VERTICAL - AI in Transportation/Aerospace


AI in vision systems and imaging, decision making, autonomous command and control, prediction of dynamic traffic and road conditions, vehicle design, routing, scheduling and maintenance, among others leading to improved safety, efficiency, and decision making throughout transportation systems.



Modern growing, dynamic, global transportation systems benefit from many uses of AI. Latest advances in vision systems alone have led to rapid development in autonomous surface- and air-based vehicles, traffic and pedestrian detection and avoidance, automated license plate recognition, and improved means to monitor driver performance and safety. At larger scales AI can be used to understand and predict traffic flows, to help re-distribute flows in optimal ways in light of incidents that may arise, help with the monitoring of road conditions, etc. “Smart cities” are now embedding these technologies in the transportation grids to improve the safety of everyone using the system. AI has the opportunity of revolutionizing the transportation of goods through autonomous trucks, ships, and aircraft. Within aerospace, AI has additional utility from the design optimization of new aircraft to the development of autonomous air taxis, to the optimized routing of aerial vehicles in crowded urban environments, to long-endurance space missions where AI is required to perform smart decision-making in real-time perhaps even without the ability for pre-confirmation from Earth-bound human controllers. AI can also play an important role in prognostics for maintenance of jet turbines, for the optimal routing of vehicles with simultaneous sensor allocation, and so forth.


  • AI in Vehicle Design, to improve efficiency and minimize energy requirements in a wide range of environments, design techniques for improving computational efficiency, managing uncertainty, and understanding relationships in complex systems through the application of AI.
  • AI for Transportation and Vehicle Autonomy, to convey information from sensors for real-time autonomous control of land, sea, air, and space vehicles including environments where communications between autonomous systems and human operators may or may not be denied, or to improve perception in challenging conditions or for instance provide assisted driving in hybrid driver-vehicle interaction.
  • AI for Routing and Scheduling, to optimize path planning and logistics of individual vehicles, small fleets or entire city or national transportation grids, towards the minimization of supply chain and delivery disruptions despite unanticipated dynamics.
  • The challenges of regulatory guidance around AI in transportation, including hybrid autonomous and human-operated “platoon” transportation systems or deployment of tracking systems.
  • AI for Maintenance, specifically within Transportation Systems, highlighting diagnostic and prognostic models capable of identifying faults in advance of failures, improving safety and decreasing overall costs for consumers.
  • AI in Ride Sharing, to match drivers to passengers, to forecast supply and demand, for optimal price strategies and overall improved logistics.
  • AI for Urban Mobility, either through improved design of smart cities through improved transportation grids, traffic management systems, or novel use cases such as through aerial taxis.
  • AI for Swarming, including strategies for centralized or decentralized control of large numbers of unmanned vehicles simultaneously as individuals or teams, or as hybrid man-machine partnerships to complete mission objectives.


Eric Bechhoefer (Green Power Monitoring Systems)

Mariagrazia Dotoli (Politecnico di Bari, Italy)

Gary Fogel (Natural Selection, Inc.)

Nikunj C. Oza (NASA Ames)

Karen Panetta (Tufts University)

Christopher Silva (NASA Ames)

Adrian Stoica (NASA JPL)

Liang Tang (General Electric)

Kanishka Tyagi (Aptiv)

Huafeng Yu (Boeing)