Survey and Tutorial on Hybrid Human-Artificial Intelligence

The growing computing power,easy acquisition of large-scale data,and constantly improved algorithms have led to a new wave of artificial intelligence(AI)applications,which change the ways we live,manufacture,and do business.Along with this development,a rising concern is the relationship between AI and human intelligence,namely,whether AI systems may one day overtake,manipulate,or replace humans.In this paper,we introduce a novel concept named hybrid human-artificial intelligence(H-AI),which fuses human abilities and AI capabilities into a unified entity.It presents a challenging yet promising research direction that prompts secure and trusted AI innovations while keeping humans in the loop for effective control.We scientifically define the concept of H-AI and propose an evolution road map for the development of AI toward H-AI.We then examine the key underpinning techniques of H-AI,such as user profile modeling,cognitive computing,and human-in-the-loop machine learning.Afterward,we discuss H-AI’s potential applications in the area of smart homes,intelligent medicine,smart transportation,and smart manufacturing.Finally,we conduct a critical analysis of current challenges and open gaps in H-AI,upon which we elaborate on future research issues and directions.