CN110210058B - Reference line generation method, system, terminal and medium conforming to vehicle dynamics - Google Patents
Reference line generation method, system, terminal and medium conforming to vehicle dynamics Download PDFInfo
- Publication number
- CN110210058B CN110210058B CN201910343224.5A CN201910343224A CN110210058B CN 110210058 B CN110210058 B CN 110210058B CN 201910343224 A CN201910343224 A CN 201910343224A CN 110210058 B CN110210058 B CN 110210058B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- map
- model
- dynamics
- line
- 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
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000013528 artificial neural network Methods 0.000 claims abstract description 18
- 230000000306 recurrent effect Effects 0.000 claims abstract description 14
- 238000004088 simulation Methods 0.000 claims abstract description 10
- 230000015654 memory Effects 0.000 claims description 63
- 210000002569 neuron Anatomy 0.000 claims description 57
- 210000004027 cell Anatomy 0.000 claims description 30
- 239000011159 matrix material Substances 0.000 claims description 30
- 239000013598 vector Substances 0.000 claims description 29
- 238000013016 damping Methods 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 10
- 230000005540 biological transmission Effects 0.000 claims description 6
- 230000001133 acceleration Effects 0.000 claims description 3
- 239000003638 chemical reducing agent Substances 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 238000005094 computer simulation Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 230000009347 mechanical transmission Effects 0.000 claims description 3
- 238000002360 preparation method Methods 0.000 claims description 3
- 238000005096 rolling process Methods 0.000 claims description 3
- 239000000725 suspension Substances 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 2
- 230000007774 longterm Effects 0.000 description 18
- 238000010586 diagram Methods 0.000 description 9
- 230000009471 action Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000007787 long-term memory Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000001360 synchronised effect Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000004913 activation Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/06—Power analysis or power optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Aviation & Aerospace Engineering (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Navigation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a reference line generation method, a system, a terminal and a medium which accord with vehicle dynamics, comprising the following steps: s01: acquiring a map, acquiring positions of a starting point and a stopping point of a vehicle in the map, and acquiring a global path plan of the starting point and the stopping point; s02: setting a virtual vehicle kinematic model according to vehicle body dynamic parameters, and simulating a path planned by a running global path in a map by using the vehicle kinematic model; s03: and collecting the simulated running track as a reference running line. The method abandons the generation mode of the global path planning path, combines the vehicle dynamics model, the vehicle kinematics model and the map scene, and uses the recurrent neural network to control the vehicle dynamics model to simulate running in a simulation environment so as to obtain a reference running line.
Description
Technical Field
The invention relates to the technical field of automobile electronics, in particular to a reference line generation method, a system, a terminal and a medium which accord with vehicle dynamics.
Background
The reference line is a common module in the map path planning service, and after the starting position of the user is obtained and the destination position of the user is input, the map generates a global path (global path), the global path is composed of sparse road nodes along the line, and the road nodes along the line are connected in series by a path planning line from the starting position to the destination position in the ending direction to form the global path (global path).
The global road (global path) is directly connected between nodes, and the actual running path of the vehicle is required to meet the vehicle body dynamics control requirement and the complex working condition of the real road scene under the influence of the vehicle body dynamics parameters of different vehicle types under different road scenes, so that the global road (global path) can be used as an unmanned reference line of L4 or L5 level. There is a need for a reference line generation method that combines vehicle body dynamics parameters with current high-precision scene maps.
Disclosure of Invention
In order to solve the above and other potential technical problems, the invention provides a reference line generation method, a system, a terminal and a medium which accord with vehicle dynamics, abandon a generation mode of a global path planning path, and control the vehicle dynamics model to simulate running in a simulation environment by using a recurrent neural network in combination with a vehicle dynamics model, a vehicle kinematics model and a map scene to obtain a reference running line.
A method of generating a reference line consistent with vehicle dynamics, comprising:
s01: acquiring a map, acquiring positions of a starting point and a stopping point of a vehicle in the map, and acquiring a global path plan of the starting point and the stopping point;
s02: setting a virtual vehicle kinematic model according to vehicle body dynamic parameters, and simulating a path planned by a running global path in a map by using the vehicle kinematic model;
s03: and collecting the simulated running track as a reference running line.
Further, in the step S01, the map is a city level map of a certain city, a district level map of a certain region, a town level map of a certain town, a street level map, or a map of a certain indoor scene.
Further, the map obtained in the step S01 may be a city level map, a district level map, a town level map, a street level map, or a loading portion of an indoor scene level map where the vehicle is located at the current vehicle positioning position.
That is, the acquired map may be an integral map, that is, a city level map, a district level map, a town level map, a street level map, or a map of a certain parking lot scene downloaded in the vehicle-mounted terminal, or may be a local map where a certain level map is loaded at the current location of the vehicle.
