Robot grasp planner speeds up object picking with accurate evaluation
EquiGQNet: Fast Grasp Quality Evaluation via Shared Equivariant Point Cloud Encoding
Robotics
Summary
Planning how a robot hand can pick up different objects is tricky, especially when the objects are new and scattered on a table. The authors designed a system called EquiGQNet that quickly figures out good ways to grasp objects by better using the 3D shape information without repeating calculations. Their method is much faster than earlier ones and works well in both simulations and real-world tests, helping robots pick up more objects successfully and quickly.
What this means in practice
- •For industrial automation teams: Increase robotic bin picking speed and success by rapidly evaluating complex objects for grasping using a shared 3D scene encoding approach.
- •For warehouse robotics engineers: Improve cluttered tabletop decluttering robots’ pick rates and grasp reliability by integrating this fast, accurate grasp quality evaluation method.
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/.