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

arXiv:2608.17628v1 Announce Type: cross Abstract: 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.

Related

• Learning to Refine: Spectral-Decoupled Iterative Refinement Framework for Precipitation Nowcasting
• A Primer on SO(3) Action Representations in Deep Reinforcement Learning
• Stable Deep Reinforcement Learning via Isotropic Gaussian Representations
• DualMem: Bypassing the Objectness Bottleneck for Calibrated Unknown-Stream Filtering in Open-World Object Detection

Source: arXiv cs.AI | 2026-08-19