基于神经表面渲染学习杂乱场景中的任意视角 6DoF 机器人抓取
Learning Any-View 6DoF Robotic Grasping in Cluttered Scenes via Neural Surface Rendering
AI总结：
研究解决了杂乱场景中任意视角的 6DoF 抓取难题，提出 NeuGraspNet 方法，将抓取重解释为渲染，通过共享特征空间联合学习局部表面渲染与抓取函数，实现完全隐式的抓取质量预测，并在真实移动机器人上验证了其优于现有方法的有效性。
摘要：
真实世界机器人操作的一个重大挑战是，如何在无需额外场景探索的情况下，从任意单一视角对杂乱场景中的物体进行有效的 6DoF 抓取。这项工作将抓取重新解释为渲染，并引入了 NeuGraspNet，这是一种利用神经体积表示和表面渲染进展的新型 6DoF 抓取检测方法。它通过在共享特征空间中联合学习渲染局部物体表面和学习抓取函数，来编码机器人末端执行器与物体表面之间的交互。该方法使用全局（场景级）特征进行抓取生成，并使用局部（抓取级）神经表面特征进行抓取评估。这使得即使在部分观测的场景中，也能进行有效的、完全隐式的 6DoF 抓取质量预测。NeuGraspNet 可在移动操作场景中常见的随机视角下运行，并优于现有的隐式和半隐式抓取方法。该方法的现实世界适用性已通过移动操作机器人得到验证，能够在开放、杂乱的空间中进行抓取。项目网站：https://sites.google.com/view/neugraspnet
英文摘要：
A significant challenge for real-world robotic manipulation is the effective 6DoF grasping of objects in cluttered scenes from any single viewpoint without the need for additional scene exploration. This work reinterprets grasping as rendering and introduces NeuGraspNet, a novel method for 6DoF grasp detection that leverages advances in neural volumetric representations and surface rendering. It encodes the interaction between a robot's end-effector and an object's surface by jointly learning to render the local object surface and learning grasping functions in a shared feature space. The approach uses global (scene-level) features for grasp generation and local (grasp-level) neural surface features for grasp evaluation. This enables effective, fully implicit 6DoF grasp quality prediction, even in partially observed scenes. NeuGraspNet operates on random viewpoints, common in mobile manipulation scenarios, and outperforms existing implicit and semi-implicit grasping methods. The real-world applicability of the method has been demonstrated with a mobile manipulator robot, grasping in open, cluttered spaces. Project website at https://sites.google.com/view/neugraspnet
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
