analiza aiqbench
This paper introduces GPA-RAM, a framework that enhances robotic manipulation by integrating grasp priors into imitation policies while utilizing state-space modeling (Mamba) for efficient real-time inference on physical hardware. The approach significantly boosts success rates in fine-grained tasks like bimanual insertion without requiring additional pose annotations or increasing computational overhead beyond acceptable limits. This advancement represents a meaningful step toward deploying robust, data-efficient AI agents capable of precise physical interaction in unstructured environments.
GPA-RAM: Grasp-Pretraining Augmented Robotic Attention Mamba for Spatial Task Learning
arXiv:2504.19683v4 Announce Type: replace Abstract: 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/.
Abstract: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 this https URL.
Robotics (cs.RO)
arXiv:2504.19683 [cs.RO]
(or arXiv:2504.19683v4 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2504.19683 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 292 cuvinte
Subiecte conexe
Robo-Harness K1: Harnessing Robot-Use Agents via Perception Augmentation
arXiv · 25 sept. 2026
EATR-Stereo: Embodiment-Aware Routing of Paired Stereo Evidence for Humanoid Vision-Language-Action Control
arXiv · 19 aug. 2026
[AINews] Hot Chips: OpenAI’s Jalapeño, Cerebras CS-5, Groq 3 LPX, Apple M6
Latent Space · 27 aug. 2026
Build a Physical AI model factory with NVIDIA Cosmos 3 on SageMaker HyperPod
AWS · 4 sept. 2026