The invention discloses an automotive external airbag system based on an artificial neural network algorithm. The external airbag system comprises a video analysis system, a radar system, an analysis processing system and an external airbag device, wherein the video analysis system acquires omnidirectional video images of an automobile in real time and analyzes obstacle targets and road conditions in the videos; the analysis processing system has an experience database recording collision data of multiple automobiles of the type on different road conditions, with different colliding targets and at different speeds; the obstacle targets and road conditions around the automobile, and the distance between automobiles and the outline shape of the automobile are analyzed in real time to generate a target function of collision; the target function is trained by using an artificial neural network so as to obtain a mature target function; by putting the obstacle targets and road conditions and the distance between automobiles and the outline shape of the automobile, which are acquired, in the mature target function, the behavior of surrounding automobiles can be anticipated; when it is anticipated that collision will occur, the external airbag device is controlled to start.
Automotive external airbag system based on artificial neural network algorithm
2015-06-10
Patent
Elektronische Ressource
Englisch
IPC: | B60R Fahrzeuge, Fahrzeugausstattung oder Fahrzeugteile, soweit nicht anderweitig vorgesehen , VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR |