Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.16767 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918163790168064 |
|---|---|
| author | Li, Jia Zhao, Guoxiang |
| author_facet | Li, Jia Zhao, Guoxiang |
| contents | Translating natural language instructions into executable motion plans is a fundamental challenge in robotics. Traditional approaches are typically constrained by their reliance on domain-specific expertise to customize planners, and often struggle with spatio-temporal couplings that usually lead to infeasible motions or discrepancies between task planning and motion execution. Despite the proficiency of Large Language Models (LLMs) in high-level semantic reasoning, hallucination could result in infeasible motion plans. In this paper, we introduce the T3 Planner, an LLM-enabled robotic motion planning framework that self-corrects it output with formal methods. The framework decomposes spatio-temporal task constraints via three cascaded modules, each of which stimulates an LLM to generate candidate trajectory sequences and examines their feasibility via a Signal Temporal Logic (STL) verifier until one that satisfies complex spatial, temporal, and logical constraints is found.Experiments across different scenarios show that T3 Planner significantly outperforms the baselines. The required reasoning can be distilled into a lightweight Qwen3-4B model that enables efficient deployment. All supplementary materials are accessible at https://github.com/leeejia/T3_Planner. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_16767 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | T3 Planner: A Self-Correcting LLM Framework for Robotic Motion Planning with Temporal Logic Li, Jia Zhao, Guoxiang Robotics Translating natural language instructions into executable motion plans is a fundamental challenge in robotics. Traditional approaches are typically constrained by their reliance on domain-specific expertise to customize planners, and often struggle with spatio-temporal couplings that usually lead to infeasible motions or discrepancies between task planning and motion execution. Despite the proficiency of Large Language Models (LLMs) in high-level semantic reasoning, hallucination could result in infeasible motion plans. In this paper, we introduce the T3 Planner, an LLM-enabled robotic motion planning framework that self-corrects it output with formal methods. The framework decomposes spatio-temporal task constraints via three cascaded modules, each of which stimulates an LLM to generate candidate trajectory sequences and examines their feasibility via a Signal Temporal Logic (STL) verifier until one that satisfies complex spatial, temporal, and logical constraints is found.Experiments across different scenarios show that T3 Planner significantly outperforms the baselines. The required reasoning can be distilled into a lightweight Qwen3-4B model that enables efficient deployment. All supplementary materials are accessible at https://github.com/leeejia/T3_Planner. |
| title | T3 Planner: A Self-Correcting LLM Framework for Robotic Motion Planning with Temporal Logic |
| topic | Robotics |
| url | https://arxiv.org/abs/2510.16767 |