A New Class of Industrial Robot

Dertouzos Lecturer Series 2012/2013
A New Class of Industrial Robot
Speaker: Rodney Brooks
Speaker Affiliation: Chairman & CTO, Rethink Robotics, Inc.
Host: Daniela Rus
Host Affiliation: CSAIL

Date: 12-13-2012
Time: 4:15 PM - 5:30 PM
Refreshments: 4:00 PM
Location: 34-101

Abstract:
Rethink Robotics (http://www.rethinkrobotics.com/) has been developing a new class of industrial robot for the  last four years. They first announced the robot on September 18th, and shipping it to small US manufacturers in late 2012/early 2013.  Its total cost of ownership is an order of magnitude cheaper than a conventional industrial  robot, its integration time is under two hours, and it can easily be retrained to do new tasks by factory line workers, without they themselves requiring any special training on how to operate the robot.  It is safe to work with collaboratively, and it has a very low barrier to entry for companies that have not previously had automation equipment.  It is made in the USA, and our goal is for it to make American workers even more productive than they already are, so that US manufacturing of low cost goods can be competitive with other regions.

Bio:
Rodney Brooks is the Panasonic Professor of Robotics (emeritus) at MIT, and the Founder, Chairman and CTO of Rethink Robotics.  Previously he was Director of MIT CSAIL until 2007, and Co-founder, sometimes Chairman, and CTO of iRobot  from 1990 to 2008.  He had 27 fabulous PhD students at Stanford and MIT, and has managed to have fun building robots for most of his life.

Signal Processing for Graphs

Speaker: Ben Miller
Speaker Affiliation: MIT Lincoln Laboratory
Host: Polina Golland
Host Affiliation: MIT CSAIL

Date: 12-11-2012
Time: 4:00 PM - 5:30 PM
Location: 32D-463 (Star)

In numerous applications, detection of a small subset of nodes in a network is a problem of significant interest. While detection theory provides a framework that enables analysis of the detectability of small anomalies in large networks, the combinatorial nature of graphs—the common mathematical object for network representation—complicates the application of detection theory, requiring NP-hard problems to be solved for optimal detection. This presentation outlines Lincoln Laboratory’s Signal Processing for Graphs effort, which aims to create a  computationally tractable framework for anomalous subgraph detection. The framework uses a regression-based residuals analysis, leveraging tools from community detection for the problem of detecting small anomalies. Issues of parameter estimation and fitting the data  to a given model are discussed, and a processing chain for detection in graph data is presented. The processing chain uses several detection statistics, which improve in detection performance as the increase in computational  complexity. Temporal dynamics are also incorporated into  the chain, enabling detection that would not be possible by considering a static graph, as we demonstrate on both simulated and application data.