Motion-Nets: 6D Tracking of Unknown Objects in Unseen Environments using RGB
This enables robots to track unknown objects in new settings, though it appears incremental as it builds on existing pose estimation and tracking methods.
The authors tackled the problem of 6D object tracking in unseen environments using RGB data, developing Motion-Nets to segment scenes and predict object motion, achieving quantitative accuracy for 30-60 frames with low errors up to 100 frames.
In this work, we bridge the gap between recent pose estimation and tracking work to develop a powerful method for robots to track objects in their surroundings. Motion-Nets use a segmentation model to segment the scene, and separate translation and rotation models to identify the relative 6D motion of an object between two consecutive frames. We train our method with generated data of floating objects, and then test on several prediction tasks, including one with a real PR2 robot, and a toy control task with a simulated PR2 robot never seen during training. Motion-Nets are able to track the pose of objects with some quantitative accuracy for about 30-60 frames including occlusions and distractors. Additionally, the single step prediction errors remain low even after 100 frames. We also investigate an iterative correction procedure to improve performance for control tasks.