CN109631915B - Trajectory prediction method, apparatus, device and computer readable storage medium - Google Patents
Trajectory prediction method, apparatus, device and computer readable storage medium Download PDFInfo
- Publication number
- CN109631915B CN109631915B CN201811554353.0A CN201811554353A CN109631915B CN 109631915 B CN109631915 B CN 109631915B CN 201811554353 A CN201811554353 A CN 201811554353A CN 109631915 B CN109631915 B CN 109631915B
- Authority
- CN
- China
- Prior art keywords
- acceleration
- moment
- vehicle
- time
- obstacle
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The embodiment of the invention provides a track prediction method, a track prediction device, track prediction equipment and a computer readable storage medium, wherein the track prediction method comprises the following steps: acquiring environmental data at a first moment, and calculating the acceleration of the obstacle vehicle at the first moment by using an acceleration prediction model according to the environmental data; calculating the position of the obstacle vehicle at a second moment according to the acceleration, the speed and the position of the obstacle vehicle at the first moment; calculating the acceleration of the obstacle vehicle at a first moment by using an acceleration prediction model according to the environment data at the first moment, wherein the obstacle vehicle is not taken as an object moving at a constant speed or as a stationary object; the position of the obstacle vehicle at the second moment is calculated according to the acceleration, the speed and the position of the obstacle vehicle at the first moment, so that the accuracy of the obstacle vehicle track prediction is improved, and the running safety of the unmanned vehicle is improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of unmanned driving, in particular to a track prediction method, a track prediction device, track prediction equipment and a computer readable storage medium.
Background
In the path planning in the unmanned driving field, an automatic driving system needs to predict the track of surrounding obstacle vehicles, and the predicted track is used in a path planning link, so that a path planning algorithm can process complex road conditions.
During the driving process of the obstacle vehicle, the obstacle vehicle does not drive at a uniform speed. However, in the conventional method for predicting the trajectory of the obstacle vehicle, the obstacle vehicle is generally assumed to travel at a constant speed, and the position of the obstacle vehicle at the next time is predicted from the position and the speed of the obstacle vehicle at the previous time, so that the trajectory of the obstacle vehicle is not accurately predicted.
Disclosure of Invention
The embodiment of the invention provides a track prediction method, a track prediction device, track prediction equipment and a computer readable storage medium, which are used for solving the problem that the track of an obstacle vehicle is not accurately predicted by the existing track prediction method of the obstacle vehicle.
One aspect of the embodiments of the present invention is to provide a trajectory prediction method, including:
acquiring environmental data at a first moment, wherein the environmental data at least comprises: the speed and the shape parameters of the obstacle vehicle within a preset range, the speed and the shape parameters of the vehicle and the distance between any two vehicles within the preset range;
calculating the acceleration of the obstacle vehicle at the first moment by utilizing an acceleration prediction model according to the environment data;
and calculating the position of the obstacle vehicle at a second moment according to the acceleration, the speed and the position of the obstacle vehicle at the first moment.
Another aspect of the embodiments of the present invention is to provide a trajectory prediction apparatus, including:
an environment data obtaining module, configured to obtain environment data at a first time, where the environment data at least includes: the speed and the shape parameters of the obstacle vehicle within a preset range, the speed and the shape parameters of the vehicle and the distance between any two vehicles within the preset range;
the acceleration calculation module is used for calculating the acceleration of the obstacle vehicle at the first moment by utilizing an acceleration prediction model according to the environment data;
and the position calculation module is used for calculating the position of the obstacle vehicle at a second moment according to the acceleration, the speed and the position of the obstacle vehicle at the first moment.
Another aspect of an embodiment of the present invention is to provide a terminal device, including:
a memory, a processor, and a computer program stored on the memory and executable on the processor,
the processor implements the trajectory prediction method described above when running the computer program.
It is another aspect of an embodiment of the present invention to provide a computer-readable storage medium, storing a computer program,
the computer program, when executed by a processor, implements the trajectory prediction method described above.
