Acting from Belief, Looking When Needed: A Bayesian Spatial World Model for Navigation under Intermittent Perception
Acting from Belief, Looking When Needed: A Bayesian Spatial World Model for Navigation under Intermittent Perception
ALONE, a Bayesian spatial world model, enables robot navigation under intermittent perception by using an internal spatial belief and selectively acquiring observations. It achieves 98% and 97% closed-loop success in simulation and validates real-world performance with 10 successful indoor flight trials.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Environment
- SimulationOpen source S5
Reported numbers
successful trials
10 trials
Reported trials
decision rate
10
View original evidence
achieves 98% and 97% closed-loop success at a 10 Hz decision rate.
Open source S5
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
mera 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 interm
Open source S5
ittent depth observations, with all 10 trials successful.
Open source S6
Source：arXiv Robotics — research abstracts · arxiv.org