SDA-PLANNER: State-Dependency Aware Adaptive Planner for Embodied Task Planning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shen, Zichao, Gao, Chen, Yuan, Jiaqi, Zhu, Tianchen, Fu, Xingcheng, Sun, Qingyun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908568967446528
author Shen, Zichao
Gao, Chen
Yuan, Jiaqi
Zhu, Tianchen
Fu, Xingcheng
Sun, Qingyun
author_facet Shen, Zichao
Gao, Chen
Yuan, Jiaqi
Zhu, Tianchen
Fu, Xingcheng
Sun, Qingyun
contents Embodied task planning requires agents to produce executable actions in a close-loop manner within the environment. With progressively improving capabilities of LLMs in task decomposition, planning, and generalization, current embodied task planning methods adopt LLM-based architecture.However, existing LLM-based planners remain limited in three aspects, i.e., fixed planning paradigms, lack of action sequence constraints, and error-agnostic. In this work, we propose SDA-PLANNER, enabling an adaptive planning paradigm, state-dependency aware and error-aware mechanisms for comprehensive embodied task planning. Specifically, SDA-PLANNER introduces a State-Dependency Graph to explicitly model action preconditions and effects, guiding the dynamic revision. To handle execution error, it employs an error-adaptive replanning strategy consisting of Error Backtrack and Diagnosis and Adaptive Action SubTree Generation, which locally reconstructs the affected portion of the plan based on the current environment state. Experiments demonstrate that SDA-PLANNER consistently outperforms baselines in success rate and goal completion, particularly under diverse error conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2509_26375
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SDA-PLANNER: State-Dependency Aware Adaptive Planner for Embodied Task Planning
Shen, Zichao
Gao, Chen
Yuan, Jiaqi
Zhu, Tianchen
Fu, Xingcheng
Sun, Qingyun
Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
Embodied task planning requires agents to produce executable actions in a close-loop manner within the environment. With progressively improving capabilities of LLMs in task decomposition, planning, and generalization, current embodied task planning methods adopt LLM-based architecture.However, existing LLM-based planners remain limited in three aspects, i.e., fixed planning paradigms, lack of action sequence constraints, and error-agnostic. In this work, we propose SDA-PLANNER, enabling an adaptive planning paradigm, state-dependency aware and error-aware mechanisms for comprehensive embodied task planning. Specifically, SDA-PLANNER introduces a State-Dependency Graph to explicitly model action preconditions and effects, guiding the dynamic revision. To handle execution error, it employs an error-adaptive replanning strategy consisting of Error Backtrack and Diagnosis and Adaptive Action SubTree Generation, which locally reconstructs the affected portion of the plan based on the current environment state. Experiments demonstrate that SDA-PLANNER consistently outperforms baselines in success rate and goal completion, particularly under diverse error conditions.
title SDA-PLANNER: State-Dependency Aware Adaptive Planner for Embodied Task Planning
topic Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.26375