According to the track prediction method, the track prediction device, the track prediction equipment and the computer readable storage medium, the obstacle vehicle is not taken as an object moving at a constant speed or a stationary object, but the acceleration of the obstacle vehicle at the first moment is calculated by utilizing an acceleration prediction model according to the environment data at the first moment; and calculating the position of the obstacle vehicle at the second moment according to the acceleration, the speed and the position of the obstacle vehicle at the first moment, so that the accuracy of the obstacle vehicle track prediction is improved, and the running safety of the unmanned vehicle is improved.
Drawings
FIG. 1 is a flowchart of a trajectory prediction method according to an embodiment of the present invention;
FIG. 2 is a flowchart of a trajectory prediction method according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of an acceleration prediction model according to a second embodiment of the present invention;
fig. 4 is a schematic structural diagram of a trajectory prediction apparatus according to a third embodiment of the present invention;
fig. 5 is a schematic structural diagram of a trajectory prediction apparatus according to a fourth embodiment of the present invention;
fig. 6 is a schematic structural diagram of a terminal device according to a fifth embodiment of the present invention.
With the above figures, certain embodiments of the invention have been illustrated and described in more detail below. The drawings and written description are not intended to limit the scope of the inventive concepts in any way, but rather to illustrate the inventive concepts to those skilled in the art by reference to specific embodiments.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with embodiments of the invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of embodiments of the invention, as detailed in the following claims.
The terms "first", "second", etc. referred to in the embodiments of the present invention are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. In the description of the following examples, "plurality" means two or more unless specifically limited otherwise.
The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present invention will be described below with reference to the accompanying drawings.
Example one
Fig. 1 is a flowchart of a trajectory prediction method according to an embodiment of the present invention. The embodiment of the invention provides a track prediction method aiming at the problem that the track of an obstacle vehicle is not accurately predicted by the conventional track prediction method of the obstacle vehicle.
The method in this embodiment is applied to a terminal device, which may be a vehicle-mounted terminal, and the like, and in other embodiments, the method may also be applied to other devices, and this embodiment takes the vehicle-mounted terminal as an example for schematic description. As shown in fig. 1, the method comprises the following specific steps:
step S101, obtaining environmental data of a first moment, wherein the environmental data at least comprises: the speed and profile parameters of the obstacle vehicle, the speed and profile parameters of the vehicle, and the distance between any two vehicles within the preset range.
The preset range may be a circular area having a preset distance as a radius and a current position of the vehicle as a center. The preset distance can be determined according to the coverage range of a sensor used for acquiring data on the vehicle, the preset range is the coverage range of the sensor of the vehicle, and the vehicle can acquire environmental data in the preset range.
In addition, the preset range may be set by a technician according to an actual vehicle and an application scenario, and the embodiment is not specifically limited herein.
The obstacle vehicle is a vehicle around the own vehicle, and may be another vehicle in a range covered by the own vehicle when the own vehicle acquires the environment data. During driving, other surrounding vehicles can be understood as dynamic obstacles on the driving road relative to the vehicle. In the running process of the vehicle, surrounding obstacle vehicles can change at different moments.
In this embodiment, the first time may be a current time, the host vehicle acquires environment data of the current time in real time, and predicts a position of the obstacle vehicle at a second time in the future by using the trajectory prediction method provided in this embodiment.
The vehicle-mounted terminal can acquire the environmental data at least comprises the following steps: the speed and profile of the obstacle vehicle, the speed and profile of the subject vehicle, and the distance between any two vehicles. The environment data may also include other data that can be acquired by the vehicle-mounted terminal and that may interactively affect the driving of the vehicle, such as road data, and the embodiment is not limited in this respect.
Step S102, calculating the acceleration of the obstacle vehicle at a first moment by using an acceleration prediction model according to the environment data.
After the environmental data at the first moment are acquired, the environmental data are input into a trained acceleration prediction model, and the acceleration of the obstacle vehicle at the first moment is predicted through the acceleration prediction model.
In this embodiment, a neural network model for predicting the acceleration of the vehicle is previously constructed, and the neural network model is trained by using a large amount of real historical driving data as training data to obtain an acceleration prediction model. The acceleration prediction model can accurately predict the acceleration of the obstacle vehicle at a moment in the environmental data according to the environmental data at the moment.
And step S103, calculating the position of the obstacle vehicle at the second moment according to the acceleration, the speed and the position of the obstacle vehicle at the first moment.
