MIT’s Computer Science & Artificial Intelligence Laboratory (CSAIL) has introduced a robotic system that packs groceries called RoboGrocery.
RoboGrocery specifies the size of the products, correctly differentiates between the types of products, and performs the packaging process. For example, it avoids placing light products, such as strawberries, at the bottom of the bag and places more durable products, such as cans, at the bottom of the bag.
“The challenge here is making immediate decisions about whether to pack an item or not, especially since we make no assumptions about the object as it comes down the conveyor belt,” says MIT CSAIL PhD student Annan Zhang, one of the lead authors on a new paper about RoboGrocery. “Our system measures each item, decides if it’s delicate, and packs it directly or places it in a buffer to pack later.”
To test the system’s capabilities, researchers had the robot place 10 different types of objects on a grocery conveyor belt. A soft robotic gripper is defined as a robotic hand or holding device made of flexible and soft materials. Unlike hard and rigid robotic hands, such grippers can grasp and move delicate and fragile objects without damaging them.
“Automating grocery packing with robots capable of soft and delicate grasping and high-level reasoning, like the robot in our project, has the potential to impact retail efficiency and open new avenues for innovation,” says senior author Daniela Rus, CSAIL director and professor of electrical engineering and computer science (EECS) at MIT.
Automating routine tasks, such as bagging groceries, can direct human labor to more complex and creative tasks. This can increase operational efficiency in grocery stores and reduce costs. Outside of grocery stores, this technology can also be used in industrial areas such as recycling facilities.
