CN111818189A - Vehicle road cooperative control system, method and medium - Google Patents
Vehicle road cooperative control system, method and medium Download PDFInfo
- Publication number
- CN111818189A CN111818189A CN202010943246.8A CN202010943246A CN111818189A CN 111818189 A CN111818189 A CN 111818189A CN 202010943246 A CN202010943246 A CN 202010943246A CN 111818189 A CN111818189 A CN 111818189A
- Authority
- CN
- China
- Prior art keywords
- data
- vehicle
- client
- calculation module
- edge calculation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/40—Bus networks
- H04L12/40006—Architecture of a communication node
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/40—Bus networks
- H04L2012/40267—Bus for use in transportation systems
- H04L2012/40273—Bus for use in transportation systems the transportation system being a vehicle
Abstract
The application discloses a vehicle-road cooperative control system, a vehicle-road cooperative control method and a vehicle-road cooperative control medium, the vehicle-road cooperative control system broadcasts an initialization instruction to at least one client through an edge computing module, the edge computing module acquires environment perception data, the at least one client acquires corresponding vehicle state data based on the initialization instruction and sends the vehicle state data to the edge computing module through a high-speed communication bus interface module, the edge computing module determines control strategy data according to the vehicle state data and the environment perception data, finally, the at least one client performs vehicle-road cooperative control according to the control strategy data and interconnects independent functional domains at a high speed, resource reuse and sharing of the functional domains are achieved, and data processing efficiency during control of the vehicle-road cooperative high-speed computing power is improved.
Description
Technical Field
The invention relates to the field of data processing of automatic driving or advanced driving assistance, in particular to a vehicle-road cooperative control system, a method and a medium.
Background
With the improvement of the vehicle electronization degree, especially the increase of new functions such as advanced driving assistance system and automatic driving, the number of the vehicle internal controllers is multiplied, so that the system functions in the vehicle are more and more complex, and the function cooperation of the vehicle internal control unit is more and more difficult. The ability of existing on-board networks to carry sensor data is increasingly limited. The increase of controller nodes inside the vehicle leads to an increasingly complex data synchronization of the automotive system. Particularly in the field of automatic driving, the data volume required to be received and processed by the vehicle internal controller is huge and complex, the vehicle core computing unit cannot complete real-time high-speed communication with a plurality of internal controllers, and the existing distributed computing architecture with one function corresponding to one controller or a single-module domain controller cannot meet the requirements of future automatic driving or advanced driving assistance.
Disclosure of Invention
In order to solve the above technical problems, the present invention provides a vehicle-road cooperative control system, method, and medium, which interconnect independent functional domains at high speed, implement resource reuse and sharing of the functional domains, and improve data processing efficiency during high calculation power of vehicle-road cooperation.
In order to achieve the above object, the present application provides a cooperative vehicle control system, applied in the field of automatic driving, the system comprising:
the system comprises an edge calculation module, a high-speed communication bus interface module and at least one client;
the high-speed communication bus interface module is respectively connected with the edge calculation module and the at least one client; the high-speed communication bus interface module is used for data interaction between the edge computing module and at least one client;
the edge computing module is used for acquiring environment perception data, broadcasting an initialization instruction to the at least one client through the high-speed communication bus interface module, receiving vehicle state data sent by the at least one client through the high-speed communication bus interface module, and determining control strategy data according to the vehicle state data and the environment perception data;
the at least one client is used for receiving an initialization instruction through a high-speed communication bus interface module, acquiring corresponding vehicle state data based on the initialization instruction, sending the vehicle state data to the edge calculation module through the high-speed communication bus interface module, and performing vehicle-road cooperative control according to the control strategy data.
On the other hand, the application also provides a vehicle-road cooperative control method, which comprises the following steps:
the edge calculation module broadcasts an initialization instruction to at least one client through the high-speed communication bus interface module;
the edge calculation module acquires environment perception data;
the at least one client acquires corresponding vehicle state data based on the initialization instruction, and sends the vehicle state data to the edge calculation module through a high-speed communication bus interface module;
the edge calculation module determines control strategy data according to the vehicle state data and the environment perception data;
and the at least one client side performs vehicle-road cooperative control according to the control strategy data.
In another aspect, the present application further provides a storage medium having at least one instruction, at least one program, a set of codes, or a set of instructions stored therein, which is loaded and executed by a processor to implement the above-mentioned method.
According to the method, the initialization instruction is broadcast to at least one client through the edge computing module, the edge computing module obtains environment perception data, at least one client collects corresponding vehicle state data based on the initialization instruction, the vehicle state data are sent to the edge computing module through the high-speed communication bus interface module, the edge computing module determines control strategy data according to the vehicle state data and the environment perception data, and finally at least one client performs vehicle-road cooperative control according to the control strategy data, so that the data processing efficiency of high vehicle computing power is improved, the number of vehicle-mounted controllers is greatly reduced, and the development cost is reduced.
Drawings
In order to more clearly illustrate the method, apparatus, system, and medium for transferring information models described herein, reference will now be made in brief to the accompanying drawings, which are required for embodiments of the present invention, and it should be apparent that the drawings in the following description are merely some embodiments of the invention and that other drawings may be derived therefrom by those skilled in the art without the exercise of inventive faculty.