After the acceleration of the obstacle vehicle at the first time is obtained, the position of the obstacle vehicle at a second, later time may be calculated using the kinetic equation based on the acceleration, velocity, and position of the obstacle vehicle at the first time.
According to the embodiment of the invention, the obstacle vehicle is not taken as a moving object at a constant speed, nor is the obstacle vehicle taken as a static object, but the acceleration of the obstacle vehicle at the first moment is calculated by utilizing an acceleration prediction model according to the environmental data at the first moment; the position of the obstacle vehicle at the second moment is calculated according to the acceleration, the speed and the position of the obstacle vehicle at the first moment, so that the accuracy of the obstacle vehicle track prediction is improved, and the running safety of the unmanned vehicle is improved.
Example two
FIG. 2 is a flowchart of a trajectory prediction method according to a second embodiment of the present invention; fig. 3 is a schematic structural diagram of an acceleration prediction model according to a second embodiment of the present invention. In addition to the first embodiment, the present embodiment further includes a calculation unit that calculates an acceleration of the obstacle vehicle at a first time point by using an acceleration prediction model based on the environment data, the calculation unit further including: and performing model training on a preset neural network model by using a training set to obtain an acceleration prediction model. As shown in fig. 2, the method comprises the following specific steps:
step S201, a training set is obtained.
The training set comprises a plurality of pieces of training data, each piece of training data comprises real environment data at a first historical moment, and the acceleration of a vehicle in the real environment data at a second historical moment is subjected to model training on a preset neural network model by using the training set to obtain an acceleration prediction model.
In this embodiment, a neural network model for predicting the acceleration of the vehicle is previously constructed, and the neural network model is trained by using a large amount of real historical driving data as training data to obtain an acceleration prediction model. The acceleration prediction model can accurately predict the acceleration of the obstacle vehicle at a moment in the environmental data according to the environmental data at the moment.
Optionally, Δ t represents a time interval between the second historical time and the first historical time, Δ t 'represents a time interval between the second time and the first time, and | Δ t- Δ t' | < the preset time error.
The vehicle-mounted terminal can acquire the environmental data at least comprises the following steps: the speed and profile of the obstacle vehicle, the speed and profile of the subject vehicle, and the distance between any two vehicles. The environment data may also include other data that can be acquired by the vehicle-mounted terminal and that may interactively affect the driving of the vehicle, such as road data, and the embodiment is not limited in this respect.
And S202, performing model training on a preset neural network model by using a training set to obtain an acceleration prediction model.
In this embodiment, the preset neural network model may include: a convolutional layer, a Linear rectification function (modulated Linear Unit, referred to as ReLU for short), a maximum pooling layer, a full link layer, a bn (batch normalization) layer, an inactive layer (also referred to as DropOut layer), a cyclic neural network coding layer, and a cyclic neural network decoding layer.
Optionally, the cyclic neural network coding layer and the cyclic neural network decoding layer may be implemented by using a Long Short-Term Memory network (LSTM).
The neural network structure shown in fig. 3, wherein Conv denotes a convolutional layer, ReLU denotes a ReLU layer, MaxPool denotes a max pooling layer, FC denotes a fully connected layer, BN denotes a BN layer, DropOut denotes a DropOut layer, and LSTM adjacent to the DropOut layer denotes a cyclic neural network coding layer. The part from the convolutional layer to the cyclic neural network coding layer can be understood as a coding process. The LSTM after the recurrent neural network coding layer is the recurrent neural network decoding layer, which can be understood as a process of decoding the coded result. Wherein, the convolution layer, the ReLU layer and the maximum pooling layer form a Convolutional Neural network (CNN for short); the full connection layer, the BN layer, and the DropOut layer form a full Convolutional neural network (FCN).
In this embodiment, a training set is used to perform model training on a preset neural network model to obtain an acceleration prediction model, which can be implemented by using the existing model training method, and this embodiment is not described herein again.
Optionally, the loss function term used in the training process includes the following three parts: the method comprises a fitting loss term, a punishment loss term and a smooth loss term, wherein the three loss terms are formed according to a preset proportion. The purpose of the fitting loss item is to enable the neural network to fit the positive and negative of the real acceleration, the penalty item can enable the difference between the predicted track and the real track not to exceed a set threshold, and the purpose of the smoothing item can improve the signal-to-noise ratio of the predicted data.
