A sensor information processing method based on distributed cooperation

Abstract

The invention discloses a sensor information processing method based on distributed cooperation. The method is as follows: each platform of the UAV cluster is initialized, and the sensor data processing mode of each UAV in the cluster is selected according to the total bandwidth of communication and the bandwidth occupied by different sensor data processing; each UAV in the cluster passes the state Perceive and maintain the state information table of each UAV platform in the whole network of this machine, calculate and sort the weight of local processing, and determine the data processing method of different UAVs; each UAV in the UAV cluster will process sensor data After the data is sent to the edge node for data fusion, it is reversely transmitted to each UAV in the cluster for shared decision-making, and the fused data is transmitted to the ground command and control center. The invention has good robustness and invulnerability, high information transmission efficiency, and dynamically adjustable sensor data processing mode, which optimizes the communication bandwidth and the computing power usage efficiency of the local platform, and simultaneously improves the efficiency of cooperative investigation.

Description

technical field [0001] The invention relates to the technical field of unmanned aerial vehicle software information processing, in particular to a sensor information processing method based on distributed cooperation. Background technique [0002] UAV clusters work together to detect targets has become one of the important application methods of UAVs. Through the collaboration within the cluster, the detection range of the UAV can be effectively expanded, and the detection of targets at different distances and from different perspectives can be realized. The detection information obtained by the UAVs can be fused, which effectively improves the detection quality of the target and overcomes the Flaws in the detection of UAVs in the case of a single UAV or a group of UAVs without cooperation. [0003] With the rapid development of artificial intelligence technologies such as machine learning, a single UAV can already analyze and process images acquired by sensors locally. Wh...

AI Technical Summary

Problems solved by technology

[0005] ① The interaction between the change of the communication network and the computing power of a single UAV restricts the processing efficiency of a single UAV node for sensor data

[0006] The instability of wireless channels determines that the communication network is constantly changing, and the use of fixed or centralized bandwidth allocation methods increases the difficulty of data processing by drones. Once communication resources such as bandwidth are allocated, it is difficult to adjust. If the bandwidth is not enough, the UAV data transmission will be delayed, and when the communication bandwidth exceeds the amount of data processed by a single machine, it will increase the waste of communication resources

[0007] ②Fixed or centralized communication bandwidth allocation is difficult to adapt to rapid changes in network conditions

[0008] Each UAV platform of the UAV cluster adopts the method of pre-allocation to obtain communication resources. Once the channel conditions change, such as enemy interference, communication occlusion, etc., fixed or centralized communication bandwidth allocation is difficult to cope with the change, and the adjustment is difficult. , unable to respond to various communication problems in a timely manner by increasing bandwidth, etc.

[0009] ③The processing method of sensor data by a single UAV cannot be dynamically adjusted according to changes in bandwidth or computing power

Images