Summary
In previous work, we investigated how a robot picking up two objects can estimate the poses of those objects by bringing them into contact with one another. In this extension, we propose a method that addresses the problem of reducing pose uncertainty through a sequence of frictional contact interactions between the grasped objects. As part of our method, we propose:
1) a tool segmentation routine that facilitates contact location and object pose estimation,
2) a loss that allows reasoning over solution consistency between interactions, and
3) a loss to promote converging to object poses and contact locations that explain the external force-torque experienced by each arm.
We demonstrate the efficacy of our method in a task-based demonstration both in simulation and on a real-world bimanual platform and show significant improvement in object pose estimation over single interactions.
Authors
Paper and Code
In Robotics: Science and Systems (RSS 2023), Daegu, South Korea.