CN117250602A - Collision type prediction method, apparatus, and storage medium - Google Patents
Collision type prediction method, apparatus, and storage medium Download PDFInfo
- Publication number
- CN117250602A CN117250602A CN202311514396.7A CN202311514396A CN117250602A CN 117250602 A CN117250602 A CN 117250602A CN 202311514396 A CN202311514396 A CN 202311514396A CN 117250602 A CN117250602 A CN 117250602A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- sample
- ultrasonic
- collision
- track prediction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000006870 function Effects 0.000 claims abstract description 53
- 230000002093 peripheral effect Effects 0.000 claims description 30
- 238000012549 training Methods 0.000 claims description 29
- 230000004044 response Effects 0.000 claims description 12
- 238000013016 damping Methods 0.000 claims description 4
- 238000002604 ultrasonography Methods 0.000 claims description 4
- 230000002123 temporal effect Effects 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 7
- 238000012545 processing Methods 0.000 abstract description 6
- 230000001960 triggered effect Effects 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 10
- 238000004590 computer program Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/52—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S15/00
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R21/00—Arrangements or fittings on vehicles for protecting or preventing injuries to occupants or pedestrians in case of accidents or other traffic risks
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R21/00—Arrangements or fittings on vehicles for protecting or preventing injuries to occupants or pedestrians in case of accidents or other traffic risks
- B60R21/01—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents
- B60R21/013—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents including means for detecting collisions, impending collisions or roll-over
- B60R21/0134—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents including means for detecting collisions, impending collisions or roll-over responsive to imminent contact with an obstacle, e.g. using radar systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/88—Sonar systems specially adapted for specific applications
- G01S15/93—Sonar systems specially adapted for specific applications for anti-collision purposes
- G01S15/931—Sonar systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R21/00—Arrangements or fittings on vehicles for protecting or preventing injuries to occupants or pedestrians in case of accidents or other traffic risks
- B60R2021/0002—Type of accident
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention relates to the field of data processing, and discloses a collision type prediction method, a device and a storage medium, wherein the method comprises the following steps: acquiring ultrasonic sensing data based on a plurality of ultrasonic radars installed on a current vehicle; and respectively inputting the ultrasonic sensing data into a pre-trained attenuation self-adjustment potential function corresponding to each collision type, and determining the type to be collided between the surrounding vehicles and the current vehicle. Through the technical scheme of the invention, the collision types are finely classified, corresponding attenuation self-regulating potential functions are trained for different collision types, the accuracy and the robustness in predicting the collision types are greatly improved, the corresponding passive safety devices are conveniently triggered subsequently, and the protection effect and the user experience are improved.
Description
Technical Field
The present invention relates to the field of data processing, and in particular, to a collision type prediction method, apparatus, and storage medium.
Background
Currently, collision prediction for vehicles mainly determines probability and intensity of collision by predicting trajectory prediction of surrounding vehicles. And when the probability and the intensity of collision reach a certain threshold value, triggering all passive safety devices in the vehicle so as to protect personnel in the vehicle.
However, it is difficult to determine the collision type of the vehicle through the track prediction in the above manner, so that there is a high possibility of false triggering of the partially passive safety device, which affects the user experience.
In view of this, the present invention has been made.
Disclosure of Invention
In order to solve the technical problems, the invention provides a collision type prediction method, a device and a storage medium, which are used for finely classifying collision types, training out corresponding attenuation self-regulating potential functions according to different collision types, greatly improving the accuracy and robustness of predicting the collision types, facilitating the subsequent triggering of corresponding passive safety devices, and improving the protection effect and user experience.
The embodiment of the invention provides a collision type prediction method, which comprises the following steps:
acquiring ultrasonic sensing data based on a plurality of ultrasonic radars installed on a current vehicle;
respectively inputting the ultrasonic sensing data into a pre-trained attenuation self-adjustment potential function corresponding to each collision type, and determining the type to be collided between the surrounding vehicles and the current vehicle;
the damping self-regulating potential function corresponding to each collision type is trained based on the following mode:
For each collision type, acquiring sample ultrasonic data corresponding to the collision type;
determining a first range corresponding to a first parameter in an initial self-adjusting potential function according to the sample ultrasonic data, determining a second range of the first parameter in the first range according to the precision and the density condition of the ultrasonic radar, and determining the first parameter in the second range;
and training the initial self-regulating potential function according to the sample ultrasonic data to obtain an attenuation self-regulating potential function corresponding to the collision type.
The embodiment of the invention provides electronic equipment, which comprises:
a processor and a memory;
the processor is configured to execute the steps of the collision type prediction method according to any of the embodiments by calling a program or instructions stored in the memory.
Embodiments of the present invention provide a computer-readable storage medium storing a program or instructions that cause a computer to execute the steps of the collision type prediction method according to any of the embodiments.
The embodiment of the invention has the following technical effects: the method has the advantages that ultrasonic sensing data are acquired based on a plurality of ultrasonic radars installed on the current vehicle, the ultrasonic sensing data are respectively input into the attenuation self-adjustment potential functions which are trained in advance and correspond to each collision type, the type to be collided between the surrounding vehicle and the current vehicle is determined, the attenuation self-adjustment potential functions are adopted, the collision types of the current vehicle and the surrounding vehicle are accurately predicted in real time under various complex collision conditions, the problem that a passive safety device is triggered by mistake due to the fact that the collision probability and the intensity threshold value are too low is solved, in addition, the accuracy and the robustness of collision type determination are greatly improved, and the protection effect is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a collision type prediction method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a vehicle coordinate system provided by an embodiment of the present invention;
FIG. 3 is a schematic diagram of an ultrasonic radar for a current vehicle according to an embodiment of the present invention;
FIG. 4 is a schematic illustration of a frontal-side impact provided by an embodiment of the present invention;
FIG. 5 is a schematic illustration of a frontal-side frontal-frontal collision provided by an embodiment of the present invention;
FIG. 6 is a schematic illustration of a frontal-frontal collision provided by an embodiment of the present invention;
FIG. 7 is a schematic illustration of a front-to-rear collision provided by an embodiment of the present invention;
FIG. 8 is a schematic view of a left front-side impact provided by an embodiment of the present invention;
FIG. 9 is a schematic illustration of a right front-side impact provided by an embodiment of the present invention;
FIG. 10 is a schematic illustration of a left front-left rear collision provided by an embodiment of the present invention;
FIG. 11 is a schematic illustration of a right front-left front collision provided by an embodiment of the present invention;
FIG. 12 is a schematic view of a frontal-angular collision provided by an embodiment of the present invention;
fig. 13 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the invention, are within the scope of the invention.
