The New Wave of Robot Grasping,
Presenting special guest speaker, Ken Goldberg from UC Berkeley AUTOLAB, plus an expert panel including;
Jeff McAlvay from Tempo Automation
Dr Harsha Prahlad from Grabit
Paul Ekas from Sake Robotics
The New Wave in Robot Grasping
Ken Goldberg, UC Berkeley
Despite 50 years of research, robots are still remarkably clumsy. I will present what I see as three "waves" in methodology. The first wave, which is still dominant, uses analytic methods based on screw theory and assumes exact knowledge of pose, shape, and other properties (see the 2016 Handbook of Robotics).
The relatively recent Second Wave is purely empirical: purely data driven approaches which learn grasp strategies from many examples using techniques such as reinforcement learning and hyperparametric function approximation (Deep Learning).
The "New" wave will be hybrid methods that combine analytic models to bootstrap and tune empirical models, where data and code is exchanged via the Cloud using emerging advances in cloud computing, big data, deep learning, and the internet of things. This talk will present an overview and new results from my lab for applications in home decluttering, warehouse order fulfillment, and robot-assisted surgery.
The New Wave of Robot Grasping website
Silicon Valley Robotics