Safe Planner: Empowering Safety Awareness in Large Pre-Trained Models for Robot Task Planning

TL;DR

This paper introduces Safe Planner, a framework that enhances large pre-trained models with safety awareness for robot task planning, significantly improving safety and success rates in both simulated and real-world environments.

Contribution

The paper proposes a novel safety prediction module integrated with large pre-trained models, enabling safe and effective robot planning transferable from simulation to real-world tasks.

Findings

Achieves state-of-the-art task success rates.

Substantially improves safety during task execution.

Effective transfer of safety module from simulation to real robots.

Abstract

Robot task planning is an important problem for autonomous robots in long-horizon challenging tasks. As large pre-trained models have demonstrated superior planning ability, recent research investigates utilizing large models to achieve autonomous planning for robots in diverse tasks. However, since the large models are pre-trained with Internet data and lack the knowledge of real task scenes, large models as planners may make unsafe decisions that hurt the robots and the surrounding environments. To solve this challenge, we propose a novel Safe Planner framework, which empowers safety awareness in large pre-trained models to accomplish safe and executable planning. In this framework, we develop a safety prediction module to guide the high-level large model planner, and this safety module trained in a simulator can be effectively transferred to real-world tasks. The proposed Safe Planner framework is evaluated on both simulated environments and real robots. The experiment results demonstrate that Safe Planner not only achieves state-of-the-art task success rates, but also substantially improves safety during task execution. The experiment videos are shown in https://sites.google.com/view/safeplanner .