Survey and Tutorial on Hybrid Human-Artificial Intelligence

Abstract

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.

Bibliometric Analysis of Computational and Mathematical Models of Innovation and Technology in Business

“…Moreover, with the explosive rise of artificial intelligence (AI), further study and empirical analysis of these technologies are required [107]. Mathematicians are fundamental models in this context, as they allow the development of hybrid models that combine the participation of humans and machines.…”

Autonomous Navigation by Mobile Robot with Sensor Fusion Based on Deep Reinforcement Learning

“…where S i,t is the distance score obtained based on the current position of the robot and the candidate navigation point, calculated as shown in Equation (6). D(c i , u) is the Euclidean distance from the candidate navigation point to the global target point, calculated as shown in Equation (7).…”

“…With the application of deep reinforcement learning in robotics, its precise decision-making ability makes it a viable option for autonomous navigation. By employing deep reinforcement learning algorithms to simulate human characteristics and intelligence [ 6 ], robots are endowed with the ability to learn action policies based on the current environmental state, enabling effective navigation even in unknown environments after training in diverse environments [ 7 ]. This makes deep reinforcement learning particularly suitable for the autonomous navigation tasks of mobile robots.…”

FPGA: The super chip in the age of artificial intelligence

“…Redesigning this chip will consume a lot of cost, workforce, and time. Therefore, to solve this problem, technicians designed a general-purpose chip, using its basic logic gates to rearrange and combine to realize different chip functions [1]. This is the original idea of FPGA birth.…”