Planning with Learned Subgoals Selected by Temporal Information

TL;DR

This paper introduces a novel planning approach that integrates learned temporal estimators to select subgoals in dynamic environments, enabling robots to meet time-dependent constraints effectively.

Contribution

It proposes a generative model for decomposing complex planning tasks into subgoals and incorporates learned temporal information for subgoal selection, addressing a gap in existing spatial-only planning methods.

Findings

Successfully satisfies time-dependent constraints in experiments.

Enhances goal-oriented planning in dynamic environments.

Demonstrates improved planning efficiency with temporal estimators.

Abstract

Path planning in a changing environment is a challenging task in robotics, as moving objects impose time-dependent constraints. Recent planning methods primarily focus on the spatial aspects, lacking the capability to directly incorporate time constraints. In this paper, we propose a method that leverages a generative model to decompose a complex planning problem into small manageable ones by incrementally generating subgoals given the current planning context. Then, we take into account the temporal information and use learned time estimators based on different statistic distributions to examine and select the generated subgoal candidates. Experiments show that planning from the current robot state to the selected subgoal can satisfy the given time-dependent constraints while being goal-oriented.