Onto-LLM-TAMP: Knowledge-oriented Task and Motion Planning using Large Language Models

Muhayy Ud Din

doi:10.1016/j.robot.2026.105404

Onto-LLM-TAMP: Knowledge-oriented Task and Motion Planning using Large Language Models

2026-03-05

0

OA

AI

DOI：10.1016/j.robot.2026.105404

Original

Save

View PDF

Abstract

En 中文

Performing complex manipulation tasks in dynamic environments requires efficient Task and Motion Planning (TAMP) approaches that combine high-level symbolic plans with low-level motion control. Advances in Large Language Models (LLMs), such as GPT-4, are transforming task planning by offering natural language as an intuitive and flexible way to describe tasks, generate symbolic plans, and reason. However, the effectiveness of LLM-based TAMP approaches is limited due to static and template-based prompting, which limits adaptability to dynamic environments and complex task contexts. To address these limitations, this work proposes a novel Onto-LLM-TAMP framework that employs knowledge-based reasoning to refine and expand user prompts with task-contextual reasoning and knowledge-based environment state descriptions. Integrating domain-specific knowledge into the prompt ensures semantically accurate and context-aware task plans. The proposed framework demonstrates its effectiveness by resolving semantic errors in symbolic plan generation, such as maintaining logical temporal goal ordering in scenarios involving hierarchical object placement. The proposed framework is validated through both simulation and real-world scenarios, demonstrating significant improvements over the baseline approach in terms of adaptability to dynamic environments and the generation of semantically correct task plans.

Keywords:

Task and Motion Planning

Large Language Models

Knowledge-based Reasoning

Dynamic Environments

Symbolic Planning

Onto-LLM-TAMP: Knowledge-oriented Task and Motion Planning using Large Language Models

Abstract

AI Summary

Journal

Organization