论文标题
工具流：通过预测点云的工具流进行工具的机器人操作
ToolFlowNet: Robotic Manipulation with Tools via Predicting Tool Flow from Point Clouds
论文作者
论文摘要
点云是传达场景的3D几何形状的广泛可用和规范的数据模式。尽管从点云中分类和细分方面取得了重大进展，但从这种方式中学习的政策学习仍然具有挑战性，并且在模仿学习中的大多数先前的工作都集中在图像或状态信息中学习政策。在本文中，我们提出了一个新颖的框架，用于从点云中学习政策，用于使用工具进行机器人操纵。我们使用一种新颖的神经网络工具氟网，该网络可预测机器人控制的工具上的密集每点流，然后使用流程来得出机器人应执行的转换。我们将此框架应用于通过连续移动工具（包括sc sc和倒入）来模仿具有挑战性可变形的对象操纵任务的学习，并证明了与不使用流量的基线相比的性能明显提高。我们使用工具氟下进行50次物理铲实验，并获得82％的sc oop成功。有关补充材料，请参见https://tinyurl.com/toolflownet。
Point clouds are a widely available and canonical data modality which convey the 3D geometry of a scene. Despite significant progress in classification and segmentation from point clouds, policy learning from such a modality remains challenging, and most prior works in imitation learning focus on learning policies from images or state information. In this paper, we propose a novel framework for learning policies from point clouds for robotic manipulation with tools. We use a novel neural network, ToolFlowNet, which predicts dense per-point flow on the tool that the robot controls, and then uses the flow to derive the transformation that the robot should execute. We apply this framework to imitation learning of challenging deformable object manipulation tasks with continuous movement of tools, including scooping and pouring, and demonstrate significantly improved performance over baselines which do not use flow. We perform 50 physical scooping experiments with ToolFlowNet and attain 82% scooping success. See https://tinyurl.com/toolflownet for supplementary material.