Further, the reference travel line is vector data, which is defined in the local map according to the direction of the local map road.
Further, the vehicle dynamics model in step S02 includes a vehicle dynamics model in a low-speed scene mode and a vehicle dynamics model in a high-speed scene mode.
Further, the vehicle dynamics model in step S02 may set different vehicle dynamics models according to different vehicle models. Preferably, the vehicle dynamics model can be established in a calibrated manner.
Further, in the step S02, the vehicle kinematic model is composed of a plurality of nonlinear multi-body systems, a mass matrix, a damping matrix and a stiffness matrix are taken as vehicle body dynamics parameters, and a state vector and a disturbance force vector are taken as dynamics variables to represent a dynamics function of the vehicle model.
Further, the model of the vehicle dynamics model in step S02 has high weights on the mass matrix and the damping matrix in the vehicle dynamics parameters in the low-speed scene mode.
Further, the vehicle model of the vehicle dynamics model in step S02 has high weights on the stiffness matrix, the state vector and the disturbance force vector in the vehicle dynamics parameters in the high-speed scene mode.
Further, the disturbance force vector comprises one or more of a wheel speed pulse, a steering wheel angle range, a vehicle speed, a vehicle acceleration and a design maximum vehicle speed.
Further, the quality matrix comprises a vehicle preparation quality and a vehicle total quality.
Further, the damping matrix comprises one or more of an automobile wheelbase, a windward area, a rolling resistance coefficient, an air resistance coefficient, mechanical transmission efficiency, a tire model, an engine model, rated power, a speed reducer transmission ratio and maximum input torque.
Further, the vehicle kinematic model in the high-speed scene mode in step S02 includes a vehicle kinematic model, where the vehicle kinematic model includes one or more of a multi-body system kinematic model, a vehicle body kinematic and dynamics model, a suspension modeling and analysis model, a road surface and tire contact model, a transmission system modeling, a vehicle stress analysis mechanical model, a single-rail and double-rail motion model.
Further, the local map at the current moment, the global path planning, the vehicle control signal at the current moment, the vehicle dynamics model and the vehicle kinematics model are used as the input of the deep recurrent neural network, and the control signal of the vehicle at the current moment is obtained.
Further, the deep recurrent neural network includes n neuron cell layers, namely, from an input layer to an output layer, the input of the first neuron cell layer includes a data cluster of a vehicle near-field moving object at the present moment and cell memory data at a moment on the first neuron cell layer, the input of the second neuron cell layer is an output result of the first neuron cell layer and cell memory data at a moment on the second neuron cell layer, the input of the nth neuron cell layer is a probability that an output result of the nth neuron cell layer and a cell memory data at a moment on the nth neuron cell layer are respectively marked as a first neuron cell layer, a second neuron cell layer … th neuron cell layer, the output of the nth neuron cell layer is an intention prediction result of each near-field moving object, each branch model is trained in parallel between the first neuron cell layer, the second neuron cell layer and the … nth neuron cell layer, and the parallel training results are aggregated, synchronized and/or updated in a synchronous and/or asynchronous mode parameters are applied to each branch model.
Further, the working principle of the neuron cell layer is as follows: the neuron cell layer is like a conventional memory cell, and comprises an input layer, a memory cell with self-circulation connection, a forgetting gate and an output layer; the input layer may allow the incoming signal to change the state of memory of the cell or prevent it. On the other hand, the input layer may allow the state of the cell memory to affect or prevent other neurons. Including but not limited to two vectors: h (t) and c (t) ("c" stands for "cell"), h (t) is considered a short term state, which represents input from the next layer of neuronal cells, and c (t) is considered a long term state, which represents memory of the neuronal cells at the previous time, which can last from one time step to another. Recurrent neural networks can learn the long term state of memory content, i.e., cell memory can selectively regulate interactions between the cell memory (i.e., memory cells) itself and the external environment through the amnestic gates and/or memory gates of the neuronal cell layers. As a long-term state c (t-1) traverses the network from left to right, it first passes through a forgetting gate, loses some of the memory cell memory at the last moment, and then adds some new cell memory addition (adding memory selected by the input gate) at the current moment. Therefore, in the continuous time axis, every time the input layer is input, some memories are discarded and some memories are added. Also, after addition, the long-term state is replicated and passed through the tanh function (i.e., g (t)), and the result is filtered by the output layer. This results in a short-term state h (t).
