# ObjDream：用对象级理解和未来状态预测引导 Vision-Language-Action 模型

> 原文链接：https://robotics.hellobike.com/papers/2026-10-14-2610-20223
> 频道：papers | 更新日期：2026-10-14 | 标签：arxiv, cs.RO
> 核心摘要：ObjDream通过对象级表征与动作条件未来状态预测指导VLA，并在多个基准和真实机器人中验证泛化。

# ObjDream：用对象级理解和未来状态预测引导 Vision-Language-Action 模型

::: v-pre
> 原文链接：[ObjDream: Guiding Vision-Language-Action Models with Object-Level Understanding and Future State Prediction](https://arxiv.org/abs/2610.20223)（arXiv 2610.20223 · 发布日期：2026-10-14）

**ObjDream: Guiding Vision-Language-Action Models with Object-Level Understanding and Future State Prediction**

ObjDream通过对象级表征与动作条件未来状态预测指导VLA，并在多个基准和真实机器人中验证泛化。

## 核心要点

- 现有VLA多沿用图像级视觉表征，缺少操纵所需的细粒度对象理解。
- ObjDream以时空对象编码器形成时间对象槽，分离表示持久身份与动态状态。
- 将结构化对象表征插入VLM token序列，并用身份引导路由调制注意力。
- 训练中预测动作条件的未来对象状态；实验显示提升分布偏移与场景扰动下泛化。

**验证范围与局限**：验证范围为 LIBERO、LIBERO-Plus、RoboTwin 2.0 和真实机器人中的新对象布局与背景变化。

## 英文摘要 (Abstract)

Vision-language-action (VLA) models have emerged as a powerful paradigm for robotic manipulation, enabling robots to generate actions from visual observations and language instructions. However, most existing VLA models still operate on image-level visual representations inherited from pretrained vision-language backbones, while lacking fine-grained object understanding for manipulation. As a result, their robustness can degrade under out-of-distribution object layouts, clutter, and background variations. To address these limitations, we introduce ObjDream, an object-centric VLA framework centered on object-level understanding and future object state prediction. ObjDream uses a spatio-temporal object encoder to organize visual observations into temporal object slots, where persistent object identity and dynamic object state are represented through separate channels. These structured object representations are inserted into the token sequence of the vision-language model (VLM), where identity-guided routing modulates VLM attention to the corresponding object tokens. In addition, an action-conditioned object dynamics module predicts compact future object states relevant to manipulation during training, explicitly supervising object state evolution under robot actions without requiring future prediction at inference. Experiments on LIBERO, LIBERO-Plus, and RoboTwin 2.0 show that ObjDream improves generalization under diverse distribution shifts and scene perturbations. Real-world robot experiments further demonstrate that ObjDream transfers to physical manipulation settings with novel object arrangements and background changes.

作者：Huailiang Ma, Yuxuan Li, Ziyi Zhao, Xinkai Wang, Mingyu Li, Xinyu Guo, Lifeng Zhu, Aiguo Song, Cewu Lu, Jianhua Sun
:::

## 原始参考来源 (Sources)

- [arXiv 2610.20223：ObjDream: Guiding Vision-Language-Action Models with Object-Level Understanding and Future State Prediction](https://arxiv.org/abs/2610.20223)