The first self-checkout system was installed in 1986 at a Kroger grocery store just outside of Atlanta. It took several decades, but the technology eventually proliferated across the United States. Given the direction automated grocery stores are headed, it seems robotic bagging isn’t too far behind.
MIT’s CSAIL department presents this week Robotic Grocery Store. It combines computer vision with a flexible robotic gripper to bag a wide variety of different items. To test the system, the researchers placed 10 objects unknown to the robot on a grocery store conveyor belt.
The products ranged from delicate items like grapes, bread, kale, muffins and crackers to much more solid products like soup cans, lunch boxes and ice cream containers. The vision system comes into play first, detecting the objects before determining their size and orientation on the belt.
When the gripper touches the grapes, pressure sensors in its fingers determine that they are in fact fragile and therefore should not be dropped to the bottom of the bag – something many of us have no doubt been taught to do. their costs. Then he notices that the can is a more rigid structure and places it at the bottom of the bag.
“This is an important first step toward robots that pack groceries and other items in real-world settings,” said Annan Zhang, one of the study’s lead authors. “While we’re not quite ready for commercial deployment, our research demonstrates the power of integrating multiple sensing modalities into soft robotic systems.”
The team notes that there is still much work to be done, including upgrading the gripping device and imaging system to better determine how and in what order to pack things. As the system becomes more robust, it can also be deployed outside of the grocery store in more industrial spaces like recycling plants.
