# Training-free Suction Grasp Detection for Deformed Aseptic Cartons Using Vision-Language Models and Geometric Surface Scoring

arXiv: https://arxiv.org/abs/2608.28246 · HTML: https://mlsanity.com/paper/2608.28246/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 17 references that are in the map.
- First posted on arXiv 28 Aug 2026.

## Builds on (most cited first, 11 of 11)

- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [ZeroWaste Dataset: Towards Deformable Object Segmentation in Cluttered Scenes](https://mlsanity.com/paper/2106.02740/) (2021)
- [TACO: Trash Annotations in Context for Litter Detection](https://mlsanity.com/paper/2003.06975/) (2020)
- [SuctionNet-1Billion: A Large-Scale Benchmark for Suction Grasping](https://mlsanity.com/paper/2103.12311/) (2021)
- [AffordGrasp: In-Context Affordance Reasoning for Open-Vocabulary Task-Oriented Grasping in Clutter](https://mlsanity.com/paper/2503.00778/) (2025)
- [GraspSAM: When Segment Anything Model Meets Grasp Detection](https://mlsanity.com/paper/2409.12521/) (2024)
- [Sim-Suction: Learning a Suction Grasp Policy for Cluttered Environments Using a Synthetic Benchmark](https://mlsanity.com/paper/2305.16378/) (2023)
- [HiFi-CS: Towards Open Vocabulary Visual Grounding For Robotic Grasping Using Vision-Language Models](https://mlsanity.com/paper/2409.10419/) (2024)
- [OptiGrasp: Optimized Grasp Pose Detection Using RGB Images for Warehouse Picking Robots](https://mlsanity.com/paper/2409.19494/) (2024)
- [Diffusion Suction Grasping with Large-Scale Parcel Dataset](https://mlsanity.com/paper/2502.07238/) (2025)

## Abstract (arXiv)

Robotic sorting of recyclable waste is challenging due to the deformable and geometrically inconsistent nature of target objects. We present a training-free suction grasping system for sorting deformed aseptic beverage cartons, decoupling target identification from grasp-point selection. An open-vocabulary vision-language model detects cartons from a text prompt, SAM2 refines each detection into an instance mask, and a geometric scoring method selects the suction point by combining surface flatness with normal alignment. Three geometric methods are compared: k-nearest-neighbour PCA, Sobel cross-product, and RANSAC plane fitting. Evaluated on a real robot across three deformation levels and 35 cluttered scenes, single-object grasp success reaches 88.2% and end-to-end retrieval in clutter is 72.6%.