The collision type prediction method provided by the embodiment of the invention is mainly suitable for the situation of predicting the collision type with surrounding vehicles before the vehicles collide. The collision type prediction method provided by the embodiment of the invention can be executed by the electronic equipment.
Fig. 1 is a flowchart of a collision type prediction method provided in an embodiment of the present invention. Referring to fig. 1, the collision type prediction method specifically includes:
s110, acquiring ultrasonic sensing data based on a plurality of ultrasonic radars installed on the current vehicle.
Wherein the current vehicle is a vehicle that makes a collision type prediction. The ultrasonic sensing data are data acquired by a plurality of ultrasonic radars, namely ultrasonic data obtained when detecting surrounding vehicles.
Specifically, a plurality of ultrasonic radars are installed at a plurality of preset positions of the current vehicle, and data acquired by the ultrasonic radars are acquired, namely ultrasonic sensing data.
On the basis of the above example, the ultrasonic sensing data may be acquired based on a plurality of ultrasonic radars installed on the current vehicle in the following manner:
under the condition that the distance between the peripheral vehicle and the current vehicle is smaller than or equal to a second preset distance and larger than a first preset distance, carrying out track prediction on the peripheral vehicle;
and stopping track prediction on the peripheral vehicles under the condition that the distance between the peripheral vehicles and the current vehicle is smaller than or equal to a first preset distance, and acquiring ultrasonic sensing data based on a plurality of ultrasonic radars installed on the current vehicle.
Wherein the surrounding vehicles are other vehicles surrounding the current vehicle. The second preset distance is greater than the first preset distance, the second preset distance is a distance threshold value for distinguishing between track prediction and non-track prediction of the surrounding vehicle, and the first preset distance is a distance threshold value for distinguishing between collision type recognition and non-collision type recognition of the surrounding vehicle.
Specifically, the distance between the surrounding vehicles around the current vehicle and the current vehicle is monitored, and when the distance is smaller than or equal to the second preset distance and larger than the first preset distance, the surrounding vehicles are indicated to enter the track prediction range of the current vehicle, so that track prediction is performed on the surrounding vehicles. In the case where the distance between the nearby vehicle and the current vehicle is less than or equal to the first preset distance, it is indicated that there is a possibility that the nearby vehicle collides with the current vehicle at this time, and therefore, it is necessary to stop the trajectory prediction of the nearby vehicle and perform the collision type recognition on the nearby vehicle, that is, perform the operation of acquiring ultrasonic sensing data based on a plurality of ultrasonic radars installed on the current vehicle, so as to facilitate the subsequent recognition of the collision type.
On the basis of the above example, whether the distance between the nearby vehicle and the current vehicle is less than or equal to the first preset distance may be determined by:
If the ultrasonic signal intensity between the current vehicle and the surrounding vehicles is larger than the preset signal intensity, determining that the distance between the surrounding vehicles and the current vehicle is smaller than or equal to the first preset distance.
The ultrasonic signal intensity is the intensity of ultrasonic signals received by the ultrasonic radar and reflected by surrounding vehicles. The preset signal strength is the preset strength of an ultrasonic signal for judging whether the distance between the surrounding vehicle and the current vehicle is smaller than or equal to a first preset distance, and can be calibrated according to the first preset distance.
Specifically, the intensity of the ultrasonic signal reflected by the surrounding vehicles is acquired as the ultrasonic signal intensity according to each ultrasonic radar installed on the current vehicle. If the ultrasonic signal intensity is greater than the preset signal intensity, determining that the distance between the surrounding vehicles and the current vehicle is smaller than or equal to a first preset distance.
On the basis of the above example, the track prediction may be performed on the nearby vehicle in a case where the distance between the nearby vehicle and the current vehicle is less than or equal to the second preset distance and greater than the first preset distance, by:
establishing a vehicle coordinate system according to the current vehicle;
determining the current track prediction times under the condition that the distance between the peripheral vehicle and the current vehicle is smaller than or equal to a second preset distance and larger than a first preset distance, determining the peripheral vehicle coordinates of the peripheral vehicle in a vehicle coordinate system, inputting the current track prediction times and the peripheral vehicle coordinates into a pre-trained track prediction model, and determining a prediction coordinate value;
Judging whether the coordinate difference between the predicted coordinate value and the origin of the vehicle coordinate system is smaller than a preset coordinate difference or not according to the predicted coordinate value;
if so, stopping the operation of determining the coordinates of the surrounding vehicles in the vehicle coordinate system, and executing the operation of acquiring ultrasonic sensing data based on a plurality of ultrasonic radars installed on the current vehicle.
The vehicle coordinate system uses the tail direction head of the current vehicle as the positive direction of a transverse axis, the transverse axis is positioned on the left-right central symmetry plane of the current vehicle, the origin of the transverse axis is the most protruding point of the current vehicle on the left-right central symmetry plane of the current vehicle, the left side of the current vehicle points to the right side of the current vehicle as the positive direction of a longitudinal axis, the longitudinal axis is positioned on a horizontal plane which is perpendicular to the left-right central symmetry plane of the current vehicle and passes through the origin of the transverse axis, the origin of the longitudinal axis and the origin of the transverse axis are the same point, namely the origin of the vehicle coordinate system, and a schematic diagram of the vehicle coordinate system is shown in fig. 2. The current track prediction times are times when current track prediction is performed for surrounding vehicles, it is understood that the position of the next prediction time of each predicted surrounding vehicle is track prediction once, and it is also understood that when the same surrounding vehicle repeatedly enters the track prediction range, the current track prediction times are zeroed when entering each time. The surrounding vehicle coordinates are coordinate values of the surrounding vehicle in the vehicle coordinate system. The trajectory prediction model is a pre-trained coordinate for predicting the surrounding vehicle in the vehicle coordinate system at the next prediction time. The predicted coordinate value is a coordinate value of the surrounding vehicle predicted by the trajectory prediction model in the vehicle coordinate system at the next predicted time. The preset coordinate difference value is used for judging whether collision occurs between the surrounding vehicles and the current vehicle, namely whether the exiting track is needed to be predicted and the coordinate difference value threshold value of collision type identification is needed. The ultrasonic sensing data are data acquired by each ultrasonic radar.
