Learning to Infer Kinematic Hierarchies for Novel Object Instances
Learning to Infer Kinematic Hierarchies for Novel Object Instances
复制标题
DOI：
10.1109/icra46639.2022.9811968
复制
发表时间：
2021-10
期刊：
影响因子：
--
通讯作者：
H. Abdul-Rashid;Miles Freeman;Ben Abbatematteo;G. Konidaris;Daniel Ritchie
中科院分区：
文献类型：
--
作者：
H. Abdul-Rashid;Miles Freeman;Ben Abbatematteo;G. Konidaris;Daniel Ritchie
操纵一个铰接物体需要感知它的运动层次结构：它的各个部分、每个部分如何移动以及这些运动如何耦合。以前的工作已经探索了运动学的感知，但没有一个工作能够在不依赖模式或模板的情况下推断出从未见过的对象实例的完整运动学层次结构。我们提出了一种新颖的感知系统来实现这一目标。我们的系统推断物体的运动部件以及与它们相关的运动耦合。为了推断零件，它使用点云实例分割神经网络；为了推断运动层次结构，它使用图神经网络来预测与推断零件相关的边缘（即关节）的存在、方向和类型。我们使用合成 3D 模型的模拟扫描来训练这些网络。我们在 3D 对象的模拟扫描上评估我们的系统，并演示使用我们的系统驱动现实世界机器人操作的概念验证。
Manipulating an articulated object requires perceiving its kinematic hierarchy: its parts, how each can move, and how those motions are coupled. Previous work has explored perception for kinematics, but none infers a complete kinematic hierarchy on never-before-seen object instances, without relying on a schema or template. We present a novel perception system that achieves this goal. Our system infers the moving parts of an object and the kinematic couplings that relate them. To infer parts, it uses a point cloud instance segmentation neural network and to infer kinematic hierarchies, it uses a graph neural network to predict the existence, direction, and type of edges (i.e. joints) that relate the inferred parts. We train these networks using simulated scans of synthetic 3D models. We evaluate our system on simulated scans of 3D objects, and we demonstrate a proof-of-concept use of our system to drive real-world robotic manipulation.