Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Trajectory prediction model training method and device, trajectory prediction method and device, equipment and medium

A trajectory prediction and training method technology, applied in the field of intelligent transportation, can solve problems such as threats to intelligent driving, and achieve the effect of high accuracy and precise trajectory prediction

Pending Publication Date: 2022-02-08
CHINA FIRST AUTOMOBILE
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Existing intelligent driving solutions are difficult to respond to and deal with emergencies in a timely manner. If the sudden lane change or sudden braking of surrounding vehicles cannot be predicted in advance, the safety of intelligent driving will face a huge threat. Therefore, Trajectory prediction for advanced autonomous driving has gradually become a research hotspot in the field

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Trajectory prediction model training method and device, trajectory prediction method and device, equipment and medium
  • Trajectory prediction model training method and device, trajectory prediction method and device, equipment and medium
  • Trajectory prediction model training method and device, trajectory prediction method and device, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] figure 1 It is a flow chart of a trajectory prediction model training method provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation where the trajectory prediction model is trained before trajectory prediction. The method can be executed by a trajectory prediction model training device, which can be implemented in software and / or hardware, and can be integrated into an electronic device with a trajectory prediction model training function. Such as figure 1 As shown, the training method of the trajectory prediction model provided in this embodiment specifically includes:

[0037] S101. Using the trajectory prediction model, process the historical trajectory data of the sample vehicle and the historical trajectory data of surrounding vehicles of the sample vehicle to obtain predicted trajectory data of the sample vehicle and predicted driving behavior data of the sample vehicle.

[0038] Wherein, the trajectory prediction model...

Embodiment 2

[0070] Figure 2A It is a flow chart of a trajectory prediction model training method provided in Embodiment 2 of the present invention, Figure 2B A schematic structural diagram of a trajectory prediction model provided in Embodiment 2 of the present invention, such as Figure 2B As shown, the trajectory prediction model executes the process from acquiring historical trajectory data to outputting predicted trajectory data and predicted driving behavior data, and sequentially processes the historical trajectory data through the encoder network, pooled convolutional network and decoder network, and finally Output predicted trajectory data and predicted driving behavior data.

[0071] Next, on the basis of the above-mentioned embodiments, this embodiment combines Figure 2B The trajectory prediction model shown, for Figure 2A The training method of the trajectory prediction model shown is introduced in detail, including:

[0072] S201. Through the encoder network of the tra...

Embodiment 3

[0109] image 3It is a flow chart of a trajectory prediction method provided by Embodiment 3 of the present invention. This embodiment is applicable to the situation of how to realize more accurate trajectory prediction in an automatic driving vehicle, especially applicable to the realization of the trajectory prediction model trained by the above embodiment In the case of trajectory prediction, the method can be executed by a trajectory prediction device, which can be implemented in software and / or hardware, and can be integrated into an electronic device with a trajectory prediction function. Such as image 3 As shown, the trajectory prediction method provided in this embodiment specifically includes:

[0110] S301. Obtain historical trajectory data of the vehicle to be predicted and historical trajectory data of surrounding vehicles of the vehicle to be predicted.

[0111] Wherein, the historical trajectory data refers to the trajectory data of a period of preset historic...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The embodiment of the invention discloses a trajectory prediction model training method and device, a trajectory prediction method and device, equipment and a medium. The method comprises: processing historical trajectory data of a sample vehicle and historical trajectory data of vehicles around the sample vehicle through a trajectory prediction model, and obtaining predicted trajectory data of the sample vehicle and predicted driving behavior data of the sample vehicle; determining a loss function according to the predicted trajectory data of the sample vehicle, the real trajectory data of the sample vehicle and the predicted driving behavior data of the sample vehicle; and training the trajectory prediction model according to the loss function. Through the technical scheme provided by the embodiment of the invention, the accuracy of the trained trajectory prediction model is higher, so that more accurate trajectory prediction on the autonomous vehicle based on the trajectory prediction model is realized.

Description

technical field [0001] Embodiments of the present invention relate to intelligent transportation technologies, and in particular to trajectory prediction model training and trajectory prediction methods, devices and storage media. Background technique [0002] With the rapid development of smart car technology, autonomous driving technology has gradually become a research hotspot in the field. [0003] Existing intelligent driving solutions are difficult to respond to and deal with emergencies in a timely manner. If the sudden lane change or sudden braking of surrounding vehicles cannot be predicted in advance, the safety of intelligent driving will face a huge threat. Therefore, Trajectory prediction for advanced autonomous driving has gradually become a research hotspot in the field. Contents of the invention [0004] The trajectory prediction model training and trajectory prediction method, device, equipment, and medium provided by the embodiments of the present invent...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/18G06F16/29G06K9/62
CPCG06F17/18G06F16/29G06F18/214
Inventor 高延熹吕颖韩佳琪
Owner CHINA FIRST AUTOMOBILE
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products