# Learning Object Relations with Graph Neural Networks for Target-Driven Grasping in Dense Clutter

arXiv: https://arxiv.org/abs/2203.00875 · HTML: https://mlsanity.com/paper/2203.00875/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Mar 2022.

## Built on by (most cited first, 6 of 6)

- [Graph learning in robotics: a survey](https://mlsanity.com/paper/2310.04294/) (2023)
- [GraNet: A Multi-Level Graph Network for 6-DoF Grasp Pose Generation in Cluttered Scenes](https://mlsanity.com/paper/2312.03345/) (2023)
- [Multi-Object Graph Affordance Network: Goal-Oriented Planning through Learned Compound Object Affordances](https://mlsanity.com/paper/2309.10426/) (2023)
- [Target-Oriented Object Grasping via Multimodal Human Guidance](https://mlsanity.com/paper/2408.11138/) (2024)
- [Grasp the Graph (GtG) 2.0: Ensemble of Graph Neural Networks for High-Precision Grasp Pose Detection in Clutter](https://mlsanity.com/paper/2505.02664/) (2025)
- [Learning Object-Centric Spatial Reasoning for Sequential Manipulation in Cluttered Environments](https://mlsanity.com/paper/2603.02511/) (2026)

## Abstract (arXiv)

Robots in the real world frequently come across identical objects in dense clutter. When evaluating grasp poses in these scenarios, a target-driven grasping system requires knowledge of spatial relations between scene objects (e.g., proximity, adjacency, and occlusions). To efficiently complete this task, we propose a target-driven grasping system that simultaneously considers object relations and predicts 6-DoF grasp poses. A densely cluttered scene is first formulated as a grasp graph with nodes representing object geometries in the grasp coordinate frame and edges indicating spatial relations between the objects. We design a Grasp Graph Neural Network (G2N2) that evaluates the grasp graph and finds the most feasible 6-DoF grasp pose for a target object. Additionally, we develop a shape completion-assisted grasp pose sampling method that improves sample quality and consequently grasping efficiency. We compare our method against several baselines in both simulated and real settings. In real-world experiments with novel objects, our approach achieves a 77.78% grasping accuracy in densely cluttered scenarios, surpassing the best-performing baseline by more than 15%. Supplementary material is available at https://sites.google.com/umn.edu/graph-grasping.