Fig. 1 is a schematic structural diagram of a vehicle-road cooperative control system according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of an edge calculation module according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a vehicle-road cooperative control system applied to a vehicle according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of a vehicle-road cooperative control system applied to a road side according to an embodiment of the present application;
fig. 5 is a schematic flow chart of a vehicle-road cooperative control method according to an embodiment of the present application;
fig. 6 is a schematic flow chart of a cooperative vehicle-road control method according to another embodiment of the present application;
fig. 7 is a schematic flowchart of a cooperative vehicle-road control method according to another embodiment of the present application;
fig. 8 is a schematic flowchart of a cooperative vehicle-road control method according to another embodiment of the present application;
fig. 9 is a schematic flowchart of a cooperative vehicle-road control method according to another embodiment of the present application;
fig. 10 is a schematic flow chart of a vehicle-road cooperative control method according to another embodiment of the present application.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In order to implement the technical solution of the present application, so that more engineering workers can easily understand and apply the present application, the working principle of the present application will be further described with reference to specific embodiments.
In the following, referring to fig. 1, an embodiment of a vehicle-road cooperative control system is first described, the system including:
an edge computing module 100, a high-speed communication bus interface module 200, and at least one client 300. The high-speed communication bus interface module 200 is connected with the edge computing module 100 and at least one client 300, respectively. The high-speed communication bus interface module 200 is used for data interaction between the edge computing module 100 and at least one client 300. The edge computing module 100 is configured to obtain the environment awareness data, broadcast an initialization instruction to the at least one client 300 through the high-speed communication bus interface module 200, receive the vehicle state data sent by the at least one client 300 through the high-speed communication bus interface module 200, and determine the control strategy data according to the vehicle state data and the environment awareness data.
Specifically, the environmental awareness data acquired by the edge computing module 100 may include:
the vehicle-mounted sensor-based road side equipment comprises environment sensing data collected by the vehicle-mounted sensor, environment sensing data collected by the road side equipment and environment sensing data collected by surrounding vehicles. The environmental perception data collected by the roadside device and the environmental perception data collected by the surrounding vehicles can be received by the vehicle-road cooperative control system through a 5G-TCAM (5G-Terminal Communication Antenna Module) of the vehicle. Specifically, the data types of the environmental perception data may include data types such as raw data, point cloud data, environmental image data, and signal phases.
The at least one client 300 is configured to receive the initialization instruction through the high-speed communication bus interface module 200, acquire corresponding vehicle state data based on the initialization instruction, send the vehicle state data to the edge computing module 100 through the high-speed communication bus interface module 200, and perform cooperative control on a vehicle route according to the control strategy data.
Specifically, the high-speed communication bus interface module 200 may adopt a PCIe (peripheral component interconnect express, high-speed serial computer extended bus standard) bus interface, where the transmission rate of the PCIe bus may reach 32GTps (Giga transmission Per Second), and the PCIe bus has a high-speed transmission performance of 16 channels, and the throughput of the PCIe bus may reach 63GBps (Giga Byte Per Second). Compared with the conventional low-speed vehicle-mounted buses such as CAN, FlexRay and LIN, the PCIe bus CAN improve the real-time performance of data transmission, increase the bandwidth and improve the transmission rate in an automatic driving application scene.
In some embodiments, as shown in fig. 2, the edge calculation module 100 may include:
the system comprises a communication interface unit 101, a high-speed communication bus interface unit 102, a perception fusion processing unit 103, a decision planning processing unit 104, a data storage unit 105, a data acceleration processing unit 106 and a power management unit 107. The communication interface unit 101 is respectively connected with the data acceleration processing unit 106 and the perception fusion processing unit 103, the data acceleration processing unit 106 is respectively connected with the perception fusion processing unit 103 and the data storage unit 105, the decision planning processing unit 104 is respectively connected with the perception fusion processing unit 103 and the data storage unit 105, the high-speed communication bus interface unit 102 is respectively connected with the decision planning processing unit 104 and the data acceleration processing unit 106, and the power management unit 107 is respectively in power supply connection with the perception fusion processing unit 103, the decision planning processing unit 104 and the data acceleration processing unit 106.
The data storage unit 105 may employ a high-density NAND flash memory of UFS3.0 or more, and on the one hand, may be used as a car black box to store and backup all control strategy data and real-time vehicle state data, and on the other hand, may be used to store sensor data such as high-precision map data and image data, computational models, program codes, and the like.
The communication interface unit 101 is used to receive context awareness data.
Specifically, the sensor accessed by the communication interface unit 101 may include:
a combination of any one or more of a camera, a millimeter wave radar, a laser radar, an ultrasonic radar, a global positioning system, and an inertial measurement unit.
The high-speed communication bus interface unit 102 is used for data interaction with at least one client.
The perception fusion processing unit 103 is configured to perform classification preprocessing on the vehicle state data and the environmental perception data to obtain intermediate data and target data, receive a fusion target list, and predict a perception result at a next time based on the fusion target list and the target data.