The preset ratio and the set threshold may be set by a technician according to experience, and this embodiment is not specifically limited herein.
Optionally, the predicted acceleration may be processed by a kalman filter algorithm and a kalman smoothing algorithm to obtain an indirect acceleration, the predicted acceleration and the indirect acceleration are input into a loss function, and a final predicted acceleration is obtained by solving with a gradient descent algorithm.
After the acceleration prediction model is obtained, trajectory prediction may be performed using the acceleration prediction model through steps S203-S205.
Step S203, acquiring environmental data at the first time, where the environmental data at least includes: the speed and profile parameters of the obstacle vehicle, the speed and profile parameters of the vehicle, and the distance between any two vehicles within the preset range.
The preset range may be a circular area with the current position of the vehicle as a center and the preset distance as a radius. The preset distance can be determined according to the coverage range of a sensor used for acquiring data on the vehicle, the preset range is the coverage range of the sensor of the vehicle, and the vehicle can acquire environmental data in the preset range.
In addition, the preset range may be set by a technician according to an actual vehicle and an application scenario, and the embodiment is not specifically limited herein.
The obstacle vehicle is a vehicle around the own vehicle, and may be another vehicle in a range covered by the own vehicle when the own vehicle acquires the environment data. During driving, other surrounding vehicles can be understood as dynamic obstacles on the driving road relative to the vehicle. In the running process of the vehicle, surrounding obstacle vehicles can change at different moments.
In this embodiment, the first time may be a current time, the host vehicle acquires environment data of the current time in real time, and predicts a position of the obstacle vehicle at a second time in the future by using the trajectory prediction method provided in this embodiment.
Step S204, calculating the acceleration of the obstacle vehicle at the first moment by using an acceleration prediction model according to the environment data.
After the environmental data at the first moment are acquired, the environmental data are input into a trained acceleration prediction model, and the acceleration of the obstacle vehicle at the first moment is predicted through the acceleration prediction model.
And step S205, calculating the position of the obstacle vehicle at the second moment according to the acceleration, the speed and the position of the obstacle vehicle at the first moment.
After the acceleration of the obstacle vehicle at the first time is obtained, the position of the obstacle vehicle at a second, later time may be calculated using the kinetic equation based on the acceleration, velocity, and position of the obstacle vehicle at the first time.
In this embodiment, there may be one or more obstacle vehicles within the preset range. If a plurality of obstacle vehicles are included in the preset range, the position of each obstacle vehicle at the second moment is calculated in the step.
Specifically, each obstacle vehicle is taken as a target vehicle, and the position of the target vehicle at the second moment is calculated according to the acceleration, the speed and the position of the target vehicle at the first moment, so that the position of each obstacle vehicle at the second moment is obtained.
Further, the position of the target vehicle at the second time is calculated according to the acceleration, the speed and the position of the target vehicle at the first time, which can be specifically realized by the following steps:
calculating the position of the target vehicle at the second time using the following kinematic equation:
wherein p istAnd pt-1Are all a function of position, ptIndicating the position of the target vehicle at the second moment in time, pt-1Indicating the position of the target vehicle at a first moment in time, vt-1Representing the speed of the target vehicle at a first moment, at-1Represents the acceleration of the target vehicle at a first time, at represents the interval period between the first time and a second time,
representing a position function pt-1The remainder of the taylor expansion of (1).
According to the embodiment of the invention, the obstacle vehicle is not taken as a moving object at a constant speed, nor is the obstacle vehicle taken as a static object, but the acceleration of the obstacle vehicle at the first moment is calculated by utilizing an acceleration prediction model according to the environmental data at the first moment; the position of the obstacle vehicle at the second moment is calculated according to the acceleration, the speed and the position of the obstacle vehicle at the first moment, so that the accuracy of the obstacle vehicle track prediction is improved, and the running safety of the unmanned vehicle is improved.