Further, the function of the fully-connected layer of the neuron cell layer is as follows: the input vector x (t) of the current input layer and the previous short-term state h (t-1) are fed to four different fully connected layers. Four fully attached layers all have different uses: the second fully connected layer is the layer outputting g (t). It has the effect of analysing the current input x (t) and the previous (short term) state h (t-1). In the cell layer of a conventional recurrent neural network, its outputs are directly output to y (t) and h (t). In long term memory neural networks (LSTM), the output of this h (t) is not directly output, but the direct output is stored in a long term state. The first full-connection layer, the third full-connection layer and the fourth full-connection layer are all gate controllers. Because they use logistical activation functions, their output ranges from 0 to 1. Their outputs are fed to the multiplication section so if they output 0 they will close the gate and if they output 1 they open the gate. The first fully connected layer controlled forget gate (controlled by f (t)) controls which part of the long term state should be forgotten. The input gate of the third full link layer control (controlled by i (t)) controls which part of g (t) of the second full link layer control should be added to the long term state. Finally, the output gate of the fourth fully connected layer (controlled by o (t)) controls which parts of the long term should read and output states at this time step (from h (t)) and y (t). In summary, the long-term memory neural network unit can learn to recognize important inputs by means of the action of the input gate and store them in a long-term state, forget unnecessary parts according to the action of the forgetting gate, memorize necessary parts, and learn to extract it as needed. They can be used to capture a time series, long text, audio recordings, and interesting portions of the input vector x (t) of the input layer in successive video frames.
A vehicle dynamics compliant reference line generation system comprising:
a map acquisition module that acquires coordinates from a vehicle start point and a vehicle end point,
A positioning module that obtains positions of a start point and an end point of the vehicle in a map,
A global path planning module, which obtains a global path plan of a starting point to a final point,
The simulation module is used for setting a virtual vehicle kinematic model according to the vehicle body dynamic parameters, and simulating a path planned by a running global path in a map by using the vehicle kinematic model;
The reference driving line generation module gathers the simulation driving track as the reference driving line.
Further, the map loading module embeds the reference line generated by the reference driving line generating module generated at the previous moment into the map as a part of the semantic elements in the map.
Further, the vehicle body dynamic parameter control system also comprises a low-speed scene mode and a high-speed scene mode, wherein the low-speed scene mode is provided with higher weights for a quality matrix and a damping matrix in the vehicle body dynamic parameter; the stiffness matrix, the state vector and the disturbance force vector in the dynamic parameters of the vehicle body are provided with higher weights in the high-speed scene mode.
A method for using a reference line conforming to vehicle dynamics includes storing the generated reference travel line in a structured map, and when a real vehicle travels to the map again, using the map stored with the reference travel line.
Further, when the real vehicle receives the navigation task, a map and a running reference line are requested from a cloud, the cloud finds out a local map along a route and a reference system running line contained in the local map according to a starting point, a stopping point and a global route plan of the real vehicle, the local map loaded with the reference running line is transmitted to a vehicle control system through a communication network, the vehicle control system receives the local map and the reference running line in the local map, and the vehicle control system controls the actual running of a vehicle body according to the local route plan of the vehicle control system and the reference running line. When the vehicle uses the local map, the starting position, the ending position and the global path planning of the vehicle are defined, so that when the local map is loaded currently, the reference driving line is also loaded in the local map.
A terminal device, such as a smart phone that can perform the above-described reference line generation method conforming to vehicle dynamics or a vehicle-mounted terminal control device that can perform the above-described reference line generation method conforming to vehicle dynamics.
The cloud comprises a reference line generation method and/or a reference line generation system which are/is used for achieving the vehicle dynamics.
A computer storage medium for storing the above-described vehicle dynamics-compliant reference line generation method program and/or vehicle dynamics-compliant reference line generation system.
As described above, the present invention has the following advantageous effects:
and a generation mode of a global path planning path is abandoned, and a vehicle dynamics model, a vehicle kinematics model and a map scene are combined, so that the vehicle dynamics model is controlled to simulate running in a simulation environment by using a recurrent neural network to obtain a reference running line.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 shows a schematic diagram of the present invention for underground parking and global path planning.
Fig. 2 shows a schematic diagram of a global path and a reference driving line in a local map and a local map splice at a certain moment.
Fig. 3 shows a schematic diagram of a global path and a reference driving line in a local map and a local map splice at another moment.
Fig. 4 shows a schematic diagram of a global path and a reference driving line in a local map and a local map splice at another moment.
Fig. 5 shows a schematic diagram of a global path and a reference driving line in a local map and a local map splice at another moment.
Fig. 6 shows a schematic diagram of a global path and a reference driving line in a local map and a local map splice at another moment.
FIG. 7 is a schematic diagram of a neuronal cell layer according to the present invention.
FIG. 8 is a schematic representation of a neuronal cell layer according to the present invention.
Fig. 9 is a schematic diagram of the network model training of the present invention.
FIG. 10 is a schematic diagram of the network model training of the present invention.
100-A first local map; 200-a second local map; 300-a third local map; 400-fourth local map; 500-a fifth partial map; 600-sixth local map.
