Robust Planning and Decision-making for Safe Legged Locomotion

Guest Speaker:
Ye Zhao – Georgia Tech

Wednesday, February 3rd, 2021
Zoom Webinar Link
2:00pm – 3:00pm

Webinar Link:
https://usc.zoom.us/webinar/register/WN_Qk4-7AthThudso7LXs2OiAn

Abstract: Our society has witnessed the advancement of legged locomotion autonomy and mobility, but they have not become prevalent as autonomous driving and wheeled robot mobility. One crux is the lack of robust, scalable, and real-time planning and decision-making algorithms for these highly complex legged machines with contact-rich behaviors. To address this issue, symbolic planning, logic- based formal method, and distributed optimization are promising yet underexplored for locomotion problems. This talk will present three unique perspectives to quantify uncertainties and reason about robustness in task and motion planning algorithms for highly dynamic legged locomotion. I will start with temporal-logic-based reactive motion planning for whole-body dynamic locomotion in constrained environments and propose robust metrics to enable resilient contact decisions. Following this direction, I will present our recent task planning framework with belief tracking for safe locomotion in partially observable environments. In the end, I will talk about contact-aware trajectory optimization methods that parameterize terrain uncertainties for robust cost design to enhance risk-sensitive locomotion performance.

Biography: Ye Zhao is an Assistant Professor at The George W. Woodruff School of Mechanical Engineering, Georgia Institute of Technology. He works on planning and decision-making algorithms of highly dynamic and contact-rich robots. He is especially interested in challenging locomotion and manipulation problems with formal guarantees on robustness and autonomy. He was a Postdoctoral Fellow at Harvard University, and received his Ph.D. degree in Mechanical Engineering from The University of Texas at Austin in 2016. At Georgia Tech, he leads the Laboratory for Intelligent Decision and Autonomous Robots (LIDAR) (http://lab-idar.gatech.edu/). He is also affiliated with the Institute for Robotics and Intelligent Machines (IRIM) and the Decision and Control Laboratory (DCL).

—

Hosts: Feifei Qian and Pierluigi Nuzzo 

Center for Cyber-Physical Systems and the Internet of Things (CCI) http://cci.usc.edu
Ming Hsieh Institute for Electrical and Computer Engineering (MHI) http://mhi.usc.edu

–>