Road Surface Condition Identification Based on Statistical Pattern Recognition

A method of determining an adhesive condition of a surface of a vehicle road using a statistical pattern recognition technique, the method comprising the steps of:

• (a) providing a plurality of probability distribution functions for a plurality of road surfaces which represent respective adhesive effects between the vehicle tire of a driven vehicle and the vehicle road;
• (b) setting a count to an initial setting;
• (c) obtaining vehicle operating characteristic data;
• (d) determining an index based on the vehicle operating characteristic data;
• (e) applying a probability analysis for each adhesive condition road surface as a function of the determined index;
• (f) recursively updating the probability analysis for each respective road surface adhesive condition as a function of the count;
• (g) determining whether the count is less than a predetermined number;
• (h) repeating steps (c)-(g) if the count is less than the predetermined count;
• (i) determining a likelihood factor for each road surface adhesive condition as a function of each respective recursively updated probability analysis, each respective road surface adhesive condition having a respective likelihood factor that identifies the likelihood of the road surface having the respective adhesive condition as a function of the index;
• (j) selecting the respective likelihood factor that identifies the adhesive condition of the road surface traveled by the vehicle;
• and
• (k) inputting the identified adhesive condition of the road surface and the respective likelihood factor into a vehicle control process.