EXAMPLE III
Fig. 4 is a schematic structural diagram of a trajectory prediction apparatus according to a third embodiment of the present invention. The trajectory prediction device provided by the embodiment of the invention can execute the processing flow provided by the trajectory prediction method embodiment. As shown in fig. 4, the trajectory prediction device 30 includes: an environment data acquisition module 301, an acceleration calculation module 302 and a position calculation module 303.
Specifically, the environment data obtaining module 301 is configured to obtain environment data at a first time, where the environment data at least includes: the speed and the shape parameters of the obstacle vehicle within a preset range, the speed and the shape parameters of the vehicle, and the distance between any two vehicles within the preset range.
And the acceleration calculation module 302 is used for calculating the acceleration of the obstacle vehicle at the first moment by utilizing the acceleration prediction model according to the environment data.
And the position calculating module 303 is used for calculating the position of the obstacle vehicle at the second moment according to the acceleration, the speed and the position of the obstacle vehicle at the first moment.
The apparatus provided in the embodiment of the present invention may be specifically configured to execute the method embodiment provided in the first embodiment, and specific functions are not described herein again.
According to the embodiment of the invention, the obstacle vehicle is not taken as a moving object at a constant speed, nor is the obstacle vehicle taken as a static object, but the acceleration of the obstacle vehicle at the first moment is calculated by utilizing an acceleration prediction model according to the environmental data at the first moment; the position of the obstacle vehicle at the second moment is calculated according to the acceleration, the speed and the position of the obstacle vehicle at the first moment, so that the accuracy of the obstacle vehicle track prediction is improved, and the running safety of the unmanned vehicle is improved.
Example four
Fig. 5 is a schematic structural diagram of a trajectory prediction apparatus according to a fourth embodiment of the present invention. In addition to the third embodiment, as shown in fig. 5, in the present embodiment, the trajectory prediction device 30 further includes: model training module 304.
and performing model training on a preset neural network model by using a training set to obtain an acceleration prediction model.
Optionally, the model training module 304 is further configured to:
the method comprises the steps of obtaining a training set, wherein the training set comprises a plurality of pieces of training data, and each piece of training data comprises real environment data of a first historical moment and acceleration of a vehicle in the real environment data at a second historical moment.
Wherein, the time interval between the second historical time and the first historical time is represented by delta t, the time interval between the second time and the first time is represented by delta t ', and | delta t-delta t' | < a preset time error.
Optionally, the neural network model includes: the device comprises a convolution layer, a ReLU layer, a maximum pooling layer, a full connection layer, a BN layer, a Dropout layer, a cyclic neural network coding layer and a cyclic neural network decoding layer.
Optionally, the position calculating module 303 is further configured to:
the method comprises the steps that a plurality of obstacle vehicles are included in the preset range, each obstacle vehicle is used as a target vehicle, the position of the target vehicle at a second moment is calculated according to the acceleration, the speed and the position of the target vehicle at a first moment, and the position of each obstacle vehicle at the second moment is obtained.
Optionally, the position calculating module 303 is further configured to:
calculating the position of the target vehicle at the second time using the following kinematic equation:
wherein p istAnd pt-1Are all a function of position, ptIndicating the position of the target vehicle at the second moment in time, pt-1Indicating the position of the target vehicle at a first moment in time, vt-1Representing the speed of the target vehicle at a first moment, at-1Represents the acceleration of the target vehicle at a first time, at represents the interval period between the first time and a second time,
representing a position function pt-1The remainder of the taylor expansion of (1).
The apparatus provided in the embodiment of the present invention may be specifically configured to execute the method embodiment provided in the second embodiment, and specific functions are not described herein again.
According to the embodiment of the invention, the obstacle vehicle is not taken as a moving object at a constant speed, nor is the obstacle vehicle taken as a static object, but the acceleration of the obstacle vehicle at the first moment is calculated by utilizing an acceleration prediction model according to the environmental data at the first moment; the position of the obstacle vehicle at the second moment is calculated according to the acceleration, the speed and the position of the obstacle vehicle at the first moment, so that the accuracy of the obstacle vehicle track prediction is improved, and the running safety of the unmanned vehicle is improved.
EXAMPLE five
Fig. 6 is a schematic structural diagram of a terminal device according to a fifth embodiment of the present invention. As shown in fig. 6, the terminal device 50 includes: a processor 501, a memory 502, and computer programs stored on the memory 502 and executable by the processor 501.
The processor 501, when executing a computer program stored on the memory 502, implements the trajectory prediction method provided by any of the method embodiments described above.
According to the embodiment of the invention, the obstacle vehicle is not taken as a moving object at a constant speed, nor is the obstacle vehicle taken as a static object, but the acceleration of the obstacle vehicle at the first moment is calculated by utilizing an acceleration prediction model according to the environmental data at the first moment; the position of the obstacle vehicle at the second moment is calculated according to the acceleration, the speed and the position of the obstacle vehicle at the first moment, so that the accuracy of the obstacle vehicle track prediction is improved, and the running safety of the unmanned vehicle is improved.
In addition, an embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the trajectory prediction method provided in any of the above method embodiments is implemented.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
It is obvious to those skilled in the art that, for convenience and simplicity of description, the foregoing division of the functional modules is merely used as an example, and in practical applications, the above function distribution may be performed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to perform all or part of the above described functions. For the specific working process of the device described above, reference may be made to the corresponding process in the foregoing method embodiment, which is not described herein again.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.
It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.
Claims (16)
1. A trajectory prediction method, comprising:
acquiring environmental data at a first moment, wherein the environmental data at least comprises: the speed and the shape parameters of the obstacle vehicle within a preset range, the speed and the shape parameters of the vehicle and the distance between any two vehicles within the preset range;
calculating the acceleration of the obstacle vehicle at the first moment by utilizing an acceleration prediction model according to the environment data;
calculating the position of the obstacle vehicle at a second moment according to the acceleration, the speed and the position of the obstacle vehicle at the first moment;
the calculating the acceleration of the obstacle vehicle at the first time using an acceleration prediction model based on the environmental data includes:
after the environment data are acquired, inputting the environment data into a trained acceleration prediction model, and predicting the acceleration of the obstacle vehicle at the first moment through the acceleration prediction model.
2. The method of claim 1, wherein calculating the acceleration of the obstacle vehicle at the first time prior to calculating the acceleration of the obstacle vehicle using an acceleration prediction model based on the environmental data further comprises:
and carrying out model training on a preset neural network model by utilizing a training set to obtain the acceleration prediction model.
3. The method of claim 2, wherein before the model training of the neural network model by using the training set to obtain the acceleration prediction model, the method further comprises:
the training set is obtained and comprises a plurality of pieces of training data, and each piece of training data comprises real environment data of a first historical moment and acceleration of a vehicle in the real environment data at a second historical moment.
4. The method of claim 3,
and using delta t to represent the time interval between the second historical time and the first historical time, using delta t 'to represent the time interval between the second time and the first time, and using the delta t-delta t' | < a preset time error.
5. The method according to any one of claims 2 to 4,
the neural network model includes: the device comprises a convolution layer, a ReLU layer, a maximum pooling layer, a full connection layer, a BN layer, a Dropout layer, a cyclic neural network coding layer and a cyclic neural network decoding layer.
6. The method according to any one of claims 1-4, wherein the predetermined range includes a plurality of obstacle vehicles, and the calculating the position of the obstacle vehicle at the second time based on the acceleration, speed and position of the obstacle vehicle at the first time comprises:
and respectively taking each obstacle vehicle as a target vehicle, and calculating the position of the target vehicle at the second moment according to the acceleration, the speed and the position of the target vehicle at the first moment to obtain the position of each obstacle vehicle at the second moment.
7. The method of claim 6, wherein calculating the position of the target vehicle at the second time based on the acceleration, velocity, and position of the target vehicle at the first time comprises:
calculating the position of the target vehicle at the second time using the following kinematic equation:
wherein p istAnd pt-1Are all a function of position, ptRepresenting the position of the target vehicle at the second moment in time, pt-1Representing the position of the target vehicle at the first moment in time, vt-1Representing the speed of the target vehicle at the first moment in time, at-1Represents the acceleration of the target vehicle at the first timing, at represents the interval period between the first timing and the second timing,
representing a position function pt-1The remainder of the taylor expansion of (1).
