Bayesian model enables drones to navigate with fewer observations
Acting from Belief, Looking When Needed: A Bayesian Spatial World Model for Navigation under Intermittent Perception
Robotics
Summary
Robots usually need constant sensor input to navigate safely, but that can be limiting when those sensors are needed for other tasks. The authors designed a method that lets a robot keep an internal map of its surroundings and only check the sensors when necessary. Their system uses past information and learned knowledge about common shapes to fill in gaps and decide when to look again. This approach was tested on drones in simulations and real indoor flights, showing high success but much fewer sensor checks.
What this means in practice
- •For drone navigation engineers: Design drone control systems that reduce sensor usage by acting on internal maps, improving multitasking and resource sharing.
- •For autonomous robot developers: Create robots that navigate effectively even when navigation sensors are temporarily unavailable, by relying on belief-based spatial reasoning.
Authors
Feihong Yang, Xiang Long, Jincheng Yu, Jianfei Zhang, Guangjun Ge, Chao Wang, Yu Wang
Abstract
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.