# Iterative Grasp Pose Refinement: A Deep Reinforcement Learning Approach for 2D Vision

arXiv: https://arxiv.org/abs/2608.17628 · HTML: https://mlsanity.com/paper/2608.17628/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 11 of its 24 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

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

- [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)
- [An Introduction to Deep Reinforcement Learning](https://mlsanity.com/paper/1811.12560/) (2018)
- [kPAM: KeyPoint Affordances for Category-Level Robotic Manipulation](https://mlsanity.com/paper/1903.06684/) (2019)
- [Reinforcement and Imitation Learning for Diverse Visuomotor Skills](https://mlsanity.com/paper/1802.09564/) (2018)
- [Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations](https://mlsanity.com/paper/2003.06085/) (2020)
- [Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation](https://mlsanity.com/paper/2105.14829/) (2021)
- [Learning Task-Oriented Grasping for Tool Manipulation from Simulated Self-Supervision](https://mlsanity.com/paper/1806.09266/) (2018)
- [Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control](https://mlsanity.com/paper/1511.03791/) (2015)
- [Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods](https://mlsanity.com/paper/1802.10264/) (2018)
- [Efficient Robotic Task Generalization Using Deep Model Fusion Reinforcement Learning](https://mlsanity.com/paper/1912.05205/) (2019)
- [Improving the Successful Robotic Grasp Detection Using Convolutional Neural Networks](https://mlsanity.com/paper/2403.05211/) (2024)

## Abstract (arXiv)

Developing robots capable of understanding and manipulating objects requires compact, interpretable, and generalizable representations. This work proposes a reinforcement learning-based framework for robotic grasp refinement, integrating keypoint-based object representations with a Deep Q-Network (DQN). Using 2D overhead images captured in a simulated environment, a geometric-based algorithm generates initial grasp candidates, which are iteratively refined by the proposed framework, transforming failed grasps into successful ones. Experiments conducted on 300 objects from the Dex-Net dataset using a UR5 manipulator demonstrate the framework's effectiveness, achieving a 100% success rate on objects previously deemed ungraspable by geometrical methods. The framework's sim-to-real transferability is further validated through physical experiments on a Delta parallel robot, where a refined grasp successfully manipulates an object that was previously ungraspable. The findings underscore the effectiveness of reinforcement learning in addressing challenges in robotic grasping, offering a scalable and adaptable solution for contact-rich manipulation tasks.