Vehicle-mounted high-definition map data source selection method and device

Abstract

The invention provides a vehicle-mounted high-definition map data source selection method and device, the method is combined with a reinforcement learning method to construct an asynchronous data source selection framework, the framework is divided into an offline training part and an online selection part, the offline part is responsible for training a neural network model by using a deep reinforcement learning algorithm, and the online selection part is responsible for training a neural network model by using a deep reinforcement learning algorithm; meanwhile, the online part uses neural network parameters synchronized from the offline part to select data sources, and parallel execution of data source selection, experience track collection and model training is achieved. According to the invention, the problem of reduced throughput in the data source transmission process can be avoided, frequent data source switching is avoided, and the optimal vehicle-mounted high-definition map data source is effectively selected.

Description

technical field [0001] The invention relates to the field of deep learning technology, in particular to a method and device for selecting a vehicle-mounted high-definition map data source. Background technique [0002] With the widespread deployment of information infrastructure and the rapid development of in-vehicle sensing technology, autonomous driving has become a promising direction to revolutionize the current automotive technology. Autonomous driving is the future development trend of intelligent technology. It uses a large number of sensors to form a perception system to perceive the environmental information around the vehicle. According to the road structure, vehicle position, obstacle status and other information obtained by the perception system, an automatic electronic control system is implemented to control the speed and direction of the vehicle, so that it can drive safely and reliably on the road. Unlike traditional electronic maps, autonomous vehicles req...

AI Technical Summary

Problems solved by technology

[0003] The traditional HD map selection and distribution method is to use the RTT index to judge the data source, but as the number of vehicles in the coverage area increases, the traditional solution uses the communication model (vehicle-to-infrastructure (V2I) or vehicle-to-vehicle (V2V)) to select the data source, where the throughput will be significantly reduced; moreover, traditional schemes select the data source only by measuring the round-trip time (RTT) between the data source and the vehicle, in which case the state of the vehicle is changing in real time, Especially in complex mobile scenarios, since other types of vehicle information (e.g., speed, direction) are not considered, the measurement of RTT cannot guarantee the best data source selection results; , there will be frequent data source switching, resulting in frequent RTT updates and inefficient data transmission

In conclusion, the existing schemes cannot effectively judge the quality of the currently selected data source, and the frequent movement of the vehicle leads to inaccurate RTT measurement and inefficient data transmission

Images