Multi-unmanned system supervision and control station based on MAS

Abstract

The invention provides a multi-unmanned system supervision and control station and method based on MAS. The multi-unmanned system supervision and control station based on the MAS includes a parallel system architecture; the parallel system architecture includes a multi-agent software and hardware supervision and control system and unmanned systems; the multi-agent software and hardware supervisionand control system includes a hardware platform and a software platform; the hardware platform includes a multi-screen workstation; and the multi-screen workstation is provided with a dynamic physiological collection component capable of detecting operator physiological data and dynamic instructions. By using the multi-unmanned system supervision and control station based on the MAS, the real-time working state, environment complexity, task complexity and comprehensive intelligence information of the unmanned system are effectively monitored; the control mode of the unmanned system is calculated according to the environment complexity, the task complexity, the fatigue of the operator, and the autonomous level of the unmanned system, so that the control mode dynamic switching of the unmanned system is realized; and the human-machine hybrid intelligence is formed by a hybrid autonomous mode that is observable, interpretable and predictable, and can be intervened. The multi-unmanned system supervision and control station based on the MAS is applied to the field of supervision and control.

Description

technical field [0001] The invention relates to the field of supervisory control, in particular to an MAS-based multi-unmanned system supervisory control station and method. Background technique [0002] The supervisory control based on multi-agent system (MAS, Multi-AgentSystem) is the key content of human-unmanned collaboration, and it is an effective way to realize complementary advantages and form efficient collaboration. In the new generation of artificial intelligence development plan released in 2017, it is clearly proposed to study basic theories such as "human-in-the-loop" hybrid enhanced intelligence, human-computer intelligence symbiosis behavior enhancement, and develop technologies such as human-computer interaction. In recent years, it has begun to develop from the interactive control of "man-in-the-loop" to the direction of supervisory control of "man-on-the-loop". During the execution of the task, the operator has the final decision-making power, supervising...

AI Technical Summary

Problems solved by technology

[0003] The patent document with the patent number 201610838445.6 provides a multi-modal natural interactive single-operator multi-UAV hybrid active control method. The UAV operator can use the voice control mode, eye movement control mode, and gesture control mode. However, it only solves the operator's state assessment, and does not build a comprehensive supervision that integrates multi-agent monitoring, operator state monitoring, environment complexity and task complexity assessment. control system

Images