Learning Spatiotemporal Decision Priors for Efficient Path Planning under Partial Observability

2026-07-24

AI Summary

In partially observable environments, conventional planners often exhibit redundant search and myopic behavior due to their inability to leverage transferable decision knowledge from historical trajectories. This work proposes ImiPath, a novel framework that explicitly incorporates reusable spatiotemporal decision priors to bias the search direction based on past experience. ImiPath employs localized spatiotemporal observation representations, a SpatioTemporal-Attention Policy Network (STAPNet), and a prior-guided heterogeneous planning ensemble to effectively integrate such priors into the planning process. The approach significantly reduces redundant node expansions while preserving path quality, thereby enhancing search efficiency. Empirical validation on a magnetic microrobot platform demonstrates its practical deployability and real-world effectiveness.

Abstract

Path planning under partial observability remains challenging because an agent must make long-horizon navigation decisions from only locally bounded observations. Nevertheless, historical trajectories contain reusable experience-guided directional preferences. Classical planners, however, typically solve each instance from scratch and lack an explicit mechanism to exploit such transferable decision knowledge, often leading to redundant node expansions and locally myopic search behaviors. Motivated by this limitation, this paper proposes ImiPath, a prior-guided learning framework that distills reusable spatiotemporal decision priors from demonstration trajectories and uses them as experience-informed directional guidance to bias planners toward reliable and promising search directions under partial observability. Specifically, ImiPath first constructs a local spatiotemporal observation representation, which encodes the spatial information of the local environment and the temporal information of historical trajectories. The SpatioTemporal-Attention Policy Network (STAPNet) then transforms this representation into dicision priors. These priors are further incorporated into heterogeneous planners as directional guidance, biasing the search toward locally promising regions. Extensive experiments demonstrate that ImiPath achieves competitive path quality and improves search efficiency by reducing redundant node expansions under local observability. Additional physical experiments on a magnetic microrobot platform further validate the adaptability and practical deployment potential of the proposed framework.

Problem

• partial observability
• path planning
• decision priors
• spatiotemporal representation
• search efficiency

Innovation

• spatiotemporal decision priors
• partial observability
• prior-guided planning
• STAPNet
• efficient path planning