Detailed Description
Other advantages and effects of the present invention will become apparent to those skilled in the art from the following disclosure, which describes the embodiments of the present invention with reference to specific examples. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict.
It should be understood that the structures, proportions, sizes, etc. shown in the drawings are for illustration purposes only and should not be construed as limiting the invention to the extent that it can be practiced, since modifications, changes in the proportions, or otherwise, used in the practice of the invention, are not intended to be critical to the essential characteristics of the invention, but are intended to fall within the spirit and scope of the invention. Also, the terms such as "upper," "lower," "left," "right," "middle," and "a" and the like recited in the present specification are merely for descriptive purposes and are not intended to limit the scope of the invention, but are intended to provide relative positional changes or modifications without materially altering the technical context in which the invention may be practiced.
With reference to figures 1 to 10 of the drawings,
A method of generating a reference line consistent with vehicle dynamics, comprising:
s01: acquiring a map, acquiring positions of a starting point and a stopping point of a vehicle in the map, and acquiring a global path plan of the starting point and the stopping point;
s02: setting a virtual vehicle kinematic model according to vehicle body dynamic parameters, and simulating a path planned by a running global path in a map by using the vehicle kinematic model;
s03: and collecting the simulated running track as a reference running line.
Further, in the step S01, the map is a city level map of a certain city, a district level map of a certain region, a town level map of a certain town, a street level map, or a map of a certain indoor scene.
Further, the map obtained in the step S01 may be a city level map, a district level map, a town level map, a street level map, or a loading portion of an indoor scene level map where the vehicle is located at the current vehicle positioning position.
That is, the acquired map may be an integral map, that is, a city level map, a district level map, a town level map, a street level map, or a map of a certain parking lot scene downloaded in the vehicle-mounted terminal, or may be a local map where a certain level map is loaded at the current location of the vehicle.
Further, the reference travel line is vector data, which is defined in the local map according to the direction of the local map road.
Further, the vehicle dynamics model in step S02 includes a vehicle dynamics model in a low-speed scene mode and a vehicle dynamics model in a high-speed scene mode.
Further, the vehicle dynamics model in step S02 may set different vehicle dynamics models according to different vehicle models. Preferably, the vehicle dynamics model can be established in a calibrated manner.
Further, in the step S02, the vehicle kinematic model is composed of a plurality of nonlinear multi-body systems, a mass matrix, a damping matrix and a stiffness matrix are taken as vehicle body dynamics parameters, and a state vector and a disturbance force vector are taken as dynamics variables to represent a dynamics function of the vehicle model.
Further, the model of the vehicle dynamics model in step S02 has high weights on the mass matrix and the damping matrix in the vehicle dynamics parameters in the low-speed scene mode.
Further, the vehicle model of the vehicle dynamics model in step S02 has high weights on the stiffness matrix, the state vector and the disturbance force vector in the vehicle dynamics parameters in the high-speed scene mode.
Further, the disturbance force vector comprises one or more of a wheel speed pulse, a steering wheel angle range, a vehicle speed, a vehicle acceleration and a design maximum vehicle speed.
Further, the quality matrix comprises a vehicle preparation quality and a vehicle total quality.
Further, the damping matrix comprises one or more of an automobile wheelbase, a windward area, a rolling resistance coefficient, an air resistance coefficient, mechanical transmission efficiency, a tire model, an engine model, rated power, a speed reducer transmission ratio and maximum input torque.
Further, the vehicle kinematic model in the high-speed scene mode in step S02 includes a vehicle kinematic model, where the vehicle kinematic model includes one or more of a multi-body system kinematic model, a vehicle body kinematic and dynamics model, a suspension modeling and analysis model, a road surface and tire contact model, a transmission system modeling, a vehicle stress analysis mechanical model, a single-rail and double-rail motion model.
Further, the local map at the current moment, the global path planning, the vehicle control signal at the current moment, the vehicle dynamics model and the vehicle kinematics model are used as the input of the deep recurrent neural network, and the control signal of the vehicle at the current moment is obtained.
Further, the deep recurrent neural network includes n neuron cell layers, namely, from an input layer to an output layer, the input of the first neuron cell layer includes a data cluster of a vehicle near-field moving object at the present moment and cell memory data at a moment on the first neuron cell layer, the input of the second neuron cell layer is an output result of the first neuron cell layer and cell memory data at a moment on the second neuron cell layer, the input of the nth neuron cell layer is a probability that an output result of the nth neuron cell layer and a cell memory data at a moment on the nth neuron cell layer are respectively marked as a first neuron cell layer, a second neuron cell layer … th neuron cell layer, the output of the nth neuron cell layer is an intention prediction result of each near-field moving object, each branch model is trained in parallel between the first neuron cell layer, the second neuron cell layer and the … nth neuron cell layer, and the parallel training results are aggregated, synchronized and/or updated in a synchronous and/or asynchronous mode parameters are applied to each branch model.
