A method and device for virtual collection of big data for automatic driving training
A technology of automatic driving and collection methods, applied in special data processing applications, genetic rules, geometric CAD, etc., can solve problems such as inability to obtain, achieve simple and convenient collection, reduce collection costs, and increase operability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0031] figure 1 It is a flow chart of the method for virtual collection of large data for automatic driving training in Embodiment 1 of the present invention. This embodiment is applicable to the situation of virtual collection of large data for automatic driving training. device, the method may specifically include:
[0032] Step 110, determining the genetic codes of each candidate driving environment target for automatic virtual driving.
[0033] In this embodiment, a highly simulated virtual engine, such as Unreal, can be used to simulate the driving environment of autonomous driving. Unreal is the abbreviation of Unreal Engine (Unreal Engine). It is a kind of game engine. It adopts technologies such as real-time ray tracing, high dynamic range lighting technology and virtual displacement, and can calculate 200 million polygons in real time per second. The degree of environment simulation is very high. Other virtual simulation platforms with a high degree of simulation c...
Embodiment 2
[0058] Image 6 It is a flow chart of the virtual collection method for automatic driving training big data in the second embodiment of the present invention. On the basis of the foregoing embodiments, this embodiment further optimizes the method for virtual collection of the above-mentioned automatic driving training big data. Correspondingly, the method in this embodiment may specifically include:
[0059] Step 210 , for each candidate driving environment target, determine the gene expression of each environmental target factor contained in the candidate driving environment target.
[0060] Specifically, several candidate driving environment targets can be randomly selected, and for each candidate driving environment target, the gene expression of each environmental target factor contained in the candidate driving environment target is determined. The specific gene codes are shown in Table 1 and figure 2 shown. For example, the candidate driving environment target may se...
Embodiment 3
[0079] Based on the foregoing embodiments, this embodiment provides an example to further illustrate the evolution process of the driving environment in the method for virtual collection of big data for automatic driving training.
[0080] In this embodiment, the idea of evolutionary algorithm can be adopted. The evolutionary algorithm is an algorithm that simulates the biological evolution of nature. The process includes selecting excellent individuals as parents, and generating children from the parents through crossover and mutation methods. Example Specifically, the evolutionary algorithm may include the following steps: 1) Given a set of initial solutions; 2) Evaluating the performance of the current set of solutions; 3) Selecting a certain number of solutions from the current set of solutions as the basis of the iterative solution; 4) Operate it again to obtain the iterative solution; 5) Stop if these solutions meet the requirements, otherwise use the solutions obtained...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


