# Grasp-TAGS：评论家蒸馏实现任务感知抓取，重排成功率达89.84%

> 原文链接：https://robotics.hellobike.com/papers/2026-11-09-2611-09864-21d22243
> 频道：papers | 更新日期：2026-11-09 | 标签：auto, arxiv
> 核心摘要：针对移动操作大物体重排难题，提出Grasp-TAGS框架。通过PPO策略训练并蒸馏Critic网络，仅凭抓取构型与目标信息预测下游效用。实验显示平均成功率达89.84%，较最优固定抓取策略提升9.97个百分点，显著降低末端姿态误差。

# Grasp-TAGS：评论家蒸馏实现任务感知抓取，重排成功率达89.84%

::: v-pre
> 本文由 AI 根据公开内容整理，可能有误，请以原文为准：[Grasp-TAGS: Task-Aware Grasp Selection via Critic Distillation for Prehensile Loco-Manipulation](https://arxiv.org/abs/2611.09864)（arXiv 2611.09864）

## 核心内容

针对服务机器人与仓储自动化中大物体长程重排任务，现有方法受限于动力学模型精度或固定初始抓取假设。Grasp-TAGS框架提出任务感知抓取选择机制，解决了几何稳定抓取在下游操作中性能差异大的问题。实验表明该方法平均成功率达89.84%，相比表现最佳的单固定抓取策略（79.87%）提升9.97个百分点，并有效降低了所有测试对象的最终朝向误差。

技术上采用统一PPO强化学习策略覆盖多种初始抓取构型，将习得的Critic蒸馏为轻量级抓取效用网络。推理阶段无需物理接触，仅依据候选抓取构型与目标信息即可排序并选择最高预期效用的抓取点供下游策略执行。该架构解耦了抓取规划与运动控制，避免了传统Model-based方法对精确环境交互动力学模型的依赖，提升了系统在复杂交互场景下的鲁棒性。

## 关键看点

- **核心指标**：大物体重排平均成功率89.84%，较最优固定抓取基线提升9.97%，且降低末端朝向误差
- **算法架构**：基于PPO训练统一策略，利用Critic Distillation生成轻量级抓取效用网络进行预接触决策
- **输入约束**：推理仅需候选抓取构型与目标条件信息，摆脱对精确物体-环境交互动力学模型的依赖
- **任务场景**：面向移动操作长程大物体重排，解决几何稳定但操作效用差异大的抓取选择难题

## 工程与产业观察

该工作验证了在具身操作中引入“抓取效用”评估的价值，将抓取从纯几何稳定性判断升级为任务导向的端到端优化。对于移动操作机器人研发，提示应重视预接触阶段的策略耦合设计；Critic蒸馏范式为在算力受限的端侧部署高质量抓取决策提供了轻量化工程路径，有助于提升非结构化环境下的作业成功率。

## 英文摘要 (Abstract)

Loco-manipulation, which requires mobile manipulators to coordinate locomotion and manipulation over long horizons, is a key capability for large-object rearrangement in applications such as service robotics and warehouse automation. Despite recent progress, reliably executing these tasks remains challenging because performance depends on complex robot-object and object-environment interaction dynamics. Existing approaches address this challenge either through model-based methods, which often require accurate dynamics models, or through learning-based methods, which reduce this requirement but typically assume a fixed or predefined initial grasp. However, different geometrically stable grasps can lead to substantially different downstream manipulation performance. Therefore, we propose Grasp-TAGS, a task-aware grasp selection framework for goal-conditioned large-object rearrangement. We train a unified PPO-based reinforcement learning policy across multiple initial grasp configurations and distill the learned critic into a lightweight grasp utility network that ranks candidate grasps using only the candidate grasp configuration and goal information. At inference time, we select the grasp with the highest predicted downstream utility for the downstream policy to complete the task, before even making a contact. Experiments demonstrate that Grasp-TAGS improves rearrangement success over both fixed single-grasp policies and random grasp selection, achieving an average success rate of 89.84% compared with 79.87% for the best-performing single-grasp policies, an improvement of 9.97 percentage points. Grasp-TAGS also reduces final orientation errors across all evaluated objects. For more qualitative results, refer to the supplementary webpage: https://rpm-lab-umn.github.io/Grasp-TAGS-web-page/

作者：Xun Tu, Minghao Zou, Karthik Desingh
:::

## 原始参考来源 (Sources)

- [arXiv 2611.09864：Grasp-TAGS: Task-Aware Grasp Selection via Critic Distillation for Prehensile Loco-Manipulation](https://arxiv.org/abs/2611.09864)