论文标题
神经运动场：编码GRASP轨迹作为隐式价值函数
Neural Motion Fields: Encoding Grasp Trajectories as Implicit Value Functions
论文作者
论文摘要
当前机器人拾取方法的管道通常包括几个阶段：抓握姿势检测，为检测到的姿势找到逆运动溶液，计划无碰撞轨迹，然后用低级跟踪控制器执行开放环轨迹向GRASP姿势执行。尽管这些抓握方法在桌上抓住静态对象方面表现出良好的性能，但在受约束环境中抓住动态对象的问题仍然是一个开放的问题。我们提出了神经运动场，这是一种新颖的对象表示，它编码对象点云和相对任务轨迹作为由神经网络参数化的隐式值函数。以对象为中心的表示形式在SE（3）空间上建模了连续分布，并允许我们通过利用基于采样的MPC来反应地执行握把以优化此值函数。
The pipeline of current robotic pick-and-place methods typically consists of several stages: grasp pose detection, finding inverse kinematic solutions for the detected poses, planning a collision-free trajectory, and then executing the open-loop trajectory to the grasp pose with a low-level tracking controller. While these grasping methods have shown good performance on grasping static objects on a table-top, the problem of grasping dynamic objects in constrained environments remains an open problem. We present Neural Motion Fields, a novel object representation which encodes both object point clouds and the relative task trajectories as an implicit value function parameterized by a neural network. This object-centric representation models a continuous distribution over the SE(3) space and allows us to perform grasping reactively by leveraging sampling-based MPC to optimize this value function.
