[Colloq] Talk - Scott Kuindersma - Feb 5th 3:15pm 108 WVH - Real-time optimization algorithms for dynamic walking, running, and manipulating robots

[Biron, Jessica]

Scott Kuindersma

Thursday, February 5th, 3:15pm
108 WVH

Title: Real-time optimization algorithms for dynamic walking, running, and manipulating robots

Abstract: The worlds largest technology companies and science funding agencies are investing heavily in robotics. They anticipate robots that perform work as first responders, efficiently explore the surfaces of planets, and streamline product manufacturing and delivery. However, despite the existence of incredibly capable hardware, the limitations of our best software for controlling and analyzing complex systems prevents us from unleashing these robots into the wild.

In this talk, I will describe my research on designing optimization algorithms that improve our ability to control dynamic motions in complex robots. I will present my work developing convex optimization-based controllers for whole-body locomotion and their application to Atlas, a full-scale hydraulic humanoid robot. I will also discuss results from my work developing statistical optimization algorithms for performing risk-sensitive policy search on robots that recover from impacts and manipulate dynamic objects. I will conclude with directions for future research, including adaptive and robust control for low-precision robots and achieving highly dynamic, versatile, and energy-efficient behaviors legged systems.

Bio: Scott Kuindersma is a Postdoctoral Associate in the Robot Locomotion Group at MIT CSAIL. He received his PhD in Computer Science from the University of Massachusetts Amherst in 2012 where he was also a Graduate Research Fellow with NASA Johnson Space Center. His research interests broadly encompass legged robotics, optimization, control, nonlinear systems, and machine learning. He has designed and implemented control algorithms for several state-of-the-art robots including the UMass uBot, NASA's Robonaut 2, and Boston Dynamics' Atlas. Currently, he is the Planning and Control Lead for MIT's DARPA Robotics Challenge team.