-conditioned correction when depth is acquired.
Decodes the belief into (i) a spatial estimate for motion planning and (ii) a query-space reliability map (probability the estimate meets the planning accuracy criterion at each query location).
Observation policy requests depth only when reliability would materially hinder the selected action and when the responsible low-reliability region is expected to be visible; otherwise it continues acting from the propagated belief.

Abstract (from arXiv)

Robot navigation commonly uses wide-coverage, high-frequency sensing to reduce partial observability; this reliance becomes restrictive when another task temporarily redirects a shared sensor from navigation, interrupting navigation-relevant observations. We study navigation under intermittent perception: acting from an internal spatial belief and looking again only when execution needs a new observation, potentially freeing the shared sensor for other tasks between navigation observations. ALONE, a Bayesian spatial world model, propagates a structured spatial belief using executed actions and corrects it with selectively acquired observations; learned priors over common geometric structures infer unobserved structure from available observation history. It decodes the belief into a spatial estimate for the motion-planning module and predicts a reliability map expressing confidence in the estimate's accuracy. ALONE requests an observation only if insufficient reliability hinders navigation and new evidence should make relevant-region spatial information more reliable; otherwise, it continues acting from the propagated belief. We instantiate ALONE for drone navigation with intermittent single-camera depth images. Across two simulated scene families, it achieves 98% and 97% closed-loop success at a 10 Hz decision rate. Among successful trials, median fractions of decision steps requiring a new depth observation are only 0.9% and 1.3%, respectively, demonstrating high navigation success with substantially reduced observation demand. Real-world indoor flight experiments further validate navigation under intermittent depth observations, with all 10 trials successful.

Publication record

Bibliographic evidence describes where and when a record appeared. It does not validate scientific claims.

First public release: 2026-10-08 · Indexed by Pub-AI: 2026-10-09 UTC

preprint