# Learning to Efficiently Plan Robust Frictional Multi-Object Grasps

arXiv: https://arxiv.org/abs/2210.07420 · HTML: https://mlsanity.com/paper/2210.07420/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 54 references that are in the map.
- First posted on arXiv 13 Oct 2022.

## Builds on (most cited first, 17 of 17)

- [Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics](https://mlsanity.com/paper/1703.09312/) (2017)
- [Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience](https://mlsanity.com/paper/1810.05687/) (2018)
- [Domain Randomization and Generative Models for Robotic Grasping](https://mlsanity.com/paper/1710.06425/) (2017)
- [Funnel Libraries for Real-Time Robust Feedback Motion Planning](https://mlsanity.com/paper/1601.04037/) (2016)
- [ACID: Action-Conditional Implicit Visual Dynamics for Deformable Object Manipulation](https://mlsanity.com/paper/2203.06856/) (2022)
- [Surprisingly Robust In-Hand Manipulation: An Empirical Study](https://mlsanity.com/paper/2201.11503/) (2022)
- [Dex-Net 3.0: Computing Robust Robot Vacuum Suction Grasp Targets in Point Clouds using a New Analytic Model and Deep Learning](https://mlsanity.com/paper/1709.06670/) (2017)
- [Occlusion-Aware Search for Object Retrieval in Clutter](https://mlsanity.com/paper/2011.03334/) (2020)
- [Sim-to-Real Transfer for Robotic Manipulation with Tactile Sensory](https://mlsanity.com/paper/2103.00410/) (2021)
- [Collision-Aware Target-Driven Object Grasping in Constrained Environments](https://mlsanity.com/paper/2104.00776/) (2021)
- [Multi-Object Grasping -- Estimating the Number of Objects in a Robotic Grasp](https://mlsanity.com/paper/2112.01270/) (2021)
- [Multi-Object Grasping in the Plane](https://mlsanity.com/paper/2206.00229/) (2022)
- [Pushing Fast and Slow: Task-Adaptive Planning for Non-prehensile Manipulation Under Uncertainty](https://mlsanity.com/paper/1805.03005/) (2018)
- [Real-Time Online Re-Planning for Grasping Under Clutter and Uncertainty](https://mlsanity.com/paper/1807.09049/) (2018)
- [Multi-Object Grasping -- Generating Efficient Robotic Picking and Transferring Policy](https://mlsanity.com/paper/2112.09829/) (2021)
- [Human-like Planning for Reaching in Cluttered Environments](https://mlsanity.com/paper/2002.12738/) (2020)
- [Robust Physics-Based Manipulation by Interleaving Open and Closed-Loop Execution](https://mlsanity.com/paper/2105.08325/) (2021)

## Built on by (most cited first, 5 of 5)

- [A Survey of Embodied Learning for Object-Centric Robotic Manipulation](https://mlsanity.com/paper/2408.11537/) (2024)
- [Stable Object Placement Planning From Contact Point Robustness](https://mlsanity.com/paper/2410.12483/) (2024)
- [RoboVista: Evaluating Vision Language Models for Diverse Robot Applications](https://mlsanity.com/paper/2607.04610/) (2026)
- [Learning to Push, Group, and Grasp: A Diffusion Policy Approach for Multi-Object Delivery](https://mlsanity.com/paper/2502.08452/) (2025)
- [Dynamic Buffers: Cost-Efficient Planning for Tabletop Rearrangement with Stacking](https://mlsanity.com/paper/2509.22828/) (2025)

## Abstract (arXiv)

We consider a decluttering problem where multiple rigid convex polygonal objects rest in randomly placed positions and orientations on a planar surface and must be efficiently transported to a packing box using both single and multi-object grasps. Prior work considered frictionless multi-object grasping. In this paper, we introduce friction to increase the number of potential grasps for a given group of objects, and thus increase picks per hour. We train a neural network using real examples to plan robust multi-object grasps. In physical experiments, we find a 13.7% increase in success rate, a 1.6x increase in picks per hour, and a 6.3x decrease in grasp planning time compared to prior work on multi-object grasping. Compared to single-object grasping, we find a 3.1x increase in picks per hour.