arXiv 2504.196832026-08-03cs.RO

GPA-RAM：用于空间任务学习的抓取预训练增强型机器人注意力Mamba

GPA-RAM: Grasp-Pretraining Augmented Robotic Attention Mamba for Spatial Task Learning

State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School（国家一般人工智能重点实验室，北京大学深圳研究生院）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究所，中国科学院）；State Key Laboratory of Internet of Things for Smart City, University of Macau（智慧城市物联网重点实验室，澳门大学）

Juyi Sheng, Yangjun Liu, Sheng Xu, Zhixin Yang, Tiantian Xu, Mengyuan Liu

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

该研究提出GPA-RAM框架，通过GPA增强模仿策略并开发RAM实现高效计算，在多机器人平台的空间操纵任务中显著提升成功率，兼顾精度与实时性。

摘要：

精细机器人操纵常因初始抓取不准确导致误差传播，需要复杂的位姿校正。我们提出抓取预训练增强（GPA），将任务演示中的抓取先验融入模仿策略，无需额外抓取位姿数据或标注。将GPA加入RVT2后，RLBench上的平均成功率从79.3%提升至84.2%；加入ACT后，ALOHA立方体搬运和双臂插入任务的成功率分别从86%和16%提升至98%和38%。为抵消增加的计算成本，我们开发了用于实时部署的机器人注意力Mamba（RAM），RAM结合基于注意力的空间特征提取与状态空间建模，可高效捕捉长程依赖。最终的GPA-RAM框架支持离散关键帧预测与连续动作生成，我们在包括物理UR5和ARX R5系统在内的四个平台上对其进行评估，GPA-RAM在RLBench上的平均成功率达87.5%，较RVT2和ARP+分别提升8.2和2.6个百分点；在ALOHA上，其立方体搬运成功率达98%、双臂插入达56%，较ACT分别提升12和40个百分点，运行帧率约71帧每秒。这些结果表明GPA-RAM兼具精确操纵与高效实时机器人执行能力，代码可在该网址获取。

英文摘要：

Fine-grained robotic manipulation often fails when inaccurate initial grasps propagate errors and necessitate complex pose correction. We propose Grasp-Pretraining Augmentation (GPA), which incorporates grasp priors from task demonstrations into imitation policies without additional grasp-pose data or annotation. When added to RVT2, GPA raises the average success rate on RLBench from 79.3% to 84.2%. When added to ACT, it raises success on ALOHA cube transfer and bimanual insertion from 86% and 16% to 98% and 38%, respectively. To offset added computational costs, we develop Robotic Attention Mamba (RAM) for real-time deployment. RAM combines attention-based spatial feature extraction with state-space modeling to capture long-range dependencies efficiently. The resulting GPA-RAM framework supports discrete keyframe prediction and continuous action generation. We evaluate it on four platforms, including physical UR5 and ARX R5 systems. GPA-RAM achieves an average success rate of 87.5% on RLBench, outperforming RVT2 and ARP+ by 8.2 and 2.6 percentage points, respectively. On ALOHA, it achieves 98% success in cube transfer and 56% in bimanual insertion, improvements of 12 and 40 percentage points over ACT, while operating at approximately 71 frames per second. These results demonstrate that GPA-RAM combines precise manipulation with efficient real-time robotic execution. Code is available at https://gpa-ram.github.io/.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。