Road adhesion coefficient estimating method based on cloud data sharing

Abstract

The invention provides a road adhesion coefficient estimating method based on cloud data sharing. The method comprises the steps of: (S100): building of a first cloud data image blocks acquired by a vision sensor are matched with adhesion coefficient estimating value based on dynamics to form data pairs, and the data pairs are uploaded to a cloud; (S200) training of classifiers: the cloud receives the data pairs, and arranges and trains the data pairs to generate useful classifiers; and (S300) matching of the classifiers: a second cloud database is built in the actual driving process of avehicle, and is matched with the trained classifiers to obtain the optimal-matched classifier for real-time road adhesion coefficient estimation. The method carries out the data management and training at the cloud completely, reduces demands on a vehicle-mounted calculating unit, can match with all the same vehicle types after completion of training, and supports online updating.

Description

technical field [0001] The invention relates to a road surface adhesion coefficient estimation method based on cloud data sharing. Background technique [0002] During the driving process of the vehicle, if the road adhesion conditions are poor or change suddenly, due to the driver's insufficient judgment on the road surface, it is very easy to cause the vehicle to collide and skid. In order to reduce the occurrence of accidents, active safety systems have become an inevitable trend of development, such as ABS, ESP and so on. The effective identification of the road surface can enable the system to change the control strategy in real time according to the road surface adhesion information, thereby improving the role of active intervention and reducing the occurrence of accidents. Therefore, road surface recognition is of great significance to ensure safe driving. In addition, when smart cars are running at medium and high speeds, the mechanical properties such as vehicle d...

AI Technical Summary

Problems solved by technology

[0004] In the prior art, although the results-based method is accurate and reliable for estimating the road surface adhesion coefficient, due to the complexity of dynamic modeling, real-time performance is difficult to guarantee; and the dynamics-based method requires the object to be in contact with the road surface to estimate, such an estimation Even if the result is accurate, it is difficult to intervene and control some extreme conditions in time

The reason-based method has a certain degree of active predictability for road surface recognition, and can identify and estimate the state of the road surface before contact, but if the sensor is too complicated or the cost is high, it will lose its commercial promotion value; The working environment is demanding, ultrasonic and electromagnetic waves are greatly affected by the environment, and their robustness is poor, and there is a problem that online learning has high requirements for on-board computing units, resulting in calculations that cannot be completed in time, and prediction accuracy is greatly affected by samples

Images