8. A trajectory prediction device, comprising:
an environment data obtaining module, configured to obtain environment data at a first time, where the environment data at least includes: the speed and the shape parameters of the obstacle vehicle within a preset range, the speed and the shape parameters of the vehicle and the distance between any two vehicles within the preset range;
the acceleration calculation module is used for calculating the acceleration of the obstacle vehicle at the first moment by utilizing an acceleration prediction model according to the environment data;
the position calculation module is used for calculating the position of the obstacle vehicle at a second moment according to the acceleration, the speed and the position of the obstacle vehicle at the first moment;
the acceleration calculation model is specifically configured to input the environment data into a trained acceleration prediction model after the environment data is acquired, and predict the acceleration of the obstacle vehicle at the first time through the acceleration prediction model.
9. The apparatus of claim 8, further comprising: a model training module to:
and carrying out model training on a preset neural network model by utilizing a training set to obtain the acceleration prediction model.
10. The apparatus of claim 9, wherein the model training module is further configured to:
the training set is obtained and comprises a plurality of pieces of training data, and each piece of training data comprises real environment data of a first historical moment and acceleration of a vehicle in the real environment data at a second historical moment.
11. The apparatus of claim 10, wherein Δ t represents a time interval between the second historical time and the first historical time, Δ t 'represents a time interval between the second time and the first time, and | Δ t- Δ t' | < a preset time error.
12. The apparatus according to any one of claims 9 to 11,
the neural network model includes: the device comprises a convolution layer, a ReLU layer, a maximum pooling layer, a full connection layer, a BN layer, a Dropout layer, a cyclic neural network coding layer and a cyclic neural network decoding layer.
13. The apparatus of any of claims 8-11, wherein the location calculation module is further configured to:
and respectively taking each obstacle vehicle as a target vehicle, and calculating the position of the target vehicle at the second moment according to the acceleration, the speed and the position of the target vehicle at the first moment.
14. The apparatus of claim 13, wherein the location calculation module is further configured to:
calculating the position of the target vehicle at the second time using the following kinematic equation:
wherein p istAnd pt-1Are all a function of position, ptRepresenting the position of the target vehicle at the second moment in time, pt-1Representing the position of the target vehicle at the first moment in time, vt-1Representing the speed of the target vehicle at the first moment in time, at-1Represents the acceleration of the target vehicle at the first timing, at represents the interval period between the first timing and the second timing,
representing a position function pt-1The remainder of the taylor expansion of (1).
15. A terminal device, comprising:
a memory, a processor, and a computer program stored on the memory and executable on the processor,
the processor, when executing the computer program, implements the method of any of claims 1-7.
16. A computer-readable storage medium, in which a computer program is stored,
the computer program, when executed by a processor, implementing the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811554353.0A CN109631915B (en) | 2018-12-19 | 2018-12-19 | Trajectory prediction method, apparatus, device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811554353.0A CN109631915B (en) | 2018-12-19 | 2018-12-19 | Trajectory prediction method, apparatus, device and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109631915A CN109631915A (en) | 2019-04-16 |
| CN109631915B true CN109631915B (en) | 2021-06-29 |
Family
ID=66075233
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811554353.0A Active CN109631915B (en) | 2018-12-19 | 2018-12-19 | Trajectory prediction method, apparatus, device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109631915B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110223318A (en) * | 2019-04-28 | 2019-09-10 | 驭势科技（北京）有限公司 | A kind of prediction technique of multi-target track, device, mobile unit and storage medium |
| CN111986472B (en) * | 2019-05-22 | 2023-04-28 | 阿里巴巴集团控股有限公司 | Vehicle speed determining method and vehicle |
