Automatic driving automobile complex environment model based on complex network, cognitive system and cognitive method

Abstract

The invention discloses an automatic driving automobile complex environment model based on a complex network, a cognitive system and a cognitive method. The method includes: on the basis of sensing the external environment of an automatic driving automobile, firstly, aiming at the complexity problem of individual driving behavior cognition, according to driving characteristic parameters used for representing the aggressive degree of driving control and mode transfer preference, performing driving style identification; secondly, according to group behavior characteristics of motion subjects in the environment, on the basis of driving style recognition, based on a complex network, taking the motion subjects as nodes and taking roads as constraints, establishing a time-varying complex dynamic network as an automatic driving vehicle complex environment model; and finally, performing parameterization expression on nodes in the complex environment model to realize node differentiation cognition of the complex environment, layering the nodes in the complex environment model by adopting a coagulation algorithm to realize hierarchical cognition of the complex environment, establishing a disorder degree measurement method of the complex environment model, and achieving global risk situation cognition of a complex environment.

Description

Technical field [0001] The present invention relates to an autonomous vehicle model complex environment, cognitive system and method for automatic recognition technology in automotive applications and, more particularly, relates to a network-based complex. Background technique [0002] Complex networks are presenting the highly complex nature of the network, it is abstract and complex systems, usually with self-organizing, self-similarity, attractor, small world, scale-free part or all of the properties. Characteristics of complex networks is the complexity, in particular in: network scale, complex connection structure, the complexity of the node (eg: complexity and dynamics node node diversity), spatial and temporal evolution of network complexity, sparseness of the network connection, and more seed weight complex fusion. Method complexity of complex networks, such as: the complexity of the nodes, links, structural complexity and the temporal evolution of the network complicates...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above-mentioned technical problems, the present invention provides a complex network-based self-driving car complex environment model, a cognitive system and a cognitive method. For the complexity problem, the driving style is identified based on the driving characteristic parameters used to represent the aggressiveness of driving manipulation and the mode transfer preference; secondly, based on the group behavior characteristics of the moving subjects in the environment, on the basis of the driving style identification, based on the complex network, With the moving subject as the node and the road as the constraint, a time-varying complex dynamic network is established as the complex environment model of the autonomous vehicle; finally, the nodes in the complex environment model are parametrically expressed to realize the node differential cognition of the complex environment, Use the agglomerative algorithm to stratify the nodes in the complex environment model, realize the hierarchical cognition of the complex environment, establish the disorder degree measurement method of the complex environment model, and realize the global risk situation cognition of the complex environment

Images