Contacting the World with Mechanical and Data-Driven Intelligence
Mechanical Engineering Department
April 11th, 2014
Abstract: Reliable physical interaction is central to many challenges society faces today, and robots must master it to become part of the solution. In my research I study how robots can contribute either through their designs or through their actions.The central idea is to combine the simplicity and reliability of end effectors and control strategies designed to exhibit mechanical intelligence with the realism and accuracy of data-driven models to give robots the necessary skills to expect, understand, and control contact. In the first part of the talk I will describe the role of the shape of a mechanism in producing intelligent behavior, and how attributes such as shape, actuation, or compliance, can be instrumental in the design of effectors like hands that are simpler, cheaper, lighter, and more reliable. In the second part of the talk, instead, I will consider how robots can actively control physical interaction by closing the loop with sensing. Contact leaves a trace of sensor readings from where robots should be able to infer useful information. I will show how we can build accurate probabilistic data-driven models for perception and actuation, in support of planning and monitoring physical interaction, with example applications to general-purpose in-hand manipulation and automated assembly.
Bio: Alberto Rodriguez will join the MIT faculty in July 2014 as an Assistant Professor in the Mechanical Engineering Department. He graduated in Mathematics ('05) and Telecommunication Engineering ('06 with honors) from the Universitat Politecnica de Catalunya (UPC) in Barcelona. He then moved to the United States and earned his PhD in Robotics, "Shape for Contact", in 2013 at Carnegie Mellon University under the supervision of Professor Matthew T. Mason, and is currently a postdoctoral student at the Computer Science and Artificial Intelligence Laboratory at MIT. Alberto is the recipient of La Caixa and Caja Madrid fellowships for graduate studies in the US, and the recipient of the Best Student Paper Awards at conferences RSS 2011 and ICRA 2013. His main research interests are in robotic manipulation, mechanical design, and automation. His long-term research goal is to provide robots with enough sensing, reasoning and acting capabilities to reliably manipulate the environment.
April 11, 2014