Intelligent decision-making method for multiple sensors and multiple targets and storage medium
A multi-sensor, intelligent decision-making technology, applied in the computer field, can solve problems such as poor ability to adapt to environmental changes
Active Publication Date: 2021-06-15
CHINA ACADEMY OF ELECTRONICS & INFORMATION TECH OF CETC
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003]
The invention provides an intelligent decision-making method for multi-sensor and multi-objectives and a computer-readable storage medium to solve the problem in the prior art that the decision-making for multi-sensors and multi-objectives is poor in adapting to environmental changes
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0042]The embodiment of the present invention aims at the problem of poor ability to adapt to environmental changes in the existing multi-sensor and multi-target decision-making, and designs a specific feature expression method, splitting multiple targets into single targets, so as to solve the problem of data dimension changes in the form of vector encoding , it is convenient to build a network and improve the training speed, and the random sampling method is used in the training process, which disrupts the correlation between samples and facilitates convergence. In addition, the present invention uses the reinforcement learning exploration mode to deal with more targets, tasks and larger action spaces, and uses the Q-network containing the state advantage value to replace the real income, and associates the split single target with the whole, so that the action decision-making is more effective. Overall, and the double Q network of the present invention solves the problem of ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses an intelligent decision-making method for multiple sensors and multiple targets and a storage medium; according to the invention, a multi-sensor and multi-target problem is modeled into a reinforcement learning classical model, a feature design and feature coding method is provided for specific scene data, and state expression and action expression are completed. According to the multi-target allocation method based on reinforcement learning, real-time decision making of a learning model on multiple targets in a dynamic environment can be achieved, and the defects that in a continuously-changing combat environment, information such as the number and attributes of the targets can be changed, dynamic decision making cannot be conducted through a traditional multi-target allocation algorithm, and consequently decision making efficiency is greatly reduced are overcome.
Description
technical field [0001] The invention relates to the field of computer technology, in particular to an intelligent decision-making method for multiple sensors and multiple targets and a storage medium. Background technique [0002] Aiming at the problem of multi-target detection in complex scenes, for multi-type sensors fixed in space, in order to improve the detection efficiency as much as possible, it is necessary to achieve multi-sensor collaborative target allocation, so that the overall performance of the system can be optimized while the scheduling cost is as small as possible. And multi-objective decision-making (assignment) is a combinatorial optimization problem. At present, there have been many research results in multi-objective decision-making technology, such as exhaustive method, dynamic network flow method, ant colony algorithm (ACO), particle swarm algorithm (PSO), genetic algorithm (GA) and other heuristic algorithms. However, there are various uncertainties...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/00G06F18/25G06F18/214Y02D30/70
Inventor 李博骁张峰高原王诏丰王子磊杨尚彤
Owner CHINA ACADEMY OF ELECTRONICS & INFORMATION TECH OF CETC