Goal2Skill: Long-Horizon Manipulation with Adaptive Planning and Reflection

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Zhen, Ning, Xinyu, Hu, Zhe, Xie, Xinxin, Li, Weize, Tang, Zhipeng, Wang, Chongyu, Yang, Zejun, Wang, Hanlin, Liu, Yitong, Pu, Zhongzhu
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908966731120640
author Liu, Zhen
Ning, Xinyu
Hu, Zhe
Xie, Xinxin
Li, Weize
Tang, Zhipeng
Wang, Chongyu
Yang, Zejun
Wang, Hanlin
Liu, Yitong
Pu, Zhongzhu
author_facet Liu, Zhen
Ning, Xinyu
Hu, Zhe
Xie, Xinxin
Li, Weize
Tang, Zhipeng
Wang, Chongyu
Yang, Zejun
Wang, Hanlin
Liu, Yitong
Pu, Zhongzhu
contents Recent vision-language-action (VLA) systems have demonstrated strong capabilities in embodied manipulation. However, most existing VLA policies rely on limited observation windows and end-to-end action prediction, which makes them brittle in long-horizon, memory-dependent tasks with partial observability, occlusions, and multi-stage dependencies. Such tasks require not only precise visuomotor control, but also persistent memory, adaptive task decomposition, and explicit recovery from execution failures. To address these limitations, we propose a dual-system framework for long-horizon embodied manipulation. Our framework explicitly separates high-level semantic reasoning from low-level motor execution. A high-level planner, implemented as a VLM-based agentic module, maintains structured task memory and performs goal decomposition, outcome verification, and error-driven correction. A low-level executor, instantiated as a VLA-based visuomotor controller, carries out each sub-task through diffusion-based action generation conditioned on geometry-preserving filtered observations. Together, the two systems form a closed loop between planning and execution, enabling memory-aware reasoning, adaptive replanning, and robust online recovery. Experiments on representative RMBench tasks show that the proposed framework substantially outperforms representative baselines, achieving a 32.4% average success rate compared with 9.8% for the strongest baseline. Ablation studies further confirm the importance of structured memory and closed-loop recovery for long-horizon manipulation.
format Preprint
id arxiv_https___arxiv_org_abs_2604_13942
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Goal2Skill: Long-Horizon Manipulation with Adaptive Planning and Reflection
Liu, Zhen
Ning, Xinyu
Hu, Zhe
Xie, Xinxin
Li, Weize
Tang, Zhipeng
Wang, Chongyu
Yang, Zejun
Wang, Hanlin
Liu, Yitong
Pu, Zhongzhu
Robotics
Recent vision-language-action (VLA) systems have demonstrated strong capabilities in embodied manipulation. However, most existing VLA policies rely on limited observation windows and end-to-end action prediction, which makes them brittle in long-horizon, memory-dependent tasks with partial observability, occlusions, and multi-stage dependencies. Such tasks require not only precise visuomotor control, but also persistent memory, adaptive task decomposition, and explicit recovery from execution failures. To address these limitations, we propose a dual-system framework for long-horizon embodied manipulation. Our framework explicitly separates high-level semantic reasoning from low-level motor execution. A high-level planner, implemented as a VLM-based agentic module, maintains structured task memory and performs goal decomposition, outcome verification, and error-driven correction. A low-level executor, instantiated as a VLA-based visuomotor controller, carries out each sub-task through diffusion-based action generation conditioned on geometry-preserving filtered observations. Together, the two systems form a closed loop between planning and execution, enabling memory-aware reasoning, adaptive replanning, and robust online recovery. Experiments on representative RMBench tasks show that the proposed framework substantially outperforms representative baselines, achieving a 32.4% average success rate compared with 9.8% for the strongest baseline. Ablation studies further confirm the importance of structured memory and closed-loop recovery for long-horizon manipulation.
title Goal2Skill: Long-Horizon Manipulation with Adaptive Planning and Reflection
topic Robotics
url https://arxiv.org/abs/2604.13942