A collision analysis method for autonomous driving vehicles based on big data

Abstract

The present invention discloses a collision analysis system and method for an autonomous driving vehicle based on big data. The collision analysis system comprises a transponder and a transmitter installed on the vehicle, an analysis module, an information generation module and a feedback receiving control module. The analysis module comprises a collision analysis module and a radio frequency signal analysis module. The transponder is used to receive a radio frequency signal carrying a first mixed information sent by other vehicles, the transmitter is used to send a radio frequency signal carrying a second mixed information to other vehicles, the collision analysis module is used to analyze the risk level of a collision of the vehicle, the radio frequency signal analysis module is used to analyze the radio frequency signal carrying the first mixed information received by the vehicle, and the information generation module generates the second mixed information sent to other vehicles according to the collision analysis module and the radio frequency signal analysis module.

Description

Technical Field

[0001] The present invention relates to the field of big data, and in particular to a collision analysis method for an autonomous driving vehicle based on big data. Background Art

[0002] Autonomous driving cars rely on artificial intelligence, visual computing, radar, monitoring devices and global positioning systems to work together, allowing computers to automatically and safely operate motor vehicles without any human active operation. Autonomous driving is an intelligent car that can be driven by a computer system without a driver, and can take passengers to their destination. Autonomous driving is an important way to improve the level of intelligent road traffic and promote the transformation and upgrading of the transportation industry. It is also a favorable opportunity to promote the integrated development of transportation, automobiles, communications and other industries. However, the existing autonomous driving vehicles have a high risk of vehicle collision during driving. Therefore, a collision analysis system and method for autonomous driving vehicles based on big data is proposed. Summary of the invention

[0003] The purpose of the present invention is to provide an autonomous driving vehicle collision analysis system and method based on big data to solve the problems in the prior art.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A collision analysis system for an autonomous driving vehicle based on big data, the collision analysis system comprising a transponder and a transmitter installed in the vehicle, an analysis module, an information generation module and a feedback receiving control module, the analysis module comprising a collision analysis module and a radio frequency signal analysis module, the transponder being used to receive radio frequency signals carrying first mixed information sent by other vehicles, the transmitter being used to send radio frequency signals carrying second mixed information to other vehicles, the collision analysis module being used to analyze the risk level of a collision of the vehicle, the radio frequency signal analysis module being used to analyze radio frequency signals carrying the first mixed information received by the vehicle, the information generation module generating the second mixed information sent to other vehicles based on the collision analysis module and the radio frequency signal analysis module, and the feedback receiving control module adjusting the vehicle's own driving data based on the output result of the collision analysis module and the analysis result of the radio frequency signal analysis, or adjusting the quality of the radio frequency signal sent by the vehicle to other vehicles.

[0006] As a preferred solution, the collision analysis module includes a sample data acquisition module, a sample data processing module, a vehicle data acquisition module and a vehicle collision risk output module. The sample data acquisition module is used to collect driving data features of vehicles that have collided or are adjacent to a collision during driving as samples. The sample data processing module uses a K-means model to cluster the driving data features in the samples, and divides them into different collision risk levels according to the clustering results. The vehicle data acquisition module is used to collect driving data features of the vehicle during driving. The vehicle collision risk output module is used to input the collected driving data features into the K-means model and output the vehicle collision risk level; the radio frequency signal analysis module includes a first response information analysis module and a first received information analysis module. The first response information analysis module is used to analyze the bit error rate of the radio frequency signal received by the vehicle and make feedback suggestions. The first received information analysis module is used to analyze and output the risk level of collision of surrounding vehicles.

[0007] As a preferred solution, the feedback receiving control module includes a vehicle driving data adjustment module and a radio frequency signal adjustment module, the vehicle driving data adjustment module includes an internal stimulation adjustment module and an external stimulation adjustment module, the internal stimulation adjustment module adjusts the vehicle's own driving data according to the vehicle's own collision risk level, the external stimulation adjustment module adjusts the vehicle's own driving data according to the collision risk level of surrounding vehicles, and the radio frequency signal adjustment module is used to receive feedback suggestions from other vehicles on the radio frequency signal quality of the signal-transmitting vehicle, and adjust the radio frequency signal quality accordingly.

[0008] A collision analysis method for autonomous driving vehicles based on big data, the collision analysis method comprising the following: a transponder installed on a central vehicle receives a radio frequency signal carrying first mixed information sent by vehicles around the central vehicle, and based on the received radio frequency signal of the first mixed information and the risk level of a collision with the central vehicle, a transmitter installed on the central vehicle sends a radio frequency signal carrying second mixed information to vehicles around the central vehicle, and the collision risk level is transmitted by signal transmission between moving vehicles, which helps other vehicles take countermeasures to avoid collision.

[0009] As a preferred embodiment, the collision analysis method further comprises the following:

[0010] The transponder installed on the central vehicle receives radio frequency signals carrying first mixed information sent by vehicles around the central vehicle, wherein the first mixed information includes first response information and first reception information, wherein the first response information is used for the central vehicle to analyze the quality of the received radio frequency signal, and the first reception information is the risk level of collision of the vehicle sending the radio frequency signal;

[0011] The central vehicle parses the first received information, and adjusts the driving data characteristics of the central vehicle accordingly to determine the risk level of a collision of the central vehicle. A transmitter installed on the central vehicle sends a radio frequency signal carrying second mixed information to vehicles around the central vehicle. The second mixed information includes second feedback information and second analysis information. The second feedback information includes feedback on the quality of the received radio frequency signal. The second analysis information is the risk level of a collision of the central vehicle.

[0012] As a preferred solution, the central vehicle analyzing the quality of the received radio frequency signal includes analyzing the bit error rate of the central vehicle radio frequency signal;

[0013] The feedback on the quality of the received RF signal includes: when the measured value of the bit error rate of the RF signal is less than the bit error rate threshold, controlling the transmitter of the corresponding vehicle transmitting the RF signal to reduce the transmission power; when the measured value of the bit error rate of the RF signal is greater than the bit error rate threshold, controlling the transmitter of the corresponding vehicle transmitting the RF signal to increase the transmission power.

[0014] In the above technical solution, the received RF signal is fed back according to the bit error rate of the received RF signal to ensure that the transmission power of the transmitter is in a reasonable state, to prevent the transmission power of the transmitter from being too high, affecting the transmission between other signals, and to prevent the transmission power of the transmitter from being too low, making it impossible to clearly parse the first received information, to prevent unclear information reception, and causing a vehicle collision.

[0015] As a preferred solution, the driving data characteristics include vehicle speed, vehicle acceleration, and the distance between the vehicle and surrounding vehicles.

[0016] As a preferred solution, the risk level of the vehicle collision in the judgment center includes:

[0017] Step S1: using the data of vehicles that have collided and near-collision as samples, collecting driving data features of the vehicle samples during driving, clustering these driving data features using the K-means model, and dividing the collision risks into four collision risk levels from high to low according to the clustering results, namely high collision risk, medium-high collision risk, low collision risk and no collision risk, and setting high collision risk and medium-high collision risk as alarm levels;

[0018] Step S2: Collect the driving data characteristics of the center vehicle, input the driving data characteristics into the K-means model, output the risk level of collision, and determine whether the vehicle issues an alarm. If the vehicle issues an alarm, the vehicle adjusts the driving data characteristics.

[0019] In the above technical solution, the vehicle will not only adjust its own driving data characteristics when its own collision risk level is high, but also adjust its own driving data characteristics when receiving high collision risk level information from other vehicles, to prevent the vehicle from being unable to respond in time when other vehicles collide, resulting in a chain collision accident.

[0020] Compared with the prior art, the beneficial effects of the present invention are as follows: in the present invention, the received radio frequency signal is fed back according to the bit error rate of the received radio frequency signal, so as to ensure that the transmission power of the transmitter is in a reasonable state, prevent the transmission power of the transmitter from being too high, affecting the transmission between other signals, and prevent the transmission power of the transmitter from being too low, making it impossible to clearly parse the first received information, thereby preventing unclear information reception from causing a vehicle collision. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a module schematic diagram of an autonomous driving vehicle collision analysis system based on big data of the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] See also Figure 1 In an embodiment of the present invention, a collision analysis system for an autonomous driving vehicle based on big data, the collision analysis system includes a transponder and a transmitter installed in the vehicle, an analysis module, an information generation module and a feedback receiving control module, the analysis module includes a collision analysis module and a radio frequency signal analysis module, the transponder is used to receive a radio frequency signal carrying a first mixed information sent by other vehicles, the transmitter is used to send a radio frequency signal of a second mixed information to other vehicles, the collision analysis module is used to analyze the risk level of a collision of the vehicle, the radio frequency signal analysis module is used to analyze the radio frequency signal carrying the first mixed information received by the vehicle, the information generation module generates the second mixed information sent to other vehicles according to the collision analysis module and the radio frequency signal analysis module, and the feedback receiving control module adjusts the vehicle's own driving data according to the output result of the collision analysis module and the analysis result of the radio frequency signal analysis, or adjusts the quality of the radio frequency signal sent by the vehicle to other vehicles.

[0024] The collision analysis module includes a sample data collection module, a sample data processing module, a vehicle data collection module and a vehicle collision risk output module. The sample data collection module is used to collect driving data features of vehicles that have collided or are adjacent to a collision during driving as samples. The sample data processing module uses a K-means model to cluster the driving data features in the samples, and divides them into different collision risk levels according to the clustering results. The vehicle data collection module is used to collect driving data features of the vehicle during driving. The vehicle collision risk output module is used to input the collected driving data features into the K-means model and output the vehicle collision risk level; the radio frequency signal analysis module includes a first response information analysis module and a first received information analysis module. The first response information analysis module is used to analyze the bit error rate of the radio frequency signal received by the vehicle and make feedback suggestions. The first received information analysis module is used to analyze and output the risk level of collision of surrounding vehicles.

[0025] The feedback receiving control module includes a vehicle driving data adjustment module and a radio frequency signal adjustment module. The vehicle driving data adjustment module includes an internal stimulation adjustment module and an external stimulation adjustment module. The internal stimulation adjustment module adjusts the vehicle's own driving data according to the vehicle's own collision risk level. The external stimulation adjustment module adjusts the vehicle's own driving data according to the collision risk level of surrounding vehicles. The radio frequency signal adjustment module is used to receive feedback suggestions from other vehicles on the radio frequency signal quality of the signal-transmitting vehicle, and adjust the radio frequency signal quality accordingly.

[0026] A collision analysis method for autonomous driving vehicles based on big data, the collision analysis method comprising the following: a transponder installed on a central vehicle receives a radio frequency signal carrying first mixed information sent by vehicles around the central vehicle, and a transmitter installed on the central vehicle sends a radio frequency signal carrying second mixed information to vehicles around the central vehicle based on the received radio frequency signal of the first mixed information and the risk level of a collision with the central vehicle.

[0027] The collision analysis method further comprises the following:

[0028] The transponder installed on the central vehicle receives radio frequency signals carrying first mixed information sent by vehicles around the central vehicle, wherein the first mixed information includes first response information and first reception information, wherein the first response information is used for the central vehicle to analyze the quality of the received radio frequency signal, and the first reception information is the risk level of collision of the vehicle sending the radio frequency signal;

[0029] The central vehicle parses the first received information, and adjusts the driving data characteristics of the central vehicle accordingly to determine the risk level of a collision of the central vehicle. A transmitter installed on the central vehicle sends a radio frequency signal carrying second mixed information to vehicles around the central vehicle. The second mixed information includes second feedback information and second analysis information. The second feedback information includes feedback on the quality of the received radio frequency signal. The second analysis information is the risk level of a collision of the central vehicle.

[0030] The central vehicle analyzing the quality of the received radio frequency signal includes analyzing the bit error rate of the central vehicle radio frequency signal;

[0031] The feedback on the quality of the received RF signal includes: when the measured value of the bit error rate of the RF signal is less than the bit error rate threshold, controlling the transmitter of the corresponding vehicle transmitting the RF signal to reduce the transmission power; when the measured value of the bit error rate of the RF signal is greater than the bit error rate threshold, controlling the transmitter of the corresponding vehicle transmitting the RF signal to increase the transmission power; providing feedback on the received RF signal according to the bit error rate of the received RF signal to ensure that the transmission power of the transmitter is in a reasonable state, to prevent the transmission power of the transmitter from being too high, affecting the transmission between other signals, and to prevent the transmission power of the transmitter from being too low, making it impossible to clearly parse the first received information, to prevent unclear information reception, and causing a vehicle collision.

[0032] The driving data features include vehicle speed, vehicle acceleration, and the distance between the vehicle and surrounding vehicles.

[0033] The risk level of the vehicle collision in the judgment center includes:

[0034] Step S1: using the data of vehicles that have collided and near-collision as samples, collecting driving data features of the vehicle samples during driving, clustering these driving data features using the K-means model, and dividing the collision risks into four collision risk levels from high to low according to the clustering results, namely high collision risk, medium-high collision risk, low collision risk and no collision risk, and setting high collision risk and medium-high collision risk as alarm levels;

[0035] Step S2: Collect the driving data characteristics of the central vehicle, input the driving data characteristics into the K-means model, output the risk level of collision, and determine whether the vehicle issues an alarm. If the vehicle issues an alarm, the vehicle adjusts the driving data characteristics. When the vehicle adjusts the driving data characteristics, it adjusts the vehicle speed, vehicle acceleration, and the distance between the vehicle and surrounding vehicles. These data can be adjusted at the same time, or one of them can be selected for adjustment.

[0036] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A collision analysis method for an autonomous driving vehicle based on big data, characterized in that: The collision analysis method includes the following: The transponder installed on the central vehicle receives the radio frequency signal carrying the first mixed information sent by the vehicles around the central vehicle, and according to the received radio frequency signal carrying the first mixed information and the risk level of collision with the central vehicle, the transmitter installed on the central vehicle sends the radio frequency signal carrying the second mixed information to the vehicles around the central vehicle; The first mixed information includes first response information and first receiving information, wherein the first response information is used by the central vehicle to analyze the quality of the received radio frequency signal, and the first receiving information is the risk level of collision of the vehicle sending the radio frequency signal; The central vehicle analyzes the first received information, and determines the risk level of the central vehicle to collide after adjusting the driving data characteristics of the central vehicle accordingly. A transmitter installed on the central vehicle sends a radio frequency signal carrying second mixed information to vehicles around the central vehicle. The second mixed information includes second feedback information and second analysis information. The second feedback information includes feedback on the quality of the received radio frequency signal. The second analysis information is the risk level of the central vehicle to collide. The central vehicle analyzing the quality of the received radio frequency signal includes analyzing the bit error rate of the central vehicle radio frequency signal; The feedback of the quality of the received radio frequency signal includes: when the measured value of the bit error rate of the radio frequency signal is less than the bit error rate threshold, controlling the transmitter of the corresponding vehicle transmitting the radio frequency signal to reduce the transmission power; when the measured value of the bit error rate of the radio frequency signal is greater than the bit error rate threshold, controlling the transmitter of the corresponding vehicle transmitting the radio frequency signal to increase the transmission power; The risk level of the vehicle collision in the judgment center includes: Step S1: using the data of vehicles that have collided and near-collision as samples, collecting driving data features of the vehicle samples during driving, clustering these driving data features using the K-means model, and dividing the collision risks into four collision risk levels from high to low according to the clustering results, namely high collision risk, medium-high collision risk, low collision risk and no collision risk, and setting high collision risk and medium-high collision risk as alarm levels; Step S2: collecting driving data features of the center vehicle, inputting the driving data features into the K-means model, outputting the risk level of collision, and judging whether the vehicle issues an alarm. If the vehicle issues an alarm, the vehicle adjusts the driving data features; The driving data features include vehicle speed, vehicle acceleration, and the distance between the vehicle and surrounding vehicles.

Images