A Hybrid Optimization Framework for Grasp Synthesis under Partial Observations
A hybrid grasp synthesis framework combining learning-based and analytical methods to generate robust grasps from partially observed point clouds.
The paper presents a novel combination of learning-based and analytical methods for grasp synthesis, which addresses the limitations of either strategy in isolation.
Before reading this…
Applications
- →Robotics
- →Computer vision
To understand this paper, make sure you know these concepts first:
- Machine learningfind papers →
- Geometric optimizationfind papers →
Abstract
More Like ThisWe propose a hybrid grasp synthesis framework that combines a learning-based Energy-Based Model (EBM) with an analytical Iterative Closest Point (ICP) method to generate robust grasps from partially observed point clouds. The learned energy function acts as a prior within a Stein Variational Gradient Descent (SVGD) framework, guiding iterative refinement of grasp configurations. Evaluated on 67 objects with 5,360 grasp attempts, our method achieves an average success rate of 60.9\%, outperforming AnyGrasp (31.1\%) and Grasp Pose Detection (48.4\%) and AS-ICP (56.6\%). These results highlight the strong generalization ability of our approach and demonstrate how combining data-driven learning with geometric optimization addresses the limitations of either strategy in isolation.