Further, the working principle of the neuron cell layer is as follows: the neuron cell layer is like a conventional memory cell, and comprises an input layer, a memory cell with self-circulation connection, a forgetting gate and an output layer; the input layer may allow the incoming signal to change the state of memory of the cell or prevent it. On the other hand, the input layer may allow the state of the cell memory to affect or prevent other neurons. Including but not limited to two vectors: h (t) and c (t) ("c" stands for "cell"), h (t) is considered a short term state, which represents input from the next layer of neuronal cells, and c (t) is considered a long term state, which represents memory of the neuronal cells at the previous time, which can last from one time step to another. Recurrent neural networks can learn the long term state of memory content, i.e., cell memory can selectively regulate interactions between the cell memory (i.e., memory cells) itself and the external environment through the amnestic gates and/or memory gates of the neuronal cell layers. As a long-term state c (t-1) traverses the network from left to right, it first passes through a forgetting gate, loses some of the memory cell memory at the last moment, and then adds some new cell memory addition (adding memory selected by the input gate) at the current moment. Therefore, in the continuous time axis, every time the input layer is input, some memories are discarded and some memories are added. Also, after addition, the long-term state is replicated and passed through the tanh function (i.e., g (t)), and the result is filtered by the output layer. This results in a short-term state h (t).
Further, the function of the fully-connected layer of the neuron cell layer is as follows: the input vector x (t) of the current input layer and the previous short-term state h (t-1) are fed to four different fully connected layers. Four fully attached layers all have different uses: the second fully connected layer is the layer outputting g (t). It has the effect of analysing the current input x (t) and the previous (short term) state h (t-1). In the cell layer of a conventional recurrent neural network, its outputs are directly output to y (t) and h (t). In long term memory neural networks (LSTM), the output of this h (t) is not directly output, but the direct output is stored in a long term state. The first full-connection layer, the third full-connection layer and the fourth full-connection layer are all gate controllers. Because they use logistical activation functions, their output ranges from 0 to 1. Their outputs are fed to the multiplication section so if they output 0 they will close the gate and if they output 1 they open the gate. The first fully connected layer controlled forget gate (controlled by f (t)) controls which part of the long term state should be forgotten. The input gate of the third full link layer control (controlled by i (t)) controls which part of g (t) of the second full link layer control should be added to the long term state. Finally, the output gate of the fourth fully connected layer (controlled by o (t)) controls which parts of the long term should read and output states at this time step (from h (t)) and y (t). In summary, the long-term memory neural network unit can learn to recognize important inputs by means of the action of the input gate and store them in a long-term state, forget unnecessary parts according to the action of the forgetting gate, memorize necessary parts, and learn to extract it as needed. They can be used to capture a time series, long text, audio recordings, and interesting portions of the input vector x (t) of the input layer in successive video frames.
A vehicle dynamics compliant reference line generation system comprising:
a map acquisition module that acquires coordinates from a vehicle start point and a vehicle end point,
A positioning module that obtains positions of a start point and an end point of the vehicle in a map,
A global path planning module, which obtains a global path plan of a starting point to a final point,
The simulation module is used for setting a virtual vehicle kinematic model according to the vehicle body dynamic parameters, and simulating a path planned by a running global path in a map by using the vehicle kinematic model;
The reference driving line generation module gathers the simulation driving track as the reference driving line.
Further, the map loading module embeds the reference line generated by the reference driving line generating module generated at the previous moment into the map as a part of the semantic elements in the map.
Further, the vehicle body dynamic parameter control system also comprises a low-speed scene mode and a high-speed scene mode, wherein the low-speed scene mode is provided with higher weights for a quality matrix and a damping matrix in the vehicle body dynamic parameter; the stiffness matrix, the state vector and the disturbance force vector in the dynamic parameters of the vehicle body are provided with higher weights in the high-speed scene mode.
A method for using a reference line conforming to vehicle dynamics includes storing the generated reference travel line in a structured map, and when a real vehicle travels to the map again, using the map stored with the reference travel line.
Further, when the real vehicle receives the navigation task, a map and a running reference line are requested from a cloud, the cloud finds out a local map along a route and a reference system running line contained in the local map according to a starting point, a stopping point and a global route plan of the real vehicle, the local map loaded with the reference running line is transmitted to a vehicle control system through a communication network, the vehicle control system receives the local map and the reference running line in the local map, and the vehicle control system controls the actual running of a vehicle body according to the local route plan of the vehicle control system and the reference running line. When the vehicle uses the local map, the starting position, the ending position and the global path planning of the vehicle are defined, so that when the local map is loaded currently, the reference driving line is also loaded in the local map.
