# Continual Learning for 6-DoF Grasp Synthesis via Experience and Demonstrations

arXiv: https://arxiv.org/abs/2610.01301 · HTML: https://mlsanity.com/paper/2610.01301/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 36 references that are in the map.
- First posted on arXiv 1 Oct 2026.

## Builds on (most cited first, 23 of 23)

- [6-DOF GraspNet: Variational Grasp Generation for Object Manipulation](https://mlsanity.com/paper/1905.10520/) (2019)
- [Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenes](https://mlsanity.com/paper/2103.14127/) (2021)
- [AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domains](https://mlsanity.com/paper/2212.08333/) (2022)
- [DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation](https://mlsanity.com/paper/2210.02697/) (2022)
- [Grasp Pose Detection in Point Clouds](https://mlsanity.com/paper/1706.09911/) (2017)
- [Efficient Learning on Point Clouds with Basis Point Sets](https://mlsanity.com/paper/1908.09186/) (2019)
- [Volumetric Grasping Network: Real-time 6 DOF Grasp Detection in Clutter](https://mlsanity.com/paper/2101.01132/) (2021)
- [Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulation](https://mlsanity.com/paper/2401.07487/) (2024)
- [M2T2: Multi-Task Masked Transformer for Object-centric Pick and Place](https://mlsanity.com/paper/2311.00926/) (2023)
- [Edge Grasp Network: A Graph-Based SE(3)-invariant Approach to Grasp Detection](https://mlsanity.com/paper/2211.00191/) (2022)
- [GraspGen: A Diffusion-based Framework for 6-DOF Grasping with On-Generator Training](https://mlsanity.com/paper/2507.13097/) (2025)
- [ICGNet: A Unified Approach for Instance-Centric Grasping](https://mlsanity.com/paper/2401.09939/) (2024)
- [GraspLDM: Generative 6-DoF Grasp Synthesis using Latent Diffusion Models](https://mlsanity.com/paper/2312.11243/) (2023)
- [DGCM-Net: Dense Geometrical Correspondence Matching Network for Incremental Experience-based Robotic Grasping](https://mlsanity.com/paper/2001.05279/) (2020)
- [Generalizing 6-DoF Grasp Detection via Domain Prior Knowledge](https://mlsanity.com/paper/2404.01727/) (2024)
- [Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots](https://mlsanity.com/paper/2509.02530/) (2025)
- [Exploratory Grasping: Asymptotically Optimal Algorithms for Grasping Challenging Polyhedral Objects](https://mlsanity.com/paper/2011.05632/) (2020)
- [TransGrasp: Grasp Pose Estimation of a Category of Objects by Transferring Grasps from Only One Labeled Instance](https://mlsanity.com/paper/2207.07861/) (2022)
- [Attribute-Based Robotic Grasping with Data-Efficient Adaptation](https://mlsanity.com/paper/2501.02149/) (2025)
- [GraspClutter6D: A Large-scale Real-world Dataset for Robust Perception and Grasping in Cluttered Scenes](https://mlsanity.com/paper/2504.06866/) (2025)
- [Uncertainty-driven Exploration Strategies for Online Grasp Learning](https://mlsanity.com/paper/2309.12038/) (2023)
- [LEGS: Learning Efficient Grasp Sets for Exploratory Grasping](https://mlsanity.com/paper/2111.15002/) (2021)
- [Pseudo-Labeling and Contextual Curriculum Learning for Online Grasp Learning in Robotic Bin Picking](https://mlsanity.com/paper/2403.02495/) (2024)

## Abstract (arXiv)

Most current grasp synthesis systems are trained offline and remain fixed during deployment. While this works well when deployment conditions resemble the training data, performance can degrade when robots encounter conditions they have not seen before, such as unfamiliar objects. In this work, we present a continual-learning framework for single-view 6-DoF grasp synthesis for a parallel-jaw gripper in cluttered scenes. Rather than finetuning a large parametric model, our method adapts through memory in a learned embedding space: grasp outcomes update future grasp scores, while optional user demonstrations are recalled and transferred to new scenes as additional candidate grasps. We evaluate our method in simulation and in extensive real-world experiments comprising over 1500 grasp trials. We show that our method matches the performance of existing 6-DoF grasping baselines even before adaptation, improves online on unseen objects from categories absent or underrepresented during training, and supports long-horizon continual learning with limited forgetting. In real-world experiments, our method reaches over 90% success rates on several challenging object categories after only 50 online grasp attempts. Videos and code at https://giuschio.github.io/clgrasping/.