HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Tianshuo, Chen, Guanyu, Chen, Yutian, Liang, Zhixuan, Liu, Yitian, Chen, Zanxin, Xu, Chunpu, Liang, Haotian, Pang, Jiangmiao, Mu, Yao, Luo, Ping
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911669011087360
author Yang, Tianshuo
Chen, Guanyu
Chen, Yutian
Liang, Zhixuan
Liu, Yitian
Chen, Zanxin
Xu, Chunpu
Liang, Haotian
Pang, Jiangmiao
Mu, Yao
Luo, Ping
author_facet Yang, Tianshuo
Chen, Guanyu
Chen, Yutian
Liang, Zhixuan
Liu, Yitian
Chen, Zanxin
Xu, Chunpu
Liang, Haotian
Pang, Jiangmiao
Mu, Yao
Luo, Ping
contents While end-to-end Vision-Language-Action (VLA) models offer a promising paradigm for robotic manipulation, fine-tuning them on narrow control data often compromises the profound reasoning capabilities inherited from their base Vision-Language Models (VLMs). To resolve this fundamental trade-off, we propose HiVLA, a visual-grounded-centric hierarchical framework that explicitly decouples high-level semantic planning from low-level motor control. In high-level part, a VLM planner first performs task decomposition and visual grounding to generate structured plans, comprising a subtask instruction and a precise target bounding box. Then, to translate this plan into physical actions, we introduce a flow-matching Diffusion Transformer (DiT) action expert in low-level part equipped with a novel cascaded cross-attention mechanism. This design sequentially fuses global context, high-resolution object-centric crops and skill semantics, enabling the DiT to focus purely on robust execution. Our decoupled architecture preserves the VLM's zero-shot reasoning while allowing independent improvement of both components. Extensive experiments in simulation and the real world demonstrate that HiVLA significantly outperforms state-of-the-art end-to-end baselines, particularly excelling in long-horizon skill composition and the fine-grained manipulation of small objects in cluttered scenes.
format Preprint
id arxiv_https___arxiv_org_abs_2604_14125
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System
Yang, Tianshuo
Chen, Guanyu
Chen, Yutian
Liang, Zhixuan
Liu, Yitian
Chen, Zanxin
Xu, Chunpu
Liang, Haotian
Pang, Jiangmiao
Mu, Yao
Luo, Ping
Computer Vision and Pattern Recognition
Artificial Intelligence
Robotics
While end-to-end Vision-Language-Action (VLA) models offer a promising paradigm for robotic manipulation, fine-tuning them on narrow control data often compromises the profound reasoning capabilities inherited from their base Vision-Language Models (VLMs). To resolve this fundamental trade-off, we propose HiVLA, a visual-grounded-centric hierarchical framework that explicitly decouples high-level semantic planning from low-level motor control. In high-level part, a VLM planner first performs task decomposition and visual grounding to generate structured plans, comprising a subtask instruction and a precise target bounding box. Then, to translate this plan into physical actions, we introduce a flow-matching Diffusion Transformer (DiT) action expert in low-level part equipped with a novel cascaded cross-attention mechanism. This design sequentially fuses global context, high-resolution object-centric crops and skill semantics, enabling the DiT to focus purely on robust execution. Our decoupled architecture preserves the VLM's zero-shot reasoning while allowing independent improvement of both components. Extensive experiments in simulation and the real world demonstrate that HiVLA significantly outperforms state-of-the-art end-to-end baselines, particularly excelling in long-horizon skill composition and the fine-grained manipulation of small objects in cluttered scenes.
title HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Robotics
url https://arxiv.org/abs/2604.14125