Developing Simulation Tools with an Eye Towards Designing Robots and Autonomous Vehicles
Speaker: Dan Negrut, University of Wisconsin-Madison
Location: 60 Fifth Avenue C15
Date: January 17, 2023, 1 p.m.
Host: Daniele Panozzo
This talk is using computer simulation to design robots and autonomous vehicles, and is inspired by the following vision. One can design an autonomous robot by experimenting with control policies, perception algorithms, and state estimators that look promising. Alternatively, to design the brain of the robot, one can take a model of the robot and test through simulation the promising perception, planning, and control algorithms. The algorithms of choice are subsequently deployed on the actual robots.
On paper, the simulation route is great – it cuts costs, it is fast, thorough, and safe. Sometimes, it is the only feasible alternative. However, designs synthesized in simulation often fail to transfer to the actual robot, a manifestation of the so-called sim-to-real gap. This talk dwells on two things: (i) an open source software infrastructure called Chrono, which we develop and use to simulate the robot, the sensors on the robot, and the virtual world in which the robot/autonomous vehicle operates; and (ii) how to factor in the human component, to understand the human-robot and/or human-automation interplay.
Dan Negrut received his Mechanical Engineering Ph.D. in 1998 from the University of Iowa. He spent six years working as a software developer in Ann Arbor, Michigan. In 2004 he served as an Adjunct Assistant Professor in the Department of Mathematics at the University of Michigan, Ann Arbor. He spent 2005 as a Visiting Scientist at Argonne National Laboratory in the Mathematics and Computer Science Division. At the end of 2005 Dan joined the Mechanical Engineering faculty at the University of Wisconsin-Madison. His interests are in Computational Science and he leads the Simulation-Based Engineering Lab (http://sbel.wisc.edu). Lab sponsors include National Science Foundation, NASA, US Army Research Office, Department of Transportation, and NIOSH. The lab’s projects focus on
high performance computing, computational dynamics, terramechanics, simulation-in-robotics, traffic simulation, and fluid-solid interaction problems. Dan received a National Science Foundation Career Award in 2009. Since 2010 he has been an NVIDIA CUDA Fellow. He is one of the technical leads of Project Chrono, an open source multi-physics simulation platform (http://www.projectchrono.org/).
In-person attendance only available to those with active NYU ID cards.