Skip to main content Skip to navigation
School of Mechanical and Materials Engineering SUMMER SEMINAR SERIES (5-18-2020)

Dr. Mohammadreza Radmanesh, Robotics Researcher at NASA Jet Propulsion Laboratory

Mohammadreza-Radmanesh

Thursday, May 18th, 2020
11:00 am to Noon

Location: https://wsu.zoom.us/s/94687243100

Abstract

Despite the incredible success stories from robotics in the last few years, many of our best autonomy capabilities such as planning and control algorithms and Simultaneous Localization and Mapping (SLAM) are still far from transitioning out of the research lab and into the real world. Fielding a UGV or flying a UAV at high speeds through a cluttered environment requires reliable perception and online planning in novel environments to deal with uncertainty from perception, imperfect actuators, and model errors. This talk will present recent work in developing integrated frameworks that exploit methods from logical reasoning, formal synthesis, Machine Learning (ML), and robotics to produce solutions and ultimately enable autonomy where robots perform complex tasks together. Specifically, this talk focuses on the development of algorithms for uncertain dynamical systems with a special interest in resilient cooperative control of networked multi‐vehicle systems and sensory‐driven SLAM algorithm. The developed architectures are deployed on the ground and aerial robotics and autonomous vehicles operating in GPS‐denied uncertain environments and subject to multiple constraints.

Biography

Reza Radmanesh received his Ph.D. degree in Mechanical Engineering from the University of Cincinnati in 2019. He is currently a robotic researcher at NASA Jet Propulsion Laboratory (JPL) and before this position, he was a Postdoctoral Research Fellow at the Department of Aerospace Engineering at the University of Michigan, Ann Arbor. His research interests mainly lie within the field of control and robotics with an emphasis on distributed control of networked multi‐agent systems, cooperative control, SLAM and Machine Learning.