STEP Planner: Constructing cross-hierarchical subgoal tree as an embodied long-horizon task planner

TL;DR

The STEP framework enhances long-horizon robot task planning by constructing a hierarchical subgoal tree using LLMs and real-time feedback, significantly improving success rates over existing methods.

Contribution

This paper introduces a novel hierarchical subgoal tree construction method combining LLM-based decomposition and real-time termination feedback for embodied tasks.

Findings

Achieves up to 34% success in VirtualHome benchmark.

Attains 25% success rate on real robots.

Outperforms state-of-the-art methods in long-horizon tasks.

Abstract

The ability to perform reliable long-horizon task planning is crucial for deploying robots in real-world environments. However, directly employing Large Language Models (LLMs) as action sequence generators often results in low success rates due to their limited reasoning ability for long-horizon embodied tasks. In the STEP framework, we construct a subgoal tree through a pair of closed-loop models: a subgoal decomposition model and a leaf node termination model. Within this framework, we develop a hierarchical tree structure that spans from coarse to fine resolutions. The subgoal decomposition model leverages a foundation LLM to break down complex goals into manageable subgoals, thereby spanning the subgoal tree. The leaf node termination model provides real-time feedback based on environmental states, determining when to terminate the tree spanning and ensuring each leaf node can be directly converted into a primitive action. Experiments conducted in both the VirtualHome WAH-NL benchmark and on real robots demonstrate that STEP achieves long-horizon embodied task completion with success rates up to 34% (WAH-NL) and 25% (real robot) outperforming SOTA methods.