Artificial intelligent training platform for intelligent networking vehicle plan decision-making module

Abstract

The invention, which relates to the technical field of an intelligent vehicle automatic driving and traffic simulation, relates to an artificial intelligent training platform for an intelligent networking vehicle plan decision-making module and aims at improving the intelligent level of the intelligent vehicle plan decision-making module based on enriched and vivid traffic scenes. The artificial intelligent training platform comprises a simulation environment layer, a data transmission layer, and a plan decision-making layer. The simulation environment layer is used for generating a true traffic scene based on a traffic simulation module and simulating sensing and reaction situations to the environment by an intelligent vehicle, thereby realizing multi-scene loading. The plan decision-making layer outputs a decision-making behavior of the intelligent vehicle by using environment sensing information as an input based on a deep reinforcement learning algorithm, thereby realizing training optimization of network parameters. And the data transmission layer connects the traffic environment module with a deep reinforcement learning frame based on a TCP / IP protocol to realize transmission of sensing information and vehicle control information between the simulated environment layer and the plan decision-making layer.

Description

technical field [0001] The invention belongs to the technical field of intelligent vehicle automatic driving, artificial intelligence and traffic simulation. More specifically, the invention relates to an artificial intelligence training platform for planning and decision-making modules of intelligent networked vehicles, which is applied to the research and development of core modules of intelligent vehicles and It can be used as a training tool to improve the autonomous driving level of smart cars. Background technique [0002] Facing the deteriorating traffic environment, intelligent networked vehicles are receiving more and more attention in the Internet era. The realization of automatic driving of smart cars needs to include three modules: environment perception, planning decision-making and vehicle control. The environment perception mainly depends on various sensors (such as lidar, camera, GPS, etc.) It can be called the "eyes" and "ears" of the smart car; the plannin...

AI Technical Summary

Problems solved by technology

[0006] Based on the above situation, the purpose of the present invention is to propose an artificial intelligence training platform for smart car planning and decision-making modules, which can provide more "real" and more comprehensive test and training scenarios for behavior decision-making training of smart cars. The method has a stronger generalization ability, overcomes the shortcomings of limited scenarios, high cost, and unsafety in current smart car training, and obtains a "driving level" that exceeds that of human drivers through continuous iterative learning

Images