Automatic Robot Task Planning by Integrating Large Language Model with Genetic Programming

2025-02-11

AI Summary

Robot task planning traditionally relies heavily on domain experts, and handcrafted behavior trees (BTs) suffer from low design efficiency and poor generalizability. Method: This paper proposes an end-to-end framework synergizing large language models (LLMs) and genetic programming (GP) to automatically synthesize executable BT policies directly from natural language instructions. LLMs perform semantic parsing and generate initial BT structures, while GP optimizes BT topology and parameters under executability constraints to jointly ensure semantic fidelity and control reliability. The framework requires no manually defined domain knowledge or BT templates. Contribution/Results: Experiments demonstrate a 27.4% improvement in planning accuracy across diverse simulated robot tasks—including UAVs, mobile robots, and autonomous driving scenarios—along with enhanced cross-task generalization, validating the framework’s broad applicability and reduced deployment barrier.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Accurate task planning is critical for controlling autonomous systems, such as robots, drones, and self-driving vehicles. Behavior Trees (BTs) are considered one of the most prominent control-policy-defining frameworks in task planning, due to their modularity, flexibility, and reusability. Generating reliable and accurate BT-based control policies for robotic systems remains challenging and often requires domain expertise. In this paper, we present the LLM-GP-BT technique that leverages the Large Language Model (LLM) and Genetic Programming (GP) to automate the generation and configuration of BTs. The LLM-GP-BT technique processes robot task commands expressed in human natural language and converts them into accurate and reliable BT-based task plans in a computationally efficient and user-friendly manner. The proposed technique is systematically developed and validated through simulation experiments, demonstrating its potential to streamline task planning for autonomous systems.

Problem

• Automate robot task planning
• Integrate LLM with Genetic Programming
• Generate accurate Behavior Trees

Innovation

• Large Language Model
• Genetic Programming
• Behavior Trees