6-PACK

6D-Pose Anchor-based Category-level Keypoint-tracker (6-PACK): Deep Learning for 6D Object Tracking in Robotics

A model called 6-PACK uses video from a depth-sensing camera to track objects in six dimensions (position and orientation in 3D space), extending AI object tracking beyond standard 2D approaches. The system is designed for robotics applications where understanding how objects move through physical space is critical. The Batch highlights this as a capability advance in perception for robotic manipulation and interaction.