I've written a few times about the use of robotics in retail in the past few years, whether it's the automated stock control system developed by Simbe Robotics, or even the fully automated store that recently opened in Sweden.
Of course, automation has been relatively easy to install in big box type environments that are found in Amazon warehouses, but it's much harder when dealing with more delicate items, such as fruit and vegetable, that require more sensitive handling.
Ocado, the world's largest online-only supermarket, have been experimenting with robotic picking and packing of shopping at its highly automated warehouse. The project, which is part of the SoMa Horizon 2020 framework program.
The project is a collaborative venture between the Technische Universität Berlin (TUB), Università di Pisa, Istituto Italiano di Tecnologia, Deutsches Zentrum für Luft- und Raumfahrt e.V. (DLR), the Institute of Science and Technology Austria, Ocado Technology, and Disney Research Zurich.
One of the main challenges they have looked to overcome is the ability to manipulate delicate and unusually shaped items, such as those typically found in grocery stores. To overcome this challenge, the team use a compliant gripper alongside an industrial robot arm.
The gripper is designed to handle the full 48,000 or so items currently stocked by Ocado, and it will do so via compliant robotic hands that are specifically designed to handle fragile objects, even with minimal knowledge as to the shape of the item.
An example of a compliant gripper is the RBO Hand 2 developed by the Technische Universität Berlin (TUB). The gripper uses flexible rubber materials and pressurized air for passively adapting grasps which allows for safe and damage-free picking of objects. With seven individually controllable air chambers, the anthropomorphic design enables versatile grasping strategies.
Due to its compliant design, the robotic hand is highly under-actuated: only the air pressure is controlled, while the fingers, palm, and thumb adjust their shape to the given object geometry (morphological computation). This simplifies control and enables effective exploitation of the environment.
The Ocado Technology robotics team replicated a production warehouse scenario in order to evaluate the performance of the RBO Hand 2 for Ocado's use case. The team mounted the soft hand on two different robot arms, a Staubli RX160L and a KUKA LBR iiwa14. Both of these arms can operate in the standard position controlled mode; in addition to this, the KUKA provides the capability of demonstrating a certain amount of software controlled compliance in the arm.
The experiments started with the simple scenario of grasping a single object from the example set using only the bottom of the tray. Initial results showed that the hand is able to successfully grasp a variety of shapes and the results suggested the chance of success increased when environmental constraints are being used effectively to restrict the movement of the object.
In the coming months, we plan to explore more complex scenarios, adding more objects in the IFCO, and introducing additional environmental constraints that could be exploited by a grasping strategy.
Check out the video below to see the robot grasping simple objects, such as an apple.