用强化学习迭代优化2D视觉下的抓取姿态，让原本抓不住的物体也能成功抓取。
Iterative Grasp Pose Refinement: A Deep Reinforcement Learning Approach for 2D Vision
- 基于关键点表示与DQN，通过迭代策略优化抓取姿态。
- 在300个Dex-Net物体上实现100%抓取成功率，包括原方法无法抓取的物体。
- 支持从仿真到物理机器人的迁移，适用于复杂接触场景。
构建具备理解与操作能力的机器人需要紧凑、可解释且通用的表征。本文提出一种基于强化学习的抓取姿态优化框架，结合基于关键点的物体表征与深度Q网络（DQN）。利用模拟环境中获取的2D俯视图像，先由几何算法生成初始抓取候选，再通过所提框架迭代优化，将失败抓取转化为成功抓取。在包含300个物体的Dex-Net数据集上，使用UR5机械臂的实验表明，该框架对原先几何方法判定为不可抓取的物体实现了100%的抓取成功率。进一步通过在Delta并联机器人上的实物实验验证了其从仿真到现实的迁移能力，成功操控了原本无法抓取的物体。结果表明，强化学习在解决机器人抓取挑战方面具有显著有效性，为高接触性操作任务提供了可扩展、自适应的解决方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。