Skip to main content
Chrono sims NASA project MobilityBigRocksEarth
August 16, 2022

NSF grant supports robotics and computer simulation with rural Wisconsin high school students

Written By: Caitlin Scott

Departments:

Categories:

Dan Negrut
Dan Negrut

Mechanical Engineering Professor Dan Negrut is leading a new $2.5 million NSF project to produce open source software that allows researchers to use computer simulation to design better rovers, bio-inspired robots, and other autonomous agents.

Collaborative Research: Frameworks: Simulating Autonomous Agents and the Human-Autonomous Agent Interaction is a collaboration with Carnegie Mellon, Johns Hopkins University, Georgia Tech, University of Iowa, and New Jersey Institute of Technology. The $2.5 million award will fund three years of work, with $1.875 million staying at UW-Madison. Dan Negrut is the Principal Investigator and his ME colleagues Radu Serban and Xiangru Xu are co-investigators on the project.

Negrut and Serban are two of the three technical leads on Project Chrono and this new NSF project enhances the Chrono computer simulation platform in transformative ways. Chrono is a physics-based computer simulation infrastructure based on a platform-independent (Linux, Windows, MacOS) open-source design. Chrono’s purpose is to predict through simulation the interplay between mechatronic systems, the environment they operate in, and humans with whom they might interact. The platform is intended to test via computer simulation hypotheses that would be too dangerous, difficult, or costly to verify through physical experiments. For example, Chrono is being used to help engineers with the design of the VIPER lunar rover for its 2023 mission to the moon.

Discovery and innovation are fueled by data. Most of this data comes from physical experiments – somebody building a prototype of a car, testing the new prototype, changing the design and testing it again, etc. This NSF project seeks to increase the share of this data that is produced by simulation, i.e., using the previous example, testing the prototype in simulation, without having to build many prototypes in reality. To that end, with this NSF project a multi-disciplinary team of 40 researchers will augment, validate, and use Chrono to empower research in autonomous agents (AAs). The AAs operate in complex and unstructured dynamic environments and might engage in two-way interaction with humans or other AAs. This project will also enable Chrono to generate machine learning and Artificial Intelligence training data quickly and inexpensively; facilitate comparison of competing designs for assessing trade-offs; and gauge candidate design robustness via testing in simulation of corner-case scenarios. These tasks are accomplished by upgrading and extending Chrono to leverage multiple recent computational dynamics innovations, including a new way of simulating the deformation of the lunar terrain, a scalable multi-agent framework that enables geographically-distributed, over the Internet, real-time simulation of human-AA interaction and much more.

The educational impact of this project is threefold: training undergraduate, graduate, and post-doctoral students in a multi-disciplinary fashion that emphasizes advanced computing skills development; anchoring two new courses in autonomous vehicle control and simulation in robotics; and broadening participation in computing through a residential program on the campus of the University of Wisconsin-Madison that engages teachers and students from rural high-schools.

The outreach component of the project started coming together when ME Department Chair Darryl Thelen and others visited Waunakee High School in June 2021. Negrut connected with high school leadership – including ME alumnus Jack Heinemann – around the idea of collaborating with Waunakee and similar rural Wisconsin high schools on the residential computing program. Under this project, Negrut, Xu, and two teachers from Waunakee High School will develop material that can be used by other teachers from rural high schools in training students in computer simulation and robotics related topics. Additionally, eight to ten teacher-students groups (one teacher and two to three students) from rural Wisconsin high-schools will spend one week in Negrut’s lab at UW-Madison during the 2023, 2024, and 2025 summer breaks. They will gain hands-on experience and learn more about robotics, engineering, and computational science via campus lab visits and interaction with other university researchers.

Viper rovers lunar simulation
VIPER lunar rovers bulldozing simulation, images provided by SBEL.