Specifically, a vehicle coordinate system is established for the current vehicle in the following establishing mode: the transverse axis points to the headstock from the tail of the current vehicle and is positioned on the left and right central symmetry plane of the current vehicle, and the origin of the transverse axis is the most prominent point of the current vehicle on the left and right central symmetry plane of the current vehicle; the vertical axis points to the right side from the left side of the current vehicle, is positioned on a horizontal plane which is perpendicular to the left-right central symmetry plane of the current vehicle and passes through the origin of the transverse axis, and the origin of the vertical axis and the origin of the transverse axis are the same point. And under the condition that the distance between the peripheral vehicle and the current vehicle is smaller than or equal to a second preset distance and larger than a first preset distance, determining the current track prediction times of track prediction on the peripheral vehicle at present, and determining the coordinates of the peripheral vehicle in a vehicle coordinate system as the peripheral vehicle coordinates. Further, the current track prediction number and the coordinates of the surrounding vehicle are input into a track prediction model trained in advance, and the model output result is determined as the predicted coordinate value of the surrounding vehicle. Further, a coordinate difference between the predicted coordinate value and the origin of the vehicle coordinate system is calculated, and the coordinate difference is judged to be smaller than the preset coordinate difference, if yes, the fact that the surrounding vehicles need to exit the track prediction process and enter the collision type identification process is indicated, therefore, the operation of determining the surrounding vehicle coordinates of the surrounding vehicles in the vehicle coordinate system is stopped, and the operation of acquiring ultrasonic sensing data based on a plurality of ultrasonic radars installed on the current vehicle is started and executed.
On the basis of the above example, after judging whether or not the coordinate difference between the predicted coordinate value and the origin of the vehicle coordinate system is smaller than the preset coordinate difference, for the case where the coordinate difference is not smaller than the preset coordinate difference, it may be performed by:
if not, acquiring an actual coordinate value with a time corresponding relation with the predicted coordinate value;
judging whether the distance between the surrounding vehicle and the current vehicle is greater than a second preset distance or not under the condition that the difference value between the predicted coordinate value and the actual coordinate value is within a preset error range;
if yes, stopping operation of determining surrounding vehicle coordinates of surrounding vehicles in the vehicle coordinate system;
if not, updating the current track prediction times and the surrounding vehicle coordinates, and returning to execute the operation of inputting the current track prediction times and the surrounding vehicle coordinates into a pre-trained track prediction model to determine the predicted coordinate values.
The actual coordinate value is a coordinate value of the surrounding vehicle having a time correspondence relationship with the predicted coordinate value in the vehicle coordinate system, for example: the predicted coordinate value is a coordinate value in the vehicle coordinate system corresponding to the predicted time T, and the coordinate value of the real surrounding vehicle in the vehicle coordinate system at the time T. The preset error range is a preset error range for judging whether the track prediction is accurate or not.
Specifically, if the coordinate difference between the predicted coordinate value and the origin of the vehicle coordinate system is not less than the preset coordinate difference, it is necessary to determine whether the error of track prediction meets the requirement, that is, obtain the actual coordinate value having a time correspondence with the predicted coordinate value, and determine that the difference between the predicted coordinate value and the actual coordinate value is within the preset error range. If the track prediction is within the preset error range, the track prediction is accurate, and whether the distance between the surrounding vehicle and the current vehicle is larger than a second preset distance or not is judged, namely whether the surrounding vehicle is far away from the current vehicle and is out of the track prediction range or not is judged. If the distance between the surrounding vehicle and the current vehicle is greater than the second preset distance, the surrounding vehicle is far away from the current vehicle to the outside of the track prediction range, so that whether the surrounding vehicle needs to stop track prediction, namely stopping in a vehicle coordinate system, is determined; if the distance between the peripheral vehicle and the current vehicle is not greater than the second preset distance, the peripheral vehicle is indicated to be still within the track prediction range of the current vehicle, so that the current track prediction frequency is updated, namely the current track prediction frequency is increased by one, the coordinates of the peripheral vehicle are required to be updated, the current track prediction frequency and the coordinates of the peripheral vehicle are returned to be input into a pre-trained track prediction model, and the operation of determining the prediction coordinate values is carried out so as to carry out next track prediction on the peripheral vehicle.
On the basis of the above example, after acquiring the actual coordinate value having a time correspondence with the predicted coordinate value, if the difference between the predicted coordinate value and the actual coordinate value is not within the preset error range, it may be performed by:
judging whether the distance between the surrounding vehicle and the current vehicle is smaller than or equal to a first preset distance or not under the condition that the difference value between the predicted coordinate value and the actual coordinate value is not in a preset error range;
if yes, stopping the operation of determining the coordinates of surrounding vehicles of the surrounding vehicles in the vehicle coordinate system, and executing the operation of acquiring ultrasonic sensing data based on a plurality of ultrasonic radars installed on the current vehicle;
if not, based on the predicted coordinate value and the actual coordinate value, updating training parameters corresponding to the current track prediction times in the track prediction model, updating the current track prediction times and the surrounding vehicle coordinates, and returning to execute the operation of inputting the current track prediction times and the surrounding vehicle coordinates into the pre-trained track prediction model to determine the predicted coordinate value.
The training parameters are parameters corresponding to each prediction in the track prediction model, and the training parameters corresponding to each track prediction are different.
