EquiGQNet speeds up robot grasping by sharing 3D object views
EquiGQNet: Fast Grasp Quality Evaluation via Shared Equivariant Point Cloud Encoding
Robotics
Summary
Picking up objects with robots involves figuring out the best way to grab them in a 3D space, which can take a lot of time. The authors designed EquiGQNet, a method that processes the object’s 3D shape only once and then quickly checks many possible ways to grasp it from different angles. This approach keeps important details about how the robot hand should align for each grip while being much faster than previous methods. In tests with simulated and real cluttered scenes, EquiGQNet was both faster and more successful at grasping hard-to-pick objects than earlier techniques.
6-DoF graspingpoint cloudSO(3)-equivarianceearly fusionlate fusiongrasp quality evaluationdepth imagerobotic grasp planningCross-Entropy Methodgenerative planner
Authors
Sungwon Seo, Jaeseog Won, Jiyou Shin, Youngjin Seo, Hyunjun Kim, Seokmin Yoon, Tuan Luong, Hyungpil Moon
Abstract
Planning six-degree-of-freedom (6-DoF) grasps for unseen objects in cluttered tabletop scenes from a single-view depth image requires accurate and efficient evaluation of diverse grasp candidates. Existing early-fusion methods capture local object geometry relative to each grasp candidate but repeatedly encode the scene, whereas late-fusion methods reuse a shared scene representation but may lose this grasp-relative local geometry. We propose EquiGQNet, an efficient 6-DoF grasp quality evaluator that combines the strengths of both approaches. For grasp orientation, EquiGQNet replaces the early-fusion operation of rotating and re-encoding the point cloud for each grasp candidate with an SO(3)-equivariant encode-once-then-rotate scheme, yielding grasp-aligned geometric features from a shared scene encoding. For grasp translation, Mid-level Action Fusion (MAF) injects the grasp position into intermediate features before global aggregation, retaining local geometry relative to each candidate. We evaluate EquiGQNet in two grasp planning pipelines: Cross-Entropy Method (CEM)-based continuous grasp search and candidate ranking with a pretrained generative planner. In simulation, EquiGQNet achieves grasping performance comparable to the early-fusion baseline and substantially outperforms late fusion on objects with complex geometry and limited graspable regions, while reducing CEM planning time from 3.31s to 0.48s, a 6.9x speedup over early fusion. In real-world household-object decluttering, EquiGQNet achieves a 95.2% grasp success rate and 230 picks per hour, versus 153 and 170 for early- and late-fusion baselines. Code is available at https://equigqnet.github.io/.