Intelligent vehicle end-to-end decision method and system orienting expressway scene

Abstract

The invention discloses an intelligent vehicle end-to-end decision method and system orienting expressway scenes. The system concretely comprises the following modules including a pre-training decision module, an intelligent vehicle end-to-end decision system framework module and an intelligent vehicle end-to-end decision system test module. An initial training network model is trained by using atraining sample set; a pre-training initial model is obtained; a trained decision model is loaded in the end-to-end decision system for calculating a steering wheel rotating angle value; the system has high stability; the predicted steering wheel rotating angle value is stable; the stable running of an intelligent vehicle on the practical expressway is ensured; during turning, an intelligent vehicle can well fit with a reference curve; great deviation occurrence like a convolutional network cannot occur; and a pre-trained space-time characteristic fusion network has certain capability of predicting the steering wheel rotating angle. By using a model migration method, the decision network is directly migrated into the expressway scene; much time can be saved; and the network model trainingfrom the beginning is not needed.

Description

technical field [0001] The invention relates to the field of unmanned vehicle decision-making, in particular to an end-to-end decision-making method and system for intelligent vehicles facing expressway scenarios. Background technique [0002] With the development of technology, more and more smart car researchers are focusing on the actual driving scene, hoping to realize automatic driving on the actual highway. The participating smart cars complete decision-making tasks such as obstacle avoidance, overtaking and lane changing in highway scenes like human drivers, aiming to promote smart cars to enter the actual driving scene faster and help humans complete various driving task. [0003] Compared with the urban highway scene, the highway scene has a more standardized road structure, clear lane lines, simple background, fewer environmental unpredictability factors, the movement behavior of surrounding vehicles is basically predictable, and the environment is relatively stab...

AI Technical Summary

Problems solved by technology

However, the decision-making models trained in public databases are all based on highway scenarios and cannot be directly applied to actual highway scenarios.

There are two reasons: First, the scene in the public database is very different from the actual highway scene. For example, foreign traffic signs are not consistent with domestic traffic signs, and the scenes around the same lane are also different. The model trained on the public database Directly predicting the decision value of the actual highway scene will have a large deviation; second, the internal attributes of different vehicles are not the same, and the steering wheel angle values ​​that different vehicles need to turn in the same scene are not the same. The model trained on the above is easy to output extreme decision values ​​when applied to actual vehicles on the highway

Images