Let's Handle It: Generalizable Manipulation of Articulated Objects
This work addresses manipulation tasks for household objects, but it is incremental as it uses traditional robotics methods without novel breakthroughs.
The authors tackled the problem of generalizable manipulation of articulated objects by developing a framework that maps raw point clouds and segmentation masks to joint velocities, demonstrating it on four manipulation skills in the SAPIEN ManiSkill challenge.
In this project we present a framework for building generalizable manipulation controller policies that map from raw input point clouds and segmentation masks to joint velocities. We took a traditional robotics approach, using point cloud processing, end-effector trajectory calculation, inverse kinematics, closed-loop position controllers, and behavior trees. We demonstrate our framework on four manipulation skills on common household objects that comprise the SAPIEN ManiSkill Manipulation challenge.