| CN110293968B (en) * | 2019-06-18 | 2021-09-28 | 百度在线网络技术（北京）有限公司 | Control method, device and equipment for automatic driving vehicle and readable storage medium |
| CN110275531B (en) * | 2019-06-21 | 2020-11-27 | 北京三快在线科技有限公司 | Obstacle trajectory prediction method and device and unmanned equipment |
| CN112339750A (en) * | 2019-08-08 | 2021-02-09 | 奥迪股份公司 | Vehicle detection method, device, computer equipment and storage medium |
| CN110879395B (en) * | 2019-12-03 | 2022-09-09 | 北京百度网讯科技有限公司 | Obstacle position prediction method and device and electronic equipment |
| CN111114554B (en) * | 2019-12-16 | 2021-06-11 | 苏州智加科技有限公司 | Method, device, terminal and storage medium for predicting travel track |
| CN111114543B (en) * | 2020-03-26 | 2020-07-03 | 北京三快在线科技有限公司 | Trajectory prediction method and device |
| CN111609846A (en) * | 2020-04-08 | 2020-09-01 | 延锋伟世通电子科技（上海）有限公司 | Vehicle travel track prediction method, system, medium, and vehicle-mounted terminal |
| US12103526B2 (en) * | 2020-05-27 | 2024-10-01 | Baidu Usa Llc | Precautionary slowdown speed planning |
| CN111693723B (en) * | 2020-05-29 | 2022-04-22 | 阿波罗智联(北京)科技有限公司 | Speed prediction method and device and electronic equipment |
| CN112562331A (en) * | 2020-11-30 | 2021-03-26 | 的卢技术有限公司 | Vision perception-based other-party vehicle track prediction method |
| CN115060280B (en) * | 2022-06-21 | 2023-07-25 | 湖南大学无锡智能控制研究院 | Vehicle track prediction method and device |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9983591B2 (en) * | 2015-11-05 | 2018-05-29 | Ford Global Technologies, Llc | Autonomous driving at intersections based on perception data |
| US10268200B2 (en) * | 2016-12-21 | 2019-04-23 | Baidu Usa Llc | Method and system to predict one or more trajectories of a vehicle based on context surrounding the vehicle |
| CN106952303B (en) * | 2017-03-09 | 2020-04-24 | 北京旷视科技有限公司 | Vehicle distance detection method, device and system |
| CN108803617B (en) * | 2018-07-10 | 2020-03-20 | 深圳大学 | Trajectory prediction method and apparatus |
-
2018
- 2018-12-19 CN CN201811554353.0A patent/CN109631915B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109631915A (en) | 2019-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109631915B (en) | Trajectory prediction method, apparatus, device and computer readable storage medium | |
| CN110293968B (en) | Control method, device and equipment for automatic driving vehicle and readable storage medium | |
| CN108921200B (en) | Method, apparatus, device and medium for classifying driving scene data | |
| CN109934164B (en) | Data processing method and device based on track safety degree | |
| KR101714145B1 (en) | Apparatus for identifying peripheral vehicle and method thereof | |
| US11782158B2 (en) | Multi-stage object heading estimation | |
| CN112435469B (en) | Vehicle early warning control method and device, computer readable medium and electronic equipment | |
| CN110654381B (en) | Method and device for controlling a vehicle | |
| CN112562328B (en) | Vehicle behavior prediction method and device | |
| CN111002980A (en) | Road obstacle trajectory prediction method and system based on deep learning | |
| CN109727490B (en) | Peripheral vehicle behavior self-adaptive correction prediction method based on driving prediction field | |
| CN111292352B (en) | Multi-target tracking method, device, equipment and storage medium | |
| CN113291321A (en) | Vehicle track prediction method, device, equipment and storage medium | |
| CN111192327B (en) | Method and device for determining the orientation of an obstacle | |
| US20210158128A1 (en) | Method and device for determining trajectories of mobile elements | |
| CN110654380A (en) | Method and device for controlling a vehicle | |
| CN114593735B (en) | Pose prediction method and device | |
| Toledo-Moreo et al. | Maneuver prediction for road vehicles based on a neuro-fuzzy architecture with a low-cost navigation unit | |
| CN116859931A (en) | Training method of track planning model, vehicle control mode and device | |
| CN116907523A (en) | Path planning method, path planning device, computer equipment and storage medium | |
| US20240092385A1 (en) | Driving Policy Determining Method and Apparatus, Device, and Vehicle | |
| CN116088538B (en) | Vehicle track information generation method, device, equipment and computer readable medium | |
| KR101907611B1 (en) | Localization method for autonomous vehicle | |
| CN114510037A (en) | Intelligent road condition analysis method and system based on unmanned driving | |
| CN111126365B (en) | Data acquisition method and device |
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 |