A terminal device, such as a smart phone that can perform the above-described reference line generation method conforming to vehicle dynamics or a vehicle-mounted terminal control device that can perform the above-described reference line generation method conforming to vehicle dynamics.
The cloud comprises a reference line generation method and/or a reference line generation system which are/is used for achieving the vehicle dynamics.
A computer storage medium for storing the above-described vehicle dynamics-compliant reference line generation method program and/or vehicle dynamics-compliant reference line generation system.
As a preferred embodiment, the present embodiment further provides a terminal device, such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack-mounted cloud, a blade cloud, a tower cloud, or a rack-mounted cloud (including an independent cloud or a cloud cluster formed by multiple clouds) capable of executing a program, and so on. The terminal device of this embodiment includes at least, but is not limited to: a memory, a processor, and the like, which may be communicatively coupled to each other via a system bus. It should be noted that a terminal device having a component memory, a processor, but it should be understood that not all of the illustrated components are required to be implemented, and that alternative vehicle dynamics compliant reference line generation methods may implement more or fewer components.
As a preferred embodiment, the memory (i.e., readable storage medium) includes flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory may be an internal storage unit of a computer device, such as a hard disk or memory of the computer device. In other embodiments, the memory may also be an external storage device of the computer device, such as a plug-in hard disk provided on the computer device, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD), or the like. Of course, the memory may also include both internal storage units of the computer device and external storage devices. In this embodiment, the memory is typically used to store an operating system installed on the computer device and various types of application software, such as reference line generation method program code conforming to vehicle dynamics in the embodiment, and the like. In addition, the memory can be used to temporarily store various types of data that have been output or are to be output.
The present embodiment also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a cloud, an App application store, etc., on which a computer program is stored, which when executed by a processor, performs a corresponding function. The computer-readable storage medium of the present embodiment is used for storing a reference line generating method program conforming to vehicle dynamics, which when executed by a processor implements the reference line generating method conforming to vehicle dynamics in the reference line generating method program embodiment conforming to vehicle dynamics.
The above embodiments are merely illustrative of the principles of the present invention and its effectiveness, and are not intended to limit the invention. Modifications and variations may be made to the above-described embodiments by those skilled in the art without departing from the spirit and scope of the invention. Accordingly, it is intended that all equivalent modifications and variations of the invention be covered by the claims of this invention, which are within the skill of those skilled in the art, be included within the spirit and scope of this invention.
Claims (11)
1. A method of generating a reference line that conforms to vehicle dynamics, comprising:
S01: acquiring a map, acquiring positions of a starting point and a stopping point of a vehicle in the map, and acquiring a global path plan of the starting point and the stopping point; the map is loaded with a reference driving line generated at the previous moment and used as a part of semantic elements in the map;
S02: setting a virtual vehicle kinematic model according to vehicle body dynamic parameters, and simulating a path planned by a running global path in a map by using the vehicle kinematic model; taking a local map at the current moment, a global path planning, a vehicle control signal at the current moment, a vehicle dynamics model and a vehicle kinematics model as inputs of a deep recurrent neural network to obtain the control signal of the vehicle at the current moment;
S03: collecting a simulation running track as a reference running line; the reference travel line is vector data, and is defined in the local map according to the direction of the local map road.
2. The method for generating a reference line according to vehicle dynamics according to claim 1, wherein the deep recurrent neural network comprises n neuron cell layers, namely, a first neuron cell layer and a second neuron cell layer … n-th neuron cell layer respectively marked from an input layer to an output layer, the input of the first neuron cell layer comprises a data cluster of a vehicle near-field moving object at the present moment and cell memory data at a moment on the first neuron cell layer, and the input of the second neuron cell layer is an output result of the first neuron cell layer and cell memory data at a moment on the second neuron cell layer.
3. The method according to claim 1, wherein the map obtained in step S01 is a city level map of a city, a district level map of a district, a town level map of a town, a street level map, or a map of an indoor scene.
4. The method according to claim 1, wherein the map obtained in step S01 is a loading part of a city level map, a district level map, a town level map, a street level map, and an indoor scene level map where the vehicle is located at the current vehicle positioning position.
5. The vehicle dynamics-compliant reference line generation method according to claim 1, wherein the vehicle dynamics model in step S02 includes a vehicle dynamics model in a low-speed scene mode and a vehicle dynamics model in a high-speed scene mode.
6. The method according to claim 1, wherein the vehicle dynamics model in step S02 is different vehicle dynamics models according to the vehicle model.