Specifically, when the difference between the predicted coordinate value and the actual coordinate value is not within the preset error range, it is indicated that the predicted error corresponding to the number of times of predicting the current track is too large, and the track prediction model needs to be adjusted, however, before the adjustment, in order to ensure the safety of the vehicle, it needs to be determined whether the distance between the surrounding vehicle and the current vehicle is smaller than or equal to the first preset distance, that is, whether there is a collision risk, that is, whether the ultrasonic signal intensity between the current vehicle and the surrounding vehicle is greater than the preset signal intensity. If so, the situation that the collision risk exists with the current vehicle is indicated, and therefore, the track prediction process is exited, the collision type identification process is entered, namely, the operation of determining the coordinates of surrounding vehicles of the surrounding vehicles in the vehicle coordinate system is stopped, and the operation of acquiring ultrasonic sensing data based on a plurality of ultrasonic radars installed on the current vehicle is executed. If not, the fact that the risk of collision with the current vehicle does not exist is indicated, training parameters corresponding to the current track prediction times can be updated, next track prediction can be performed, namely, the training parameters corresponding to the current track prediction times in the track prediction model are updated, the current track prediction times and surrounding vehicle coordinates are updated, and the operation of inputting the current track prediction times and the surrounding vehicle coordinates into the pre-trained track prediction model and determining the prediction coordinate values is performed.
Optionally, the trajectory prediction model is pre-trained based on the following manner:
constructing a sample data set according to the sample track data;
aiming at each sample track in the sample data set, training parameters corresponding to the sample track prediction times in the track prediction model according to the sample track prediction times corresponding to the sample track and sample actual coordinate values corresponding to the sample track prediction times, and updating the track prediction model;
when training parameters corresponding to the number of times of track prediction of each sample in the track prediction model are trained based on each sample track in the sample data set, a track prediction model trained in advance is determined.
The sample track data is track data of a vehicle around the sample in a track prediction range relative to a current vehicle of the sample, the track data comprises sample actual coordinate values corresponding to the track prediction times of each sample, and the time intervals between time points corresponding to the track prediction times of adjacent samples are the same. The sample data set includes the number of times each sample track is predicted in each sample track and the actual sample coordinate value corresponding to the number of times each sample track is predicted.
Specifically, each sample track data acquired in advance is formed into a sample data set. Further, the trajectory prediction model is trained one by one according to each piece of sample trajectory data. And training parameters corresponding to the sample track prediction times in the track prediction model according to the sample track prediction times corresponding to the sample track and the sample actual coordinate values corresponding to the sample track prediction times for each sample track in the sample data set, and taking the model obtained by training as a new track prediction model. And when the training of the track prediction model is completed according to each piece of sample track data, taking the final track prediction model as a pre-trained track prediction model.
Exemplary, the trajectory prediction model isWherein i is the number of sample track predictions, x, y are coordinate values, ++>Is to activate the function so that the trajectory prediction model meets the fit requirement of non-linearity,and->Is the training parameter corresponding to the sample track prediction times i. And determining the sample track prediction times and the actual coordinate values of the samples at preset time intervals delta t in each sample track. Inputting the first group of sample actual coordinate values in the sample data set into a track prediction model to obtain sample prediction coordinate values corresponding to the second group of sample actual coordinate values, and calculating errors between the second group of sample actual coordinate values and the sample prediction coordinate values. If the error meets the preset error requirement, the first group of training parameters are saved, namely the training parameters corresponding to the sample track prediction times 1, and if the error does not meet the preset error requirement, the first group of training parameters are updated, wherein the updating method comprises the following steps: and establishing an error function of the sample predicted coordinate value and the sample actual coordinate value, and updating the set of training parameters by using a gradient method. The above process is repeated, so that training parameters corresponding to the track prediction times of each sample can be obtained, and a pre-trained track prediction model is obtained.
S120, respectively inputting ultrasonic sensing data into the attenuation self-adjustment potential functions which are trained in advance and correspond to the collision types, and determining the type to be collided between the surrounding vehicles and the current vehicle.
Among them, the collision types include a front-side collision, a front-side oblique collision, a front-front collision, and a front-rear collision among face-face collisions, a left front-side collision, a right front-side collision, a left front-left rear collision, and a right front-left front collision among small overlap face-face collisions, and a front-angle collision among face-angle collisions. The attenuation self-adjustment potential function is respectively corresponding to each collision type and is used for judging whether the ultrasonic sensing data belongs to the corresponding collision type. The type to be collided is the predicted collision type of the current vehicle to be collided with surrounding vehicles.
Specifically, ultrasonic sensing data are respectively input into the attenuation self-regulating potential functions which are trained in advance and correspond to the collision types, and a result value output by each attenuation self-regulating potential function is obtained. If the output result value is larger than zero, the group of ultrasonic sensing data possibly belongs to the collision type corresponding to the attenuation self-adjustment potential function. If the output result value is not greater than zero, the group of ultrasonic sensing data is not in the collision type corresponding to the attenuation self-adjustment potential function. And if the collision type which possibly corresponds to the judgment result is that only one collision type exists, the collision type is taken as the type to be collided between the surrounding vehicle and the current vehicle. If at least two collision types which are possibly corresponding to each other are judged, the collision type corresponding to the maximum value in the output result values corresponding to the at least two collision types is used as the type to be collided between the surrounding vehicle and the current vehicle.
The damping self-regulating potential function corresponding to each collision type is trained based on the following mode:
for each collision type, acquiring sample ultrasonic data corresponding to the collision type;
according to the ultrasonic data of the sample, a first range corresponding to a first parameter in an initial self-adjusting potential function is determined, and according to the precision and the density condition of the ultrasonic radar, a second range of the first parameter is determined in the first range, and the first parameter is determined in the second range;
training the initial self-regulating potential function according to the ultrasonic data of the sample to obtain the attenuation self-regulating potential function corresponding to the collision type.
