DAGDiff: Guiding Dual-Arm Grasp Diffusion to Stable and Collision-Free Grasps
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918150850740224 |
|---|---|
| author | Karim, Md Faizal Vembar, Vignesh Patra, Keshab Singh, Gaurav Krishna, K Madhava |
| author_facet | Karim, Md Faizal Vembar, Vignesh Patra, Keshab Singh, Gaurav Krishna, K Madhava |
| contents | Reliable dual-arm grasping is essential for manipulating large and complex objects but remains a challenging problem due to stability, collision, and generalization requirements. Prior methods typically decompose the task into two independent grasp proposals, relying on region priors or heuristics that limit generalization and provide no principled guarantee of stability. We propose DAGDiff, an end-to-end framework that directly denoises to grasp pairs in the SE(3) x SE(3) space. Our key insight is that stability and collision can be enforced more effectively by guiding the diffusion process with classifier signals, rather than relying on explicit region detection or object priors. To this end, DAGDiff integrates geometry-, stability-, and collision-aware guidance terms that steer the generative process toward grasps that are physically valid and force-closure compliant. We comprehensively evaluate DAGDiff through analytical force-closure checks, collision analysis, and large-scale physics-based simulations, showing consistent improvements over previous work on these metrics. Finally, we demonstrate that our framework generates dual-arm grasps directly on real-world point clouds of previously unseen objects, which are executed on a heterogeneous dual-arm setup where two manipulators reliably grasp and lift them. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_21145 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DAGDiff: Guiding Dual-Arm Grasp Diffusion to Stable and Collision-Free Grasps Karim, Md Faizal Vembar, Vignesh Patra, Keshab Singh, Gaurav Krishna, K Madhava Robotics Reliable dual-arm grasping is essential for manipulating large and complex objects but remains a challenging problem due to stability, collision, and generalization requirements. Prior methods typically decompose the task into two independent grasp proposals, relying on region priors or heuristics that limit generalization and provide no principled guarantee of stability. We propose DAGDiff, an end-to-end framework that directly denoises to grasp pairs in the SE(3) x SE(3) space. Our key insight is that stability and collision can be enforced more effectively by guiding the diffusion process with classifier signals, rather than relying on explicit region detection or object priors. To this end, DAGDiff integrates geometry-, stability-, and collision-aware guidance terms that steer the generative process toward grasps that are physically valid and force-closure compliant. We comprehensively evaluate DAGDiff through analytical force-closure checks, collision analysis, and large-scale physics-based simulations, showing consistent improvements over previous work on these metrics. Finally, we demonstrate that our framework generates dual-arm grasps directly on real-world point clouds of previously unseen objects, which are executed on a heterogeneous dual-arm setup where two manipulators reliably grasp and lift them. |
| title | DAGDiff: Guiding Dual-Arm Grasp Diffusion to Stable and Collision-Free Grasps |
| topic | Robotics |
| url | https://arxiv.org/abs/2509.21145 |