7. The method according to claim 1, wherein the vehicle kinematic model in step S02 is composed of a plurality of nonlinear multi-body systems, a mass matrix, a damping matrix, and a stiffness matrix are used as vehicle body dynamics parameters, and a state vector and a disturbance force vector are used as dynamics variables to represent a dynamics function of the vehicle model; the vehicle model of the vehicle dynamics model in the step S02 has high weight on a quality matrix and a damping matrix in vehicle dynamics parameters in a low-speed scene mode; the vehicle model of the vehicle dynamics model in the step S02 has high weight on a rigidity matrix, a state vector and a disturbance force vector in vehicle dynamics parameters in a high-speed scene mode; the disturbance force vector comprises one or more of wheel speed pulse, steering wheel angle range, vehicle speed, vehicle acceleration and design maximum vehicle speed; the quality matrix comprises vehicle preparation quality and total vehicle quality; the damping matrix comprises one or more of an automobile wheelbase, a windward area, a rolling resistance coefficient, an air resistance coefficient, mechanical transmission efficiency, a tire model, an engine model, rated power, a reducer transmission ratio and maximum input torque; the vehicle kinematic model in the high-speed scene mode in the step S02 includes a whole vehicle kinematic model, wherein the whole vehicle kinematic model includes one or more of a multi-body system kinematic model, a vehicle body kinematic and dynamics model, a suspension modeling and analysis model, a road surface and tire contact model, a transmission system modeling, a vehicle stress analysis mechanical model, a single-rail and double-rail motion model.
8. A vehicle dynamics compliant reference line generation system comprising:
The map acquisition module acquires coordinates of a vehicle starting point and a vehicle ending point, and the map is loaded with a reference driving line generated by the reference driving line generation module at the last moment and is used as a part of semantic elements in the map;
A positioning module that obtains positions of a start point and an end point of the vehicle in a map,
A global path planning module, which obtains a global path plan of a starting point to a final point,
The simulation module is used for setting a virtual vehicle kinematic model according to the vehicle body dynamic parameters, and simulating a path planned by a running global path in a map by using the vehicle kinematic model; taking a local map at the current moment, a global path planning, a vehicle control signal at the current moment, a vehicle dynamics model and a vehicle kinematics model as inputs of a deep recurrent neural network to obtain the control signal of the vehicle at the current moment;
The reference driving line generation module gathers the simulation driving track as the reference driving line; the reference travel line is vector data, and is defined in the local map according to the direction of the local map road.
9. A terminal device, characterized by: a smart phone performing the vehicle dynamics-compliant reference line generation method according to any one of claims 1 to 7 or an in-vehicle terminal control apparatus performing the vehicle dynamics-compliant reference line generation system according to claim 8.
10. A computer-readable storage medium having stored thereon a computer program, characterized by: the program, when executed by a processor, implements the steps of the method of any of claims 1 to 7.
11. A method of reference line use in accordance with vehicle dynamics, the method of reference line use being implemented by the reference line generation system as set forth in claim 8, characterized in that: storing the generated reference travel line in a structured map, and when the real vehicle travels to the map again, using the map stored with the reference travel line; when a real vehicle receives a navigation task, a map and a running reference line are requested from a cloud, the cloud finds out a local map along a route and a reference system running line contained in the local map according to a real vehicle starting point, a real vehicle ending point and a global route plan, the local map loaded with the reference running line is transmitted to a vehicle control system through a communication network, the vehicle control system receives the local map and the reference running line in the local map, and the vehicle control system controls the actual running of a vehicle body according to the local route plan and the reference running line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910343224.5A CN110210058B (en) | 2019-04-26 | 2019-04-26 | Reference line generation method, system, terminal and medium conforming to vehicle dynamics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910343224.5A CN110210058B (en) | 2019-04-26 | 2019-04-26 | Reference line generation method, system, terminal and medium conforming to vehicle dynamics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110210058A CN110210058A (en) | 2019-09-06 |
| CN110210058B true CN110210058B (en) | 2024-04-26 |
Family
ID=67786450
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910343224.5A Active CN110210058B (en) | 2019-04-26 | 2019-04-26 | Reference line generation method, system, terminal and medium conforming to vehicle dynamics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110210058B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110186470B (en) * | 2019-04-26 | 2024-06-04 | 纵目科技（上海）股份有限公司 | Reference line generation system, terminal and using method conforming to vehicle dynamics |
