aiqbench analysis
This paper introduces SPARROW, a belief-space planner utilizing Partially Observable Monte Carlo Planning (POMCP) to optimize robot navigation in dynamic environments with temporary obstacles. By integrating survival models and generative simulations of blockage events, the system effectively balances rerouting, waiting, and information gathering to reduce time-to-goal by up to 26% compared to prior methods. The approach demonstrates a concrete application of advanced probabilistic planning algorithms within robotics, focusing on adaptive decision-making under uncertainty.
SPARROW: Survival-POMCP for Adaptive Robot Routing, Observation, and Waiting
arXiv:2609.21008v1 Announce Type: new Abstract: Temporary obstacles that may block a robot's planned route create a sequential navigation problem: a robot must decide whether to wait for a blockage to clear, reroute, or acquire more information about the obstacle before acting. We formulate graph navigation among temporary obstacles as a partially observable semi-Markov decision process and introduce SPARROW, a belief-space planner built on Partially Observable Monte Carlo Planning (POMCP). SPARROW searches over traversal, observation, and finite-duration waiting actions while maintaining a particle belief over latent obstacle classes and clearance times. Class-conditioned survival models are learned online from both clearance observations and right-censored encounters where the robot reroutes before clearance is observed. A generative model simulates obstacle arrivals and clearances as each action unfolds, so the planner can account for blockages that may occur along alternative routes. We further introduce a value-of-learning criterion that trades the immediate cost of collecting labelled survival data against its expected reduction in future navigation regret. Across two simulation graphs and multiple obstacle-class settings, SPARROW reduces mean time-to-goal by 12-26% relative to OSCAR, a recent survival-based method for the same problem. On a physical mobile robot, SPARROW reduces mean time-to-goal by 20.5% relative to OSCAR while selectively observing, waiting, and rerouting as environment conditions change.
Abstract:Temporary obstacles that may block a robot's planned route create a sequential navigation problem: a robot must decide whether to wait for a blockage to clear, reroute, or acquire more information about the obstacle before acting. We formulate graph navigation among temporary obstacles as a partially observable semi-Markov decision process and introduce SPARROW, a belief-space planner built on Partially Observable Monte Carlo Planning (POMCP). SPARROW searches over traversal, observation, and finite-duration waiting actions while maintaining a particle belief over latent obstacle classes and clearance times. Class-conditioned survival models are learned online from both clearance observations and right-censored encounters where the robot reroutes before clearance is observed. A generative model simulates obstacle arrivals and clearances as each action unfolds, so the planner can account for blockages that may occur along alternative routes. We further introduce a value-of-learning criterion that trades the immediate cost of collecting labelled survival data against its expected reduction in future navigation regret. Across two simulation graphs and multiple obstacle-class settings, SPARROW reduces mean time-to-goal by 12-26% relative to OSCAR, a recent survival-based method for the same problem. On a physical mobile robot, SPARROW reduces mean time-to-goal by 20.5% relative to OSCAR while selectively observing, waiting, and rerouting as environment conditions change.
Robotics (cs.RO)
arXiv:2609.21008 [cs.RO]
(or arXiv:2609.21008v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2609.21008 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 297 words
Related coverage
Biological Superintelligence
LessWrong · Jul 30, 2026
Humanity’s Last Invention — Richard Socher of Recursive
Latent Space · Sep 14, 2026
[AINews] not much happened today
Latent Space · Sep 10, 2026
Model-Based Reinforcement Learning for Heterogeneous Multi-Robot Task Assignment Under Distribution Shifts
arXiv · Aug 25, 2026