The ultrasonic data of the sample is pre-stored ultrasonic data acquired by the current vehicle before collision. The first parameter is an adjustable parameter that controls the decay rate of the potential function. The first range is a larger range of the first parameter determined from the sample ultrasound data. The second range is a smaller range of the first parameter determined according to the accuracy and the density of the ultrasonic radar, and is smaller than the first range. The initial self-regulating potential function is an untrained initial potential function.
Specifically, according to the collision types, classifying the ultrasonic data of each sample, and determining the ultrasonic data of the sample corresponding to each collision type. For each collision type, a corresponding damping self-adjustment potential function is obtained by training, and therefore, any collision type is taken as an example for illustration. According to the ultrasonic data of the sample, a first range corresponding to a first parameter in the initial self-adjusting potential function is determined, and further, according to the accuracy and the density condition of the ultrasonic radar, a second range smaller than the first range is determined, and an initial first parameter is selected according to the requirement. The initial attenuation self-regulating potential function is constructed according to the first parameter, and is trained through sample ultrasonic data, and a training result is the attenuation self-regulating potential function corresponding to the collision type.
Illustratively, the basic formula for selecting the potential function is:
wherein K is a potential function, X is input data of the potential function, X K For each of the sample ultrasound data,is a first parameter for controlling the decay rate of the potential function. According to the characteristics of the ultrasonic data of the sample, combining the complexity degree of the classification interface among collision types and the accuracy of the sensorAnd the density of the sensor arrangement>The value is adjusted to control the speed of potential function attenuation, improve classification efficiency and accuracy, analyze acquired data in a very short time before collision between surrounding vehicles and the current vehicle, and make correct classification judgment.
In the training process, the correct judgment basis of training is as follows:x is a set formed by sample ultrasonic data corresponding to a certain collision type t Is->Data in (1), n is->The number of data in (i.e.)>. Self-regulating potential function according to attenuation>It can be seen that if->Then->The method comprises the steps of carrying out a first treatment on the surface of the If->Then->. Otherwise, the attenuation self-regulating potential function obtained by training is incorrect. And, a first parameter->The absolute value of (2) can be a larger value so that the decay speed of the potential function is high and the classification efficiency is high. If the classification is correctThe current initial self-regulating potential function is saved for later classification calculations. If the classification error occurs, the current initial self-regulating potential function is updated according to the following formula:
If it isAnd->Then->；
If it isAnd->Then->；
Wherein,for the second parameter in the initial self-regulating potential function, it may be determined according to a training process. In the course of updating the initial self-regulating potential function, the first parameter +.>Further adjusting the absolute value of the potential function, further changing the attenuation speed of the potential function, and controlling the classification efficiency and accuracy until the classification is correct.
On the basis of the above example, before acquiring the sample ultrasonic data corresponding to the collision type for each collision type, the collision type corresponding to each sample ultrasonic data may also be determined, which may specifically be:
for each group of sample ultrasonic data in the collision ultrasonic data set, determining each collision slope of a connecting line between each ultrasonic radar corresponding to each ultrasonic data and a vehicle body reflection point according to each ultrasonic data in the sample ultrasonic data;
determining an initial type corresponding to the ultrasonic data of the group of samples and a slope confidence coefficient corresponding to the initial type according to each piece of ultrasonic data, each collision slope and a preset slope relation corresponding to each collision type;
if the slope confidence coefficient is greater than or equal to the preset confidence coefficient, the initial type is used as the collision type corresponding to the ultrasonic data of the group of samples;
If the slope confidence is less than the preset confidence, determining a collision type corresponding to the set of sample ultrasound data based on a voting method.
The collision ultrasonic data set is a data set formed by pre-acquired sample ultrasonic data before collision. The collision slope is the slope of the connecting line between each ultrasonic radar corresponding to the ultrasonic data of the sample and the reflecting point of the vehicle body. The preset slope relation is a corresponding relation between preset ultrasonic data and collision slope and collision type. The initial type is a collision type determined according to a preset slope relation. The slope confidence is the initial type of confidence determined according to a preset slope relationship. The preset confidence is a confidence threshold for measuring whether the initial type is authentic.
Specifically, for each set of sample ultrasonic data in the collision ultrasonic data set, each collision slope of a connection line between each ultrasonic radar and a vehicle body reflection point is determined according to ultrasonic data corresponding to each ultrasonic radar in the set of sample ultrasonic data. And analyzing each collision slope of the set of sample ultrasonic data in combination with each piece of ultrasonic data according to a preset slope relation corresponding to each collision type, and determining an initial type and a slope confidence corresponding to the initial type. Further, it is necessary to determine whether the initial type is authentic, and compare the slope confidence with a preset confidence. If the slope confidence is greater than or equal to the preset confidence, indicating that the initial type is relatively trusted, and therefore, the initial type can be used as a collision type corresponding to the set of sample ultrasonic data; if the slope confidence is less than the preset confidence, the initial type is not reliable enough, so that the group of sample ultrasonic data is classified based on a voting method, and the collision type corresponding to the group of sample ultrasonic data is determined.
By way of example, fig. 3 is a schematic diagram of an ultrasonic radar of a current vehicle, wherein 1-5 are 5 ultrasonic radars. Fig. 4 is a schematic view of a front-side collision, fig. 5 is a schematic view of a front-side collision, fig. 6 is a schematic view of a front-front collision, and fig. 7 is a schematic view of a front-rear collision. As can be seen from fig. 4 to fig. 7, the slope of the line between all the ultrasonic radars and the vehicle body reflection point is the same, and the line is determined as a face-face collision, but the corresponding perceived distances of the ultrasonic radars are different, so that different specific types under the face-face collision can be distinguished. Fig. 8 is a schematic view of a left front-side collision, fig. 9 is a schematic view of a right front-side collision, fig. 10 is a schematic view of a left front-left rear collision, and fig. 11 is a schematic view of a right front-left front collision. As can be seen from fig. 8, the ultrasonic data acquired by the ultrasonic radars 1 to 3 included in the collision surface are all vertical distances to the side of the surrounding vehicle, the slope of the line between all the ultrasonic radars corresponding to the collision surface and the vehicle body reflection point is the same, and the ultrasonic radars 4 and 5 corresponding to the non-collision surface are not identical and are all distances to the rear corner of the vehicle body side of the surrounding vehicle. The same can be done for the predetermined slope relationships corresponding to fig. 9-11. Fig. 12 is a schematic view of a frontal-angular collision. As shown in fig. 12, when the left front corner of the surrounding vehicle is in the detection range of the ultrasonic radar, all the distances of the ultrasonic radar are the distances to a certain angle, and the connection line of the ultrasonic sensor to the reflection point of the vehicle body is not parallel due to the irregular shape of the vehicle body, so that the preset slope relationship can be constructed.