The data acceleration processing unit 106 is configured to perform acceleration calculation on the intermediate data to obtain a fusion target list.
The decision plan processing unit 104 is configured to determine control strategy data based on the sensing result at the next time.
The power management unit 107 can adopt an independent dual power supply mode, that is, the power supply of the vehicle-mounted battery is divided into two independent power outputs through DC/DC, and the two independent power outputs are respectively used for supplying power to all the modules through the power management unit. When one of the power supplies fails, the other power supply can still ensure the system to continue to work normally. For example, the vehicle-mounted power supply is divided into two independent power supply inputs through DC/DC, the two independent power supply inputs are respectively divided into four power supplies of 12V, 5V, 3V and 1.8V through the power management unit, dual power supply is carried out on all modules through the electronic switch, and the power supply of all hardware modules can be accurately controlled through controlling the electronic switch, so that hardware power-on sequence adjustment, power consumption control and module function switching are realized.
In some embodiments, the edge calculation module 100 may further include: and a heat dissipation unit.
Specifically, the heat dissipation unit is used for cooling the edge calculation module. Wherein, the heat dissipation cooling can be carried out by adopting a passive, air-cooled or liquid-cooled mode. The heat dissipation unit can adopt heat conduction silica gel, externally adopts a metal alloy shell with good heat conduction performance, light weight and wide heat dissipation surface, and adopts cooling modes such as passive, air cooling or liquid cooling and the like at a heating part respectively to realize the heat dissipation and cooling of the edge calculation module.
Specifically, the edge computing module 100 may adopt a hardware design of dual system, dual power redundancy backup, and air cooling heat dissipation. The edge computing module adopts a dual-system mode, namely two independent computer minimum systems are designed on hardware, independent operating systems are respectively operated, and the edge computing module is functionally redundant in backup and cooperative in cooperation with each other. For example, a GPU processor and an NPU processor may be used as the first system to perform fusion processing of perception data and decision control generation. The KPU processor is used as a second system, processes calculation intensive application with large data volume, complex algorithm and high real-time requirement, accelerates data calculation processing and can improve the overall calculation efficiency of the system. In addition, the edge computing module implements a double backup mechanism, namely, under the condition that one system fails, the other system can be switched to replace the system to realize partial functions of the system, so that the robustness of the system is improved.
In some embodiments, the system may be applied to a vehicle, and as shown in fig. 3, the at least one client may include:
any one or more of a powertrain module 301, a body electronics module 302, a vehicle security module 303, an infotainment module 304, and a data communication module 305. Any one or more combinations of the powertrain module 301, the body electronics module 302, the vehicle security module 303, the infotainment module 304, and the data communication module 305 are connected to the high-speed communication bus interface unit 102, respectively.
In further embodiments, the system may be applied to roadside devices, as shown in fig. 4, at least one client may include at least one edge calculation module. The at least one edge calculation module is connected to the high speed communication bus interface unit 102. The central edge computing module is set to perform task allocation and complex computation, and the edge computing module serving as the client side is matched with the central edge computing module to perform data processing and computation.
In addition, when the system is applied to road side equipment, a plurality of road side edge computing modules can be cascaded in a network connection mode such as optical fiber or Ethernet to form a road side edge computing service cluster, and the edge computing service cluster under cooperative control is deployed in a large scale in a road side small machine room mode, so that the problem of difficulty in construction and deployment in current automatic driving computing resource expansion can be solved, the construction cost of infrastructure can be reduced, and the reliability and stability of the vehicle-road cooperative system can be improved.
The present application further provides an embodiment of a vehicle-road cooperative control method, as shown in fig. 5, the method may include:
s101: the edge computing module broadcasts an initialization instruction to at least one client through the high-speed communication bus interface module.
S103: the edge calculation module obtains environment perception data.
Specifically, the edge calculation module acquires environment sensing data provided by roadside or surrounding vehicles through a 5G-TCAM system outside the system, and records the environment sensing data as
。
S105: and at least one client acquires corresponding vehicle state data based on the initialization instruction and sends the vehicle state data to the edge computing module through the high-speed communication bus interface module.
Specifically, the at least one client may be a plurality of clients, for example, when the system is applied to a vehicle, the plurality of clients are a powertrain module, a body electronics module, a vehicle security module, and an infotainment module. The power assembly module acquires power state data such as current gear, speed, wheel speed, direction angle, traction force, friction and the like based on an initialization instruction, the vehicle body electronic module acquires vehicle door and window state data based on the initialization instruction, the vehicle safety module acquires safety early warning data based on the initialization instruction, the information entertainment module acquires remote notification information and the like based on the initialization instruction, and the data are recorded as
。
S107: the edge calculation module determines control strategy data according to the vehicle state data and the environment perception data.
Specifically, as shown in fig. 6, the determining, by the edge calculation module, the control strategy data according to the vehicle state data and the environmental awareness data may include:
s1071: the edge calculation module carries out classification preprocessing on the vehicle state data and the environment perception data to obtain intermediate data and target data.
S1073: and the edge calculation module performs accelerated calculation on the intermediