Ocado, the world’s largest online-only supermarket, has been evaluating the feasibility of robotic picking and packing of shopping orders in its highly-automated warehouses through the SoMa project, a Horizon 2020 framework programme for research and innovation funded by the European Union.
SoMa is a collaborative research project 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 of robotic manipulation has been the handling of easily damageable and unpredictably shaped objects such as fruit and vegetable groceries. These products have unique shapes and should be handled in a way that does not cause damage or bruising. To avoid damaging sensitive items, the project uses a compliant gripper (i.e. one that possesses spring-like properties) in conjunction with an industrial robot arm.
The variation in shape of the target objects imposes another set of constraints on the design of a suitable gripper. The gripper must be sufficiently versatile to pick a wide variety of products, including Ocado’s current range which includes over 48,000 hypermarket items.
The SoMa project (EU Horizon 2020 GA 645599) aims to design compliant robotic hands that are suitable for handling fragile objects without much detailed knowledge of an item’s shape; in addition, the robotic arms should also be capable of exploiting environmental constraints (physical constraints imposed by the environment). The goal is to develop versatile, robust, cost-effective, and safe robotic grasping and manipulation capabilities.
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.
We designed a set of experiments to evaluate grasping performance on an example set of artificial fruit stored in an IFCO (International Fruit Container) tray. The adopted strategies attempted to exploit environmental constraints (e.g. the walls and the bottom of the tray) to perform the gripping tasks successfully,.
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.
Graham Deacon, Robotics Research Team Leader
Graham Deacon January 31st, 2017
Posted In: Blog
The e-commerce market has been the growth engine of the retail environment, experiencing a 15% increase for grocery sales in 2015. One of the major challenges facing retailers is the ability to keep up with the fast growing demand coming from the online channels. This creates additional pressure on retail warehouses to find more qualified staff, whether for picking and delivering orders or for maintaining and expanding the existing warehousing infrastructure in a scalable way.
However, a recent GOV.UK survey showed that a growing number of jobs are being left unfilled because companies can’t find the right people with the appropriate skills. In addition, UK productivity on the whole has flatlined since 2008, a concerning trend given how other countries have dramatically improved theirs.
One solution to the challenges presented above is the adoption of robots working alongside human workers inside the warehouse to boost productivity, satisfy customer demand for fast delivery times, and reduce picking times. In the UK, Ocado has been a pioneer in the use of robotics and automation alongside its human workforce.
We are a net employer of 11,000 staff, but also create advanced hardware systems that help us maintain a very efficient operation. This in turn enables us to provide additional jobs and other employment opportunities, none of which would be possible without the technology we’ve developed.
Ocado Technology has been one of the first companies to realize the positive impact of advanced robotics in the e-commerce market. In addition to creating a hive system for our Ocado Smart Platform, we’ve also partnered with several universities on two robotics-related projects funded by the European Union: SecondHands and SoMa.
The SecondHands project is interesting not only from the perspective of what we will learn along the way, but also because we plan to build many highly automated CFCs worldwide (for Ocado and its OSP customers). Therefore, the SecondHands robots would help us maintain the CFCs, and ultimately help automate their construction too.
While SecondHands focuses on designing a robot assistant for industrial maintenance tasks, SoMa is exploring the utility of strategies that embody a soft manipulation approach. Typically this entails using a robotic hand that exhibits controllable compliant (i.e. spring-like) behaviour.
Given that Ocado offers over 48,000 different items on our store that vary in size, shape, weight and span from rigid to highly deformable, the SoMa robotics teams must solve many unique challenges in addition to the classical robotic manipulator problems.
Recently, the team has been working on a benchmark framework for the evaluation of soft manipulation systems used for commercial purposes. The framework takes into account several key attributes and assumptions, including the asymmetric and deformable nature of the item to be picked and the damage-free handling of the product or packaging.
Performance-wise, a successful grasp in the Ocado use case refers to robustness (i.e. a secure and reliable grasp), a low level of damage or bruising observed, and a short pick-and-place cycle time.
The benchmark framework was recently presented at a workshop (part of the International Conference on Intelligent Robots and Systems held in South Korea) to a large audience of robotics experts from around the world.
The presentation was titled “Systematic evaluation of compliant under-actuated soft manipulators in an industrial context – the Ocado use case” and included a description of the software and hardware setup being used to test several hypotheses concerning the efficacy of various pre- and post-grasping strategies employed with robot hands that are consistent with the soft manipulation paradigm.
Alex Voica, Technology Communications Manager
Alex Voica October 26th, 2016
Posted In: Blog
Recently we kicked off an exciting project to develop an autonomous humanoid robot. It will use artificial intelligence, machine learning and advanced vision systems to understand what human workers want, in order to offer assistance.
For example, it will be able to hand tools to maintenance technicians, and manipulate objects like ladders, pneumatic cylinders and bolts.
The ultimate aim is for humans to end up relying on collaborative robots because they have become an active participant in their daily tasks. In essence, the robot will know what to do, when to do it, and do it in a manner that a human can depend on.
The project is called SecondHands as it will literally provide a second pair of hands, and is part of the European Union’s Horizon 2020 Research and Innovation programme. We are leading the research, working with four other European institutions.
The tasks our robot will carry out will increase safety and efficiency, and require us to focus on key areas of robotics including:
Proactive assistance – the robot will have cognitive and perceptive ability to understand when and what help its operator needs, and then to provide it.
Artificial intelligence – to anticipate the needs of its operator and execute tasks without prompting, the robot will need to progressively acquire skills and knowledge.
3D perception – advanced 3D vision systems will allow the robot to estimate the 3D articulated pose of humans.
Humanoid form and flexibility – SecondHands will feature an active sensor head, two redundant torque controlled arms, two anthropomorphic hands, a bendable and extendable torso, and a wheeled mobile platform.
For more information, see the project’s website.
Dr Graham Deacon
Robotics Research Team Leader
UPDATE: If you think that sounds interesting, we’re looking for a talented Robotics Research Software Engineer to join the team. Take a look at the role now.
Graham Deacon July 1st, 2015
Posted In: Blog