On the basis of the above example, after determining the type of collision to be between the surrounding vehicle and the current vehicle, the passive safety device may also be triggered by:
and determining a safety device response parameter according to the type to be collided, and adjusting the passive safety device of the current vehicle according to the safety device response parameter.
Wherein the safety device response parameter is an actuation threshold parameter at the corresponding actuation of the passive safety device, such as the response threshold of the airbag, etc. Passive safety devices are devices for passive triggering to protect driver and passenger safety in the event of a vehicle collision, such as: safety air bags, side air curtains, emergency braking or emergency avoidance actions and other protection strategies.
Specifically, response parameters of the safety device corresponding to various collision types are constructed in advance according to different collision types, so that the distinction processing of the passive safety device corresponding to different collision types is realized. According to the type to be collided, determining a safety device response parameter corresponding to the type to be collided, and adjusting the passive safety device of the current vehicle according to the determined safety device response parameter so that the passive safety device of the current vehicle can adapt to the impending collision of the type to be collided.
In the identification of the entering collision type, the collision prompt sound of the current vehicle can be started in advance to send out collision prompts to personnel in the vehicle, and the response threshold of the safety air bag can be reduced, so that a series of preparation works such as the response time of the air bag and the pre-tightening of the safety belt can be reduced, the type to be collided is predicted to be obtained, and then the passive safety device is further adaptively adjusted.
For example, different response parameter settings of the passive safety device at different positions can be performed according to different collision types, so as to adjust the passive safety device in a targeted manner.
It can be understood that, under the condition that the distance between the peripheral vehicle and the current vehicle is smaller than or equal to the second preset distance and larger than the first preset distance, the track prediction efficiency and accuracy are improved, under the condition that the distance between the peripheral vehicle and the current vehicle is smaller than or equal to the first preset distance, the track prediction of the peripheral vehicle is stopped, based on a plurality of ultrasonic radars installed on the current vehicle, ultrasonic sensing data are acquired, the ultrasonic sensing data are respectively input into attenuation self-adjusting potential functions corresponding to each collision type trained in advance, the type to be collided between the peripheral vehicle and the current vehicle is determined, and the effect of accurately predicting the running track and the collision type of the peripheral vehicle in real time under various complex collision conditions by adopting a strategy combining track prediction and collision type prediction is achieved.
The embodiment has the following technical effects: the method has the advantages that ultrasonic sensing data are acquired based on a plurality of ultrasonic radars installed on the current vehicle, the ultrasonic sensing data are respectively input into the attenuation self-adjustment potential functions which are trained in advance and correspond to each collision type, the type to be collided between the surrounding vehicle and the current vehicle is determined, the attenuation self-adjustment potential functions are adopted, the collision types of the current vehicle and the surrounding vehicle are accurately predicted in real time under various complex collision conditions, the problem that a passive safety device is triggered by mistake due to the fact that the collision probability and the intensity threshold value are too low is solved, in addition, the accuracy and the robustness of collision type determination are greatly improved, and the protection effect is improved.
Fig. 13 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. As shown in fig. 13, the electronic device 400 includes one or more processors 401 and memory 402.
The processor 401 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities and may control other components in the electronic device 400 to perform desired functions.
Memory 402 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random Access Memory (RAM) and/or cache memory (cache), and the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, and the like. One or more computer program instructions may be stored on the computer readable storage medium that may be executed by the processor 401 to implement the calibration method and/or other desired functions of the vehicle-mounted BSD camera of any of the embodiments of the present invention described above. Various content such as initial arguments, thresholds, etc. may also be stored in the computer readable storage medium.
In one example, the electronic device 400 may further include: an input device 403 and an output device 404, which are interconnected by a bus system and/or other forms of connection mechanisms (not shown). The input device 403 may include, for example, a keyboard, a mouse, and the like. The output device 404 may output various information to the outside, including early warning prompt information, braking force, etc. The output device 404 may include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, etc.
Of course, only some of the components of the electronic device 400 that are relevant to the present invention are shown in fig. 13 for simplicity, components such as buses, input/output interfaces, etc. are omitted. In addition, electronic device 400 may include any other suitable components depending on the particular application.
In addition to the methods and apparatus described above, embodiments of the invention may also be a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to perform the steps of the collision type prediction method provided by any of the embodiments of the invention.
The computer program product may write program code for performing operations of embodiments of the present invention in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present invention may also be a computer-readable storage medium, on which computer program instructions are stored, which, when being executed by a processor, cause the processor to perform the steps of the collision type prediction method provided by any of the embodiments of the present invention.
The computer readable storage medium may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of the present application. As used in this specification, the terms "a," "an," "the," and/or "the" are not intended to be limiting, but rather are to be construed as covering the singular and the plural, unless the context clearly dictates otherwise. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method or apparatus comprising such elements.
It should also be noted that the positional or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the positional or positional relationship shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the apparatus or element in question must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. Unless specifically stated or limited otherwise, the terms "mounted," "connected," and the like are to be construed broadly and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.
Claims (10)
1. A collision type prediction method, characterized by comprising:
acquiring ultrasonic sensing data based on a plurality of ultrasonic radars installed on a current vehicle;
respectively inputting the ultrasonic sensing data into a pre-trained attenuation self-adjustment potential function corresponding to each collision type, and determining the type to be collided between the surrounding vehicles and the current vehicle;
the damping self-regulating potential function corresponding to each collision type is trained based on the following mode:
for each collision type, acquiring sample ultrasonic data corresponding to the collision type;
determining a first range corresponding to a first parameter in an initial self-adjusting potential function according to the sample ultrasonic data, determining a second range of the first parameter in the first range according to the precision and the density condition of the ultrasonic radar, and determining the first parameter in the second range;
and training the initial self-regulating potential function according to the sample ultrasonic data to obtain an attenuation self-regulating potential function corresponding to the collision type.
