Unlock instant, AI-driven research and patent intelligence for your innovation.

Method for long-term trajectory prediction of traffic participants

A technology for participants and transportation, applied in forecasting, traffic control systems, neural learning methods, etc., can solve the problem that the model cannot predict the time range

Pending Publication Date: 2021-07-23
ROBERT BOSCH GMBH
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If the expectation is not just to model physics in very short time periods, current models cannot make predictions for longer time horizons, where driver or system intent dominates trajectory patterns, not just physics

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
  • Method for long-term trajectory prediction of traffic participants
  • Method for long-term trajectory prediction of traffic participants
  • Method for long-term trajectory prediction of traffic participants

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0069] figure 1 A schematic diagram of the system 10 for long-term trajectory prediction of traffic participants is shown. The notation used is commonly used in the deep learning scientific literature. The system uses four inputs, namely environment data E, batched public state P[t-1], previous action data A[t-1] and previous state data S[t-1].

[0070] The environmental data E are in the form of environmental vectors. Preferably, this is a circular representation of the host vehicle's surroundings. The granularity of the environmental data E is arbitrary, however preferably 360° around the host vehicle to be relevant to the environment in all directions. Environmental data E includes all static and dynamic objects surrounding the host vehicle.

[0071] The previous public state data P[t−1], also referred to as batches of public states, relate to different states of nearby objects, in particular road users, in previous time steps. The previous public state data P[t-1] inc...

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 invention provides a method for long-term trajectory prediction for a prediction traffic participant of a plurality of traffic participants, wherein the traffic participants are an ego-vehicle or dynamic objects around the ego-vehicle, the method comprising the steps: receiving environment data (E) from the ego-vehicle relating to the environment around the ego-vehicle;receiving previous public state data (P[t-1]) of the plurality of traffic participants relating to different states of the plurality of traffic participants in a previous time step;determining environment features (F) based on the environment data (E) by an environmental model (ME) relating to the environment of the prediction traffic participant; determining dynamic features (D) based on the previous public state data (P[t-1]) by a dynamic interpreter model (MD) relating to modeled interactions between the plurality traffic participants; predicting dynamic interactions (I) of the prediction traffic participant between the prediction traffic participant and the plurality of traffic participants based on the environmental features (F) and the dynamic feature (D) by an interaction model (MI); and determining a trajectory (T) of the prediction traffic participant based on the predicted dynamic interactions (I) and the determined environment features (F).

Description

technical field [0001] The invention relates to a method for long-term trajectory prediction of traffic participants as well as a control method, a control unit, a computer program and a computer-readable data carrier. Background technique [0002] In general, accurate long-term trajectory prediction for the future given past and current conditions is an extremely challenging research problem. In the field of vehicle automation, current behavior prediction / trajectory prediction mainly consists of modeling the very near future, usually the next second. In such a very short timeframe, the influence of the car and the physics of the environment dominates the behaviour. Often, a simple linear assumption, also known as a constant velocity model, is sufficient to predict the future with acceptable accuracy. For this purpose, most systems use different types of Kalman filter based solutions. These simple models fail to provide accurate future predictions for larger time horizons...

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): G06F30/27G06N3/04G06N3/08G06Q10/04
CPCG06F30/27G06N3/08G06Q10/04G06N3/044G06N3/045G01C21/20G08G1/166B60W30/0956B60W50/0097G08G1/0112G08G1/0129G08G1/0141G08G1/164G08G1/163B60W60/0027
Inventor G·韦尔凯P·克勒希-绍博K·I·基什
Owner ROBERT BOSCH GMBH