Optimization for Robotics through Co-Design

Speaker

Brian Plancher
Assistant Professor, Computer Science Department at Barnard College, Columbia University.

Title

"Optimization for Robotics through Co-Design"

Abstract

Many promising robotics algorithms are computationally intensive, making real-time us on edge robotic hardware challenging. This constrains the adaptability of current robotics software stacks and hampers their application in real-world scenarios. In this talk, I will discuss how our lab is addressing these challenges through algorithm-hardware-software co-design, generating new algorithms and implementations that can run at real-time rates. Specifically, I will show how the performance of nonlinear model predictive control (MPC) algorithms can be significantly enhanced through a combination of parallelism, approximation, numerical conditioning, and structure exploitation.

By leveraging theoretical advancements and custom parallel implementations of rigid body dynamics and linear system solvers on GPUs, our lab has enabled whole-body nonlinear MPC for manipulators at kHz rates over long-horizon trajectories, while sustaining high speed for robotics-scale batches of solves.

About Speaker

Brian Plancher is an Assistant Professor of Computer Science at Barnard College, Columbia University where he leads the Accessible and Accelerated Robotics Lab. He holds affiliate positions in the Department of Computer Science and Electrical Engineering at the Fu Foundation School of Engineering and Applied Science, Columbia University. He is also a co-chair for the Tiny Machine Learning Open Education Initiative (TinyMLedu) and an associate co-chair for the IEEE-RAS TC on Model Based Optimization for Robotics. His research is focused on developing and implementing open-source algorithms for dynamic motion planning and control of robots by exploiting both the mathematical structure of algorithms and the design of computational platforms.

As such, his research is at the intersection of Robotics and Computer Architecture, Embedded Systems, Numerical Optimization, and Machine Learning. He also wants to improve the accessibility of STEM education and researches ways to better understand and improve diversity, equity, inclusion, and belonging in STEM education globally, as well as designs and teaches new interdisciplinary, project-based, open-access courses that lower the barrier to entry of cutting edge topics like robotics, parallel programming, and embedded machine learning.