Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhou, Weijie, Tao, Manli, Zhao, Chaoyang, Dong, Honghui, Tang, Ming, Wang, Jinqiao
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2503.08508
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918168500371456
author Zhou, Weijie
Tao, Manli
Zhao, Chaoyang
Dong, Honghui
Tang, Ming
Wang, Jinqiao
author_facet Zhou, Weijie
Tao, Manli
Zhao, Chaoyang
Dong, Honghui
Tang, Ming
Wang, Jinqiao
contents In recent years, lightweight large language models (LLMs) have garnered significant attention in the robotics field due to their low computational resource requirements and suitability for edge deployment. However, in task planning -- particularly for complex tasks that involve dynamic semantic logic reasoning -- lightweight LLMs have underperformed. To address this limitation, we propose a novel task planner, LightPlanner, which enhances the performance of lightweight LLMs in complex task planning by fully leveraging their reasoning capabilities. Unlike conventional planners that use fixed skill templates, LightPlanner controls robot actions via parameterized function calls, dynamically generating parameter values. This approach allows for fine-grained skill control and improves task planning success rates in complex scenarios. Furthermore, we introduce hierarchical deep reasoning. Before generating each action decision step, LightPlanner thoroughly considers three levels: action execution (feedback verification), semantic parsing (goal consistency verification), and parameter generation (parameter validity verification). This ensures the correctness of subsequent action controls. Additionally, we incorporate a memory module to store historical actions, thereby reducing context length and enhancing planning efficiency for long-term tasks. We train the LightPlanner-1.5B model on our LightPlan-40k dataset, which comprises 40,000 action controls across tasks with 2 to 13 action steps. Experiments demonstrate that our model achieves the highest task success rate despite having the smallest number of parameters. In tasks involving spatial semantic reasoning, the success rate exceeds that of ReAct by 14.9 percent. Moreover, we demonstrate LightPlanner's potential to operate on edge devices.
format Preprint
id arxiv_https___arxiv_org_abs_2503_08508
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LightPlanner: Unleashing the Reasoning Capabilities of Lightweight Large Language Models in Task Planning
Zhou, Weijie
Tao, Manli
Zhao, Chaoyang
Dong, Honghui
Tang, Ming
Wang, Jinqiao
Robotics
In recent years, lightweight large language models (LLMs) have garnered significant attention in the robotics field due to their low computational resource requirements and suitability for edge deployment. However, in task planning -- particularly for complex tasks that involve dynamic semantic logic reasoning -- lightweight LLMs have underperformed. To address this limitation, we propose a novel task planner, LightPlanner, which enhances the performance of lightweight LLMs in complex task planning by fully leveraging their reasoning capabilities. Unlike conventional planners that use fixed skill templates, LightPlanner controls robot actions via parameterized function calls, dynamically generating parameter values. This approach allows for fine-grained skill control and improves task planning success rates in complex scenarios. Furthermore, we introduce hierarchical deep reasoning. Before generating each action decision step, LightPlanner thoroughly considers three levels: action execution (feedback verification), semantic parsing (goal consistency verification), and parameter generation (parameter validity verification). This ensures the correctness of subsequent action controls. Additionally, we incorporate a memory module to store historical actions, thereby reducing context length and enhancing planning efficiency for long-term tasks. We train the LightPlanner-1.5B model on our LightPlan-40k dataset, which comprises 40,000 action controls across tasks with 2 to 13 action steps. Experiments demonstrate that our model achieves the highest task success rate despite having the smallest number of parameters. In tasks involving spatial semantic reasoning, the success rate exceeds that of ReAct by 14.9 percent. Moreover, we demonstrate LightPlanner's potential to operate on edge devices.
title LightPlanner: Unleashing the Reasoning Capabilities of Lightweight Large Language Models in Task Planning
topic Robotics
url https://arxiv.org/abs/2503.08508