Students in CAV course (CE597)

The course is led by Samuel Labi, professor, and Sikai Chen, postdoctoral research fellow, both in CE and researchers in the Center for Connected and Automated Transportation (CCAT).

CE597, Machine Learning and Artificial Intelligence for Autonomous Vehicle Operations II, was first offered during the Fall 2020 semester. The use of ML/AI techniques in the course is motivated by the limitations of the traditional procedures in modeling and solving complex and intractable problems that involve big data; require more efficient use of computing resources; or need solutions that are more robust, efficient and effective. With the advancements in ML/AI, autonomous vehicle systems continue to develop rapidly and are expected to be deployed on public roads in the not-too-distant future.

It is expected that autonomous vehicles (AVs) will be one of the disruptive technologies in the modern era. With a set of reliable enabling technologies including AI, AVs can significantly improve safety, mobility, energy efficiency, and socio-economic and environmental benefits associated with transportation systems of the future.

“The engineers of tomorrow must learn to adapt quickly to the vicissitudes of the times. Social, economic and technological changes constantly create new demands, not only on engineers but also on the educational systems that produce them,” Labi said. “Therefore, it is imperative that engineers cultivate the skills to develop sustainable and resilient solutions, based not only on reasoned analyses of the present situation but also on visions of a better tomorrow.”

Students who complete the course will be equipped with fundamental concepts of ML algorithms, general AI, and applications in AV operations. The course consists of instructor presentations, algorithm demonstrations, student presentations, group discussions, and guest speakers. In addition, the course discusses and demonstrates successful applications of algorithms in the context of AV operations.

The course aligns with Purdue’s Integrative Data Science Initiative, which is designed to build on and advance the University’s existing strengths to position it as a leader at the forefront of advancing data science-enabled research and education. The initiative does so by tightly coupling theory, discovery and applications while providing students with an integrated, data science-fluent campus ecosystem.

For more on the Purdue Engineering Initiative in Autonomous and Connected Systems: https://engineering.purdue.edu/Initiatives/AutoSystems