# 前沿 VLM 能否作为依赖记忆操作的机器人策略？

> 原文链接：https://robotics.hellobike.com/papers/2026-10-12-2610-17350
> 频道：papers | 更新日期：2026-10-12 | 标签：arxiv, cs.RO
> 核心摘要：使用冻结的 GPT-6-Astra 直接作为策略，在 RoboMME 16项依赖记忆操作任务800集上验证，成功率92.1%。

# 前沿 VLM 能否作为依赖记忆操作的机器人策略？

::: v-pre
> 原文链接：[Can a Frontier VLM Serve as a Robot Policy for Memory-Dependent Manipulation?](https://arxiv.org/abs/2610.17350)（arXiv 2610.17350 · 发布日期：2026-10-12）

**Can a Frontier VLM Serve as a Robot Policy for Memory-Dependent Manipulation?**

使用冻结的 GPT-6-Astra 直接作为策略，在 RoboMME 16项依赖记忆操作任务800集上验证，成功率92.1%。

## 核心要点

- 问题关注通用 VLM 能否接管长时程规划、记忆与末端控制的常规划分。
- 方法将整段 episode 保留在上下文中，输出末端执行器路点和夹爪命令，无 RoboMME 专项训练。
- 800个测试 episode 成功率92.1%，超过人类90.5%、榜首60.8%和分层系统79.1%。
- 63次失败集中在两个任务，多为过早完成或按钮按压时机、意外按压错误；项目、代码等已公开。

**验证范围与局限**：验证范围为 RoboMME 基准16项依赖记忆操作任务的800个测试 episode。

## 英文摘要 (Abstract)

We use a frozen frontier vision-language model, GPT-6-Astra, directly as the robot policy on RoboMME, a benchmark of 16 memory-dependent manipulation tasks spanning temporal, spatial, object, and procedural memory. The model keeps the whole episode in context and outputs every end-effector waypoint and gripper command, with no RoboMME-specific training. On the 800 test episodes it succeeds in 92.1%, above the previously reported human score of 90.5%, which was obtained with an oracle skill interface, and far ahead of the best leaderboard entry (60.8%) and of a hierarchical system that pairs the same model with a RoboMME-trained policy (79.1%). It matches or exceeds the human score on 13 of the 16 tasks. Its 63 failures concentrate in two tasks and are mostly premature completions and mistimed or unintended button presses. These results blur the usual division between long-horizon planning, memory and end-effector control, and raise the question of how much of this stack a single general-purpose model can take over in embodied systems. Project website: https://embodied-astra.github.io. Code, prompts and all episode logs: https://github.com/jackbjed/embodied-astra-robomme.

作者：Jack B. Jedlicki, Amish Sethi, Heng Yang
:::

## 原始参考来源 (Sources)

- [arXiv 2610.17350：Can a Frontier VLM Serve as a Robot Policy for Memory-Dependent Manipulation?](https://arxiv.org/abs/2610.17350)