# CAGE: Context-Aware Grasping Engine

arXiv: https://arxiv.org/abs/1909.11142 · HTML: https://mlsanity.com/paper/1909.11142/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Sep 2019.

## Built on by (most cited first, 10 of 10)

- [A Joint Network for Grasp Detection Conditioned on Natural Language Commands](https://mlsanity.com/paper/2104.00492/) (2021)
- [Composable Part-Based Manipulation](https://mlsanity.com/paper/2405.05876/) (2024)
- [Task-Oriented 6-DoF Grasp Pose Detection in Clutters](https://mlsanity.com/paper/2502.16976/) (2025)
- [CoGrasp: 6-DoF Grasp Generation for Human-Robot Collaboration](https://mlsanity.com/paper/2210.03173/) (2022)
- [Point2Act: Efficient 3D Distillation of Multimodal LLMs for Zero-Shot Context-Aware Grasping](https://mlsanity.com/paper/2508.03099/) (2025)
- [Remote Task-oriented Grasp Area Teaching By Non-Experts through Interactive Segmentation and Few-Shot Learning](https://mlsanity.com/paper/2303.10195/) (2023)
- [EfficientPPS: Part-aware Panoptic Segmentation of Transparent Objects for Robotic Manipulation](https://mlsanity.com/paper/2312.13906/) (2023)
- [CLASP: General-Purpose Clothes Manipulation with Semantic Keypoints](https://mlsanity.com/paper/2507.19983/) (2025)
- [Semantics in Robotics: Environmental Data Can't Yield Conventions of Human Behaviour](https://mlsanity.com/paper/2410.19308/) (2024)
- [Task-oriented grasping for dexterous robots using postural synergies and reinforcement learning](https://mlsanity.com/paper/2602.20915/) (2026)

## Abstract (arXiv)

Semantic grasping is the problem of selecting stable grasps that are functionally suitable for specific object manipulation tasks. In order for robots to effectively perform object manipulation, a broad sense of contexts, including object and task constraints, needs to be accounted for. We introduce the Context-Aware Grasping Engine, which combines a novel semantic representation of grasp contexts with a neural network structure based on the Wide & Deep model, capable of capturing complex reasoning patterns. We quantitatively validate our approach against three prior methods on a novel dataset consisting of 14,000 semantic grasps for 44 objects, 7 tasks, and 6 different object states. Our approach outperformed all baselines by statistically significant margins, producing new insights into the importance of balancing memorization and generalization of contexts for semantic grasping. We further demonstrate the effectiveness of our approach on robot experiments in which the presented model successfully achieved 31 of 32 suitable grasps. The code and data are available at: https://github.com/wliu88/rail_semantic_grasping