2. The method of claim 1, further comprising, prior to said acquiring, for each collision type, sample ultrasound data corresponding to said collision type:
For each group of sample ultrasonic data in the collision ultrasonic data set, determining each collision slope of a connecting line between each ultrasonic radar corresponding to each ultrasonic data and a vehicle body reflection point according to each ultrasonic data in the sample ultrasonic data;
determining an initial type corresponding to the ultrasonic data of the group of samples and a slope confidence coefficient corresponding to the initial type according to each piece of ultrasonic data, each collision slope and a preset slope relation corresponding to each collision type;
if the slope confidence coefficient is greater than or equal to the preset confidence coefficient, the initial type is used as a collision type corresponding to the group of sample ultrasonic data;
and if the slope confidence coefficient is smaller than the preset confidence coefficient, determining the collision type corresponding to the group of sample ultrasonic data based on a voting method.
3. The method of claim 1, wherein the acquiring ultrasonic sensing data based on a plurality of ultrasonic radars installed on a current vehicle comprises:
under the condition that the distance between the peripheral vehicle and the current vehicle is smaller than or equal to a second preset distance and larger than a first preset distance, carrying out track prediction on the peripheral vehicle; wherein the second preset distance is greater than the first preset distance;
And stopping track prediction on the peripheral vehicles under the condition that the distance between the peripheral vehicles and the current vehicle is smaller than or equal to the first preset distance, and acquiring ultrasonic sensing data based on a plurality of ultrasonic radars installed on the current vehicle.
4. A method according to claim 3, wherein the performing track prediction on the surrounding vehicle in a case where the distance between the surrounding vehicle and the current vehicle is less than or equal to a second preset distance and greater than a first preset distance comprises:
establishing a vehicle coordinate system according to the current vehicle;
determining the current track prediction times under the condition that the distance between the peripheral vehicle and the current vehicle is smaller than or equal to a second preset distance and larger than a first preset distance, determining the peripheral vehicle coordinates of the peripheral vehicle in the vehicle coordinate system, inputting the current track prediction times and the peripheral vehicle coordinates into a pre-trained track prediction model, and determining a prediction coordinate value;
judging whether the coordinate difference between the predicted coordinate value and the origin of the vehicle coordinate system is smaller than a preset coordinate difference or not according to the predicted coordinate value;
If yes, stopping the operation of determining the coordinates of surrounding vehicles in the vehicle coordinate system, and executing the operation of acquiring ultrasonic sensing data based on a plurality of ultrasonic radars installed on the current vehicle.
5. The method according to claim 4, further comprising, after said determining whether a coordinate difference between the predicted coordinate value and an origin of the vehicle coordinate system is less than a preset coordinate difference:
if not, acquiring an actual coordinate value with a time corresponding relation with the predicted coordinate value;
judging whether the distance between the surrounding vehicle and the current vehicle is greater than the second preset distance or not under the condition that the difference value between the predicted coordinate value and the actual coordinate value is within a preset error range;
if yes, stopping the operation of determining the surrounding vehicle coordinates of the surrounding vehicle in the vehicle coordinate system;
if not, updating the current track prediction times and the surrounding vehicle coordinates, and returning to execute the operation of inputting the current track prediction times and the surrounding vehicle coordinates into a pre-trained track prediction model to determine the predicted coordinate values.
6. The method according to claim 5, further comprising, after the acquiring the actual coordinate value having a temporal correspondence with the predicted coordinate value:
judging whether the distance between the surrounding vehicle and the current vehicle is smaller than or equal to the first preset distance or not under the condition that the difference value between the predicted coordinate value and the actual coordinate value is not in a preset error range;
if yes, stopping the operation of determining the coordinates of surrounding vehicles in the vehicle coordinate system, and executing the operation of acquiring ultrasonic sensing data based on a plurality of ultrasonic radars installed on the current vehicle;
if not, based on the predicted coordinate value and the actual coordinate value, updating training parameters corresponding to the current track prediction times in the track prediction model, updating the current track prediction times and the surrounding vehicle coordinates, and returning to execute the operation of inputting the current track prediction times and the surrounding vehicle coordinates into a pre-trained track prediction model to determine predicted coordinate values.
7. The method of claim 4, wherein the trajectory prediction model is pre-trained based on:
Constructing a sample data set according to the sample track data; the sample data set comprises sample track prediction times in each sample track and sample actual coordinate values corresponding to the sample track prediction times;
aiming at each sample track in the sample data set, training parameters corresponding to each sample track prediction frequency in a track prediction model according to each sample track prediction frequency corresponding to the sample track and sample actual coordinate values corresponding to each sample track prediction frequency, and updating the track prediction model;
and determining a pre-trained track prediction model under the condition that training parameters corresponding to the track prediction times of each sample in the track prediction model are trained based on each sample track in the sample data set.
8. The method according to claim 1, characterized by further comprising, after said determining a type of collision to be between a nearby vehicle and said current vehicle:
and determining a safety device response parameter according to the type to be collided, and adjusting the passive safety device of the current vehicle according to the safety device response parameter.
9. An electronic device, the electronic device comprising:
a processor and a memory;
the processor is configured to execute the steps of the collision type prediction method according to any one of claims 1 to 8 by calling a program or instructions stored in the memory.
