用抓取先验提升机器人操作成功率，实现实时高效精准控制。
GPA-RAM: Grasp-Pretraining Augmented Robotic Attention Mamba for Spatial Task Learning
- 通过抓取预训练增强模仿学习，无需额外标注数据
- 在RLBench上成功率达87.5%，在ALOHA上抓取任务达98%
- 适合需要高精度与实时性的工业机器人应用场景
精细的机器人操作常因初始抓取不准导致误差传播，需复杂姿态修正。本文提出抓取预训练增强（GPA），将任务示范中的抓取先验融入模仿策略，无需额外抓取数据或标注。将其加入RVT2后，RLBench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成功率分别从86%、16%提升至98%、38%。为缓解计算开销，设计了机器人注意力马尔可夫模型（RAM），结合注意力机制与状态空间建模，高效捕捉长程依赖。GPA-RAM支持离散关键帧预测与连续动作生成。在四个平台（含物理UR5与ARX R5）验证，其在RLBench上平均成功率达87.5%，优于RVT2和ARP+ 8.2和2.6个百分点；在ALOHA上，立方体搬运成功率达98%，双臂插入达56%，较ACT提升12和40个百分点，运行速度约71帧/秒。结果表明，GPA-RAM实现了精确操作与高效实时执行的统一。代码已公开：https://gpa-ram.github.io/
原文摘要 · Abstract (English)
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/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。