| CN111754816B (en) * | 2020-06-04 | 2023-04-28 | 纵目科技（上海）股份有限公司 | Device, method, system, terminal and medium for identifying intention of mobile object |
| CN111753371B (en) * | 2020-06-04 | 2024-03-15 | 纵目科技（上海）股份有限公司 | Training method, system, terminal and storage medium for vehicle body control network model |
| CN111661034B (en) * | 2020-06-04 | 2022-07-29 | 纵目科技（上海）股份有限公司 | Vehicle body control method, system, terminal and storage medium based on deep recurrent neural network |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101536056A (en) * | 2006-11-17 | 2009-09-16 | 罗伯特.博世有限公司 | Method for displaying route information for a navigation system |
| CN104977933A (en) * | 2015-07-01 | 2015-10-14 | 吉林大学 | Regional path tracking control method for autonomous land vehicle |
| CN105549597A (en) * | 2016-02-04 | 2016-05-04 | 同济大学 | Unmanned vehicle dynamic path programming method based on environment uncertainty |
| CN107608344A (en) * | 2017-08-21 | 2018-01-19 | 上海蔚来汽车有限公司 | Vehicle motion control method, apparatus and relevant device based on trajectory planning |
| KR101897407B1 (en) * | 2017-06-14 | 2018-10-18 | 국방과학연구소 | Method of Adaptive Dynamic Model-base]d Optimal Path Planning for Autonomous Navigation of Unmanned Ground Vehicle and Appratus thereof |
| CN109318905A (en) * | 2018-08-22 | 2019-02-12 | 江苏大学 | A kind of intelligent automobile path trace mixing control method |
| CN109491369A (en) * | 2018-12-05 | 2019-03-19 | 百度在线网络技术（北京）有限公司 | Performance estimating method, device, equipment and the medium of the practical control unit of vehicle |
-
2019
- 2019-04-26 CN CN201910343224.5A patent/CN110210058B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101536056A (en) * | 2006-11-17 | 2009-09-16 | 罗伯特.博世有限公司 | Method for displaying route information for a navigation system |
| CN104977933A (en) * | 2015-07-01 | 2015-10-14 | 吉林大学 | Regional path tracking control method for autonomous land vehicle |
| CN105549597A (en) * | 2016-02-04 | 2016-05-04 | 同济大学 | Unmanned vehicle dynamic path programming method based on environment uncertainty |
| KR101897407B1 (en) * | 2017-06-14 | 2018-10-18 | 국방과학연구소 | Method of Adaptive Dynamic Model-base]d Optimal Path Planning for Autonomous Navigation of Unmanned Ground Vehicle and Appratus thereof |
| CN107608344A (en) * | 2017-08-21 | 2018-01-19 | 上海蔚来汽车有限公司 | Vehicle motion control method, apparatus and relevant device based on trajectory planning |
| CN109318905A (en) * | 2018-08-22 | 2019-02-12 | 江苏大学 | A kind of intelligent automobile path trace mixing control method |
| CN109491369A (en) * | 2018-12-05 | 2019-03-19 | 百度在线网络技术（北京）有限公司 | Performance estimating method, device, equipment and the medium of the practical control unit of vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110210058A (en) | 2019-09-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110210058B (en) | Reference line generation method, system, terminal and medium conforming to vehicle dynamics | |
| Shadrin et al. | Experimental autonomous road vehicle with logical artificial intelligence | |
| CN112805198B (en) | Personal driving style learning for autonomous driving | |
| Ali et al. | The flatbed platoon towing model for safe and dense platooning on highways | |
| Alcala et al. | Gain‐scheduling LPV control for autonomous vehicles including friction force estimation and compensation mechanism | |
| US11704554B2 (en) | Automated training data extraction method for dynamic models for autonomous driving vehicles | |
| US11474529B2 (en) | System and method for motion planning of an autonomous driving machine | |
| CN115843347A (en) | Generating autonomous vehicle simulation data from recorded data | |
| CN112703459A (en) | Iterative generation of confrontational scenarios | |
| JP2022547611A (en) | Simulation of various long-term future trajectories in road scenes | |
| CN111832652B (en) | Training method and device for decision model | |
| CN110186470B (en) | Reference line generation system, terminal and using method conforming to vehicle dynamics | |
| CN114358128A (en) | Method for training end-to-end automatic driving strategy | |
| CN111752258A (en) | Operation test of autonomous vehicle | |
| CN114296424B (en) | Simulation test system and method | |
| CN111753371B (en) | Training method, system, terminal and storage medium for vehicle body control network model | |
| Schütt et al. | An application of scenario exploration to find new scenarios for the development and testing of automated driving systems in urban scenarios | |
| CN116859931A (en) | Training method of track planning model, vehicle control mode and device | |
| Leudet et al. | Virtual environment for training autonomous vehicles | |
| CN116620327A (en) | Lane changing decision method for realizing automatic driving high-speed scene based on PPO and Lattice | |
| CN114114954B (en) | Unmanned equipment control method and device | |
| CN114117944B (en) | Model updating method, device, equipment and readable storage medium | |
| CN111661034B (en) | Vehicle body control method, system, terminal and storage medium based on deep recurrent neural network | |
| CN114954498A (en) | Reinforced learning lane change behavior planning method and system based on simulated learning initialization | |
| CN114968782A (en) | Method for realizing intelligent driving based on Carla simulator |
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 |