Spatial RoboGrasp: Generalized Robotic Grasping Control Policy
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:P4PRB4OSrecord.jsonopen to challenge →
read the original abstract
Achieving generalizable and precise robotic manipulation across diverse environments remains a critical challenge, largely due to limitations in spatial perception. While prior imitation-learning approaches have made progress, their reliance on raw RGB inputs and handcrafted features often leads to overfitting and poor 3D reasoning under varied lighting, occlusion, and object conditions. In this paper, we propose a unified framework that couples robust multimodal perception with reliable grasp prediction. Our architecture fuses domain-randomized augmentation, monocular depth estimation, and a depth-aware 6-DoF Grasp Prompt into a single spatial representation for downstream action planning. Conditioned on this encoding and a high-level task prompt, our diffusion-based policy yields precise action sequences, achieving up to 40% improvement in grasp success and 45% higher task success rates under environmental variation. These results demonstrate that spatially grounded perception, paired with diffusion-based imitation learning, offers a scalable and robust solution for general-purpose robotic grasping.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
Pose-Agnostic Robotic Functional Grasping via Observation-Action Canonicalization
AnyMug trains a single closed-loop visuomotor policy in simulation using observation-action canonicalization and deploys it zero-shot on a real robot for functional mug-handle grasping across poses.
-
GeoSem-WAM: Geometry- and Semantic-Aware World Action Models
GeoSem-WAM adds geometric and semantic auxiliary prediction tasks to World Action Models during training to improve latent representations and action prediction accuracy while keeping inference efficient by avoiding e...
-
AttenA+: Rectifying Action Inequality in Robotic Foundation Models
AttenA+ applies velocity-driven action attention to reweight training objectives toward kinematically critical low-velocity segments, yielding small benchmark gains on Libero and RoboTwin without added parameters.
-
AttenA+: Rectifying Action Inequality in Robotic Foundation Models
AttenA+ reweights action training objectives in VLA and WAM models via inverse velocity attention to prioritize kinematically critical segments, yielding small benchmark gains.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.