Applications of Computing in Industry : Lecture

Ocado is an award winning online retailer that is revolutionising the way people buy their groceries. Ocado has no shops. Instead customers place their orders on the Ocado website or mobile platforms and these are then picked and packed in a huge automated warehouse (the largest of its kind in the world), from where they are then delivered to customers around the country within one hour slots.

Operating such a business with the scalability, efficiency and consistency that Ocado achieves requires some very sophisticated and innovative IT systems, all of which are developed in-house by its IT division, Ocado Technology. This talk explores some of the technology that Ocado has had to develop to run such a business successfully, and describes some work on a new piece of Ocado technology which uses 3D vision to get robots to pack customer orders.

Graham holds a B.Sc. in Engineering Science (Electrical) from Warwick University, an M.Eng. in Control Systems from Sheffield University, an M.A. in Philosophy of Mind from Hull University and a PhD in Artificial Intelligence from Edinburgh University.

After lecturing in Robotics and Mechatronics at the University of Surrey he worked on bespoke applications of sensor-guided robots in the automotive industry, spent some time at the BBC Research Labs working on the synthesis of novel views from multiple concurrent images, was part of a team that developed a robot to assist neurosurgeons, managed a team maintaining a number plate recognition system, and was technical lead for a start-up company (based at Imperial College Business Incubator) looking at using robots to fold sheet metal.

Graham joined Ocado in September 2010 as the Robotics Research Team Leader and was given the task of getting a robotics research team together, sorting out an environment for them to work in, and leading them to get robots to pack shopping.

Ose joined Ocado in March 2011 as the second member of its three-member Robotics Research Team. He has worked on systems for: calibrating and measuring the accuracy of depth-sensing cameras (like Microsoft's Kinect); calibrating the positions and orientations of cameras relative to robots; building 3D models of products, and registering (i.e. aligning) these models to 3D point clouds to guide robot pickers.

Prior to joining Ocado, he graduated from Imperial with a Master's in Computing in 2006, after which he did a PhD in Medical Imaging in Prof. Daniel Rueckert's Biomedical Image Analysis Group, which he completed in 2011.