MIT's CSAIL department is showcasing RoboGrocery, a system that combines computer vision with a soft robotic gripper to bag a wide range of different items2. The vision system detects objects on a conveyor belt, determining their size and orientation, while pressure sensors in the gripper handle delicate items carefully. This technology is a significant step towards having robots pack groceries and other items in real-world settings.
The researchers tested RoboGrocery with 10 objects unknown to the robot on a grocery conveyer belt1. These objects included delicate items like grapes, bread, kale, muffins, and crackers, as well as more solid items like soup cans, meal boxes, and ice cream containers.