LLM-BT: Performing Robotic Adaptive Tasks based on Large Language Models and Behavior Trees
arXiv:2404.05134 · doi:10.1109/ICRA57147.2024.10610183
Abstract
Large Language Models (LLMs) have been widely utilized to perform complex robotic tasks. However, handling external disturbances during tasks is still an open challenge. This paper proposes a novel method to achieve robotic adaptive tasks based on LLMs and Behavior Trees (BTs). It utilizes ChatGPT to reason the descriptive steps of tasks. In order to enable ChatGPT to understand the environment, semantic maps are constructed by an object recognition algorithm. Then, we design a Parser module based on Bidirectional Encoder Representations from Transformers (BERT) to parse these steps into initial BTs. Subsequently, a BTs Update algorithm is proposed to expand the initial BTs dynamically to control robots to perform adaptive tasks. Different from other LLM-based methods for complex robotic tasks, our method outputs variable BTs that can add and execute new actions according to environmental changes, which is robust to external disturbances. Our method is validated with simulation in different practical scenarios.
7 pages, 11figures, WILL PUBLISHED ON ICRA 2024
References in corpus (10)
- PDDL2.1: An Extension to PDDL for Expressing Temporal Planning Domains
- Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
- Behavior Trees in Robotics and AI: An Introduction
- PaLM-E: An Embodied Multimodal Language Model
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- Inner Monologue: Embodied Reasoning through Planning with Language Models
- Towards Blended Reactive Planning and Acting using Behavior Trees
- VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models
- On the Implementation of Behavior Trees in Robotics