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

Key points

• 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.1
• 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.1
• We instantiate ALONE for drone navigation with intermittent single-camera depth images.1
• Real-world indoor flight experiments further validate navigation under intermittent depth observations, with all 10 trials successful.1

Sources (1)

• [1]Acting from Belief, Looking When Needed: A Bayesian Spatial World Model for Navigation under Intermittent Perception
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 09:42 AM

  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.

  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.

Extractive summary: sentences quoted from the sources.