10. A computer-readable storage medium storing a program or instructions that cause a computer to execute the steps of the collision type prediction method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311514396.7A CN117250602B (en) | 2023-11-15 | 2023-11-15 | Collision type prediction method, apparatus, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311514396.7A CN117250602B (en) | 2023-11-15 | 2023-11-15 | Collision type prediction method, apparatus, and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117250602A true CN117250602A (en) | 2023-12-19 |
| CN117250602B CN117250602B (en) | 2024-03-15 |
Family
ID=89137179
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311514396.7A Active CN117250602B (en) | 2023-11-15 | 2023-11-15 | Collision type prediction method, apparatus, and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117250602B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5684701A (en) * | 1995-06-07 | 1997-11-04 | Automotive Technologies International, Inc. | Method and apparatus for sensing a vehicle crash |
| GB9722900D0 (en) * | 1997-10-31 | 1998-01-07 | Automotive Tech Int | Method and apparatus for sensing a vehicle crash |
| US7124027B1 (en) * | 2002-07-11 | 2006-10-17 | Yazaki North America, Inc. | Vehicular collision avoidance system |
| DE102016218549B3 (en) * | 2016-09-27 | 2017-12-28 | Audi Ag | Method for determining a collision-related forecast result |
| CN107848478A (en) * | 2015-07-10 | 2018-03-27 | 宝马股份公司 | The automatic identification of low speed collision and assessment |
| CN108615229A (en) * | 2018-03-09 | 2018-10-02 | 南京信息工程大学 | Collision detection optimization method based on curvature points cluster and decision tree |
| US10997800B1 (en) * | 2020-01-22 | 2021-05-04 | Zendrive, Inc. | Method and system for vehicular collision reconstruction |
| US20220161767A1 (en) * | 2020-11-23 | 2022-05-26 | Aptiv Technologies Limited | System and Method for Predicting Road Collisions with a Host Vehicle |
| CN116013110A (en) * | 2023-01-03 | 2023-04-25 | 重庆长安汽车股份有限公司 | Vehicle collision risk prediction device and method |
| CN116215520A (en) * | 2023-03-28 | 2023-06-06 | 长江大学 | Vehicle collision early warning and processing method and device based on ultrasonic waves and 3D looking around |
| CN116363769A (en) * | 2023-03-31 | 2023-06-30 | 成都路行通信息技术有限公司 | Vehicle collision monitoring method and system |
-
2023
- 2023-11-15 CN CN202311514396.7A patent/CN117250602B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5684701A (en) * | 1995-06-07 | 1997-11-04 | Automotive Technologies International, Inc. | Method and apparatus for sensing a vehicle crash |
| GB9722900D0 (en) * | 1997-10-31 | 1998-01-07 | Automotive Tech Int | Method and apparatus for sensing a vehicle crash |
| US7124027B1 (en) * | 2002-07-11 | 2006-10-17 | Yazaki North America, Inc. | Vehicular collision avoidance system |
| CN107848478A (en) * | 2015-07-10 | 2018-03-27 | 宝马股份公司 | The automatic identification of low speed collision and assessment |
| DE102016218549B3 (en) * | 2016-09-27 | 2017-12-28 | Audi Ag | Method for determining a collision-related forecast result |
| CN108615229A (en) * | 2018-03-09 | 2018-10-02 | 南京信息工程大学 | Collision detection optimization method based on curvature points cluster and decision tree |
| US10997800B1 (en) * | 2020-01-22 | 2021-05-04 | Zendrive, Inc. | Method and system for vehicular collision reconstruction |
| US20220161767A1 (en) * | 2020-11-23 | 2022-05-26 | Aptiv Technologies Limited | System and Method for Predicting Road Collisions with a Host Vehicle |
| CN116013110A (en) * | 2023-01-03 | 2023-04-25 | 重庆长安汽车股份有限公司 | Vehicle collision risk prediction device and method |
| CN116215520A (en) * | 2023-03-28 | 2023-06-06 | 长江大学 | Vehicle collision early warning and processing method and device based on ultrasonic waves and 3D looking around |
| CN116363769A (en) * | 2023-03-31 | 2023-06-30 | 成都路行通信息技术有限公司 | Vehicle collision monitoring method and system |
Non-Patent Citations (1)
| Title |
|---|
| 吴战国吴华钰吴菁: "汽车碰撞类型的非线性判别函数分类器设计", 机电一体化, vol. 23, no. 9, pages 49 - 51 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117250602B (en) | 2024-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103863321B (en) | Collision judgment equipment and anti-collision equipment | |
| US8781720B2 (en) | Vehicle travel track estimator | |
| CN104276121B (en) | Control system, vehicle and the method for controlling security parameter of vehicle safety parameter | |
| KR101690352B1 (en) | Collision monitor for a motor vehicle | |
| US8138900B2 (en) | Method and device for crash type identification for a vehicle | |
| JP6855776B2 (en) | Object detection device and object detection method | |
| US20170080929A1 (en) | Movement-assisting device | |
| CN104118382A (en) | Collision determination device, collision mitigation device, and collision determination method | |
| KR101377036B1 (en) | Parking assist apparstus and method for controlling parking of the same | |
| US20160236681A1 (en) | Vehicle driving situation determination apparatus and vehicle driving situation determination method | |
| US11926299B2 (en) | System and method for predicting road collisions with a host vehicle | |
| KR102106345B1 (en) | Rear-side alert system and controlling method thereof | |
| US11837095B2 (en) | Alarm device for vehicle | |
| US11631255B2 (en) | Apparatus and method for controlling door opening | |
| CN117250602B (en) | Collision type prediction method, apparatus, and storage medium | |
| US20190291731A1 (en) | Vehicle control apparatus and vehicle control method | |
| KR20130019908A (en) | System for predicting the possibility or impossibility of vehicle parking using support vector machine | |
| US20050004719A1 (en) | Device and method for determining the position of objects in the surroundings of a motor vehicle | |
| CN111391818B (en) | Controlling a vehicle using a control system | |
| JP5870871B2 (en) | Image processing apparatus and vehicle control system using the image processing apparatus | |
| US11358593B2 (en) | Dual direction accident prevention and assistive braking system | |
| JP4683910B2 (en) | Collision prevention support device | |
| JP5098370B2 (en) | Collision prediction device | |
| CN113511161A (en) | Pedestrian protection method, device, sensing equipment and storage medium | |
| KR102544335B1 (en) | Distance detection apparatus, collision prevention apparatus and collision prevention method using thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |