A Hybrid Optimization Framework for Grasp Synthesis under Partial Observations
For robotic grasping from partial point clouds, the hybrid approach improves success rates over purely learning-based or analytical methods.
The paper proposes a hybrid grasp synthesis framework combining a learned Energy-Based Model with an analytical ICP method, achieving a 60.9% success rate on 5,360 grasp attempts, outperforming AnyGrasp (31.1%), Grasp Pose Detection (48.4%), and AS-ICP (56.6%).
We 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.