The New Wave in Robot GraspingKen GOLDBERG, Professor, UC Berkeley |
Abstract:
Despite 50 years of research, robots remain remarkably clumsy, limiting their reliability for warehouse order fulfillment, robot-assisted surgery, and home decluttering. The First Wave of grasping research is purely analytical, applying variations of screw theory to exact knowledge of pose, shape, and contact mechanics. The Second Wave is purely empirical: end-to-end hyperparametric function approximation (aka Deep Learning) based on human demonstrations or time-consuming self-exploration. A "New Wave" of research considers hybrid methods that combine analytic models with stochastic sampling and Deep Learning models. I'll present this history with new results from our lab on grasping diverse and previously-unknown objects and discuss exciting future research including cloud and fog robotics.
Biography:
Ken Goldberg is an artist, inventor, and roboticist. He is William S. Floyd Jr Distinguished Chair in Engineering at UC Berkeley and Chief Scientist at Ambidextrous Robotics. Ken is on the Editorial Board of the journal Science Robotics, served as Chair of the Industrial Engineering and Operations Research Department, and co-founded the IEEE Transactions on Automation Science and Engineering. Short documentary films he co-wrote were selected for Sundance and one was nominated for an Emmy Award. Ken and his students have published 300 peer-reviewed papers, 9 US patents, and created award-winning artworks featured in 70 exhibits worldwide.
Digital Manufacturing on a Shoestring: Low Cost Digital Solutions for SMEsDuncan MCFARLANE, Professor, University of Cambridge |
Abstract:
One of the key findings in a number of recent studies has been that small and medium sized manufacturers (SMEs) have been slow in adopting digital solutions within their organisations. Cost is understood to be one of the key barriers to adoption and many companies cannot afford a major overhaul of their IT infrastructure in order to prepare for future digital solutions.
Digital Manufacturing on a Shoestring is an approach to increasing the digital capabilities of SMEs via a series of low cost solutions. The programme proposes using off-the-shelf, (possibly non-industrial) components and software to address a company's (digital) solution needs, adding capabilities one step at a time with minimal a priori infrastructure required. A modular approach using building-blocks with standardised interfaces is used to ensure solutions developed are reusable, and a service oriented architecture used to ensure solutions incrementally integrate.
This presentation will introduce the Digital Manufacturing on a Shoestring programme. It will present the outcomes from a wide range of industrial workshops which have yielded digital solution priorities for UK manufacturing SMEs. It will discuss challenges associated with integrating low cost technologies into industrial solutions and the style of IT architectures best suited for integrating such solutions into industrial environments.
Biography:
Duncan McFarlane is Professor of Industrial Information Engineering at the University of Cambridge, Deputy Head of the Institute for Manufacturing, Head of Distributed Information & Automation Lab, Chairman of Redbite Solutions Ltd, visiting Professorial Fellow at University of Melbourne and Fellow of St John's College. He has been involved in the design and operation of industrial automation and information systems for twenty five years. His research work has been in distributed, intelligent industrial automation, reconfigurable control systems, resilient control, RFID integration, track and trace systems, IoT and valuing industrial information. In 1993 he was a founding member of the Holonic Manufacturing Systems consortium examining the role of distributed AI in manufacturing control for the first time. Since 2000 he has been Director of the Auto ID Centre [2000-3] and Auto ID Labs [2003- present] - a programme which has led to the origins of ideas such as Internet of Things and Product Intelligence. He is founder and Chairman of RedBite Solutions Ltd - an industrial RFID and track & trace and IoT based asset management solutions company. He leads the Cambridge - Boeing research partnership. He leads the Digital Manufacturing Programme at Cambridge, is currently part of the UK Digital For Industry D4I steering group. He is a member of the Management Board of the Centre for Digital Build Britain and is Principal Investigator on the Digital Manufacturing on a Shoestring programme examining low cost digital solutions for small.