Product managers, engineering leads and strategic planners currently employed by automotive OEMs and Tier 1 suppliers who want to: 

• Shape technology roadmaps: Drive long-term product and innovation strategies.
• Bridge teams: Build a common language with engineering for better collaboration.
• Manage risk: Anticipate and mitigate challenges in AV development.

Weisong Shi
Weisong Shi is an alumni distinguished professor and chair of the Department of Computer and Information Sciences at the University of Delaware, where he leads the Connected and Autonomous Research (CAR) Lab. A leading expert in edge computing and autonomous driving, his seminal paper on edge computing has over 7,500 citations. He previously served as NSF program director and held leadership roles at Wayne State University. Shi is editor-in-chief of IEEE Internet Computing, founding chair of major conferences on edge computing and connected health, and general chair of ACM MobiCom 2024. He is an IEEE Fellow and ACM Distinguished Scientist.

William He
William He is a fifth-year doctoral candidate in computer science at the University of Delaware, working in the Connected and Autonomous Research (CAR) Lab under Weisong Shi. His research focuses on building safe and reliable machine learning and simulation environments for autonomous vehicles and mobile robots. He has collaborated with leading organizations, including Autoware, Ford, Western Digital, Blue Halo, Leidos, the Federal Highway Administration and Oak Ridge National Laboratory.

Week 1: Introduction to autonomous vehicles

History, SAE autonomy levels, industry landscape, pivotal moments in AV development. Who are the leading players in the field? How much have autonomous vehicles progressed through the past five decades? 

Week 2: Sensors and hardware

Overview of sensor types (cameras, LiDAR, radar), how AV hardware is selected and integrated.

Week 3: Perception and scene understanding

Computer vision, environmental modeling, object detection/tracking, AI limitations.

Week 4: Mapping and localization

High-definition mapping, SLAM, localization strategies, operational design domain (ODD).

Week 5: Planning, prediction and behavior

Trajectory and motion planning, prediction models, social and ethical implications.

Week 6: Control and system integration

Vehicle dynamics and control algorithms, AV stack integration, reliability.

Week 7: Safety, verification and validation

Safety standards (ISO 26262, SOTIF), validation methods, simulation/testing approaches

Week 8: Cybersecurity and data privacy

AV cybersecurity threats, data privacy, safeguards for connected vehicles

Week 9: Regulation, ethics and trust

Global regulation, legal frameworks, public trust, ethics in AV deployment. (Guest Speaker)

Week 10: AV business and future directions

Business models, market entry, deployment barriers, trends, long-term outlook. (Guest Speaker)

• Develop a robust, technology-neutral understanding of the autonomous vehicle ecosystem, including sensors, perception, decision-making and system integration.
• Identify the major technical, safety, cybersecurity and regulatory problems faced by AV developers and OEMs.
• Evaluate emerging methods and industry best practices for solving key challenges in hardware, software and business strategy.
• Analyze the non-technical factors (public trust, legal, regulatory and ethical) critical for widespread AV adoption.
• Articulate weekly core learnings and open questions to support continual improvement and exchange within a networked cohort of OEM leaders.

This program uses a pass/fail grading system, prioritizing the strategic application of knowledge over rote memorization.

To earn a digital badge, participants must complete a final capstone project or presentation that demonstrates their understanding of the implications of autonomous vehicle (AV) technologies on various business models and development lifecycles.

Capstone project: Participants may choose to implement an AV or Advanced Driver Assistance System (ADAS) function within the provided simulation environment. Examples may include advanced lane-keeping, traffic light detection or comparable applications.

Final presentation:
Participants may opt to deliver a comprehensive summary of course insights, paired with a reflective discussion on broader societal implications — such as how fully automated transportation could reshape work, leisure and urban life. 

Access to simulation software and software environment will be provided.

Hardware is not provided. Hardware requirements to run projects (not mandatory): Windows 10 or higher, or Linux Ubuntu 18.04 or higher, at least 16 GB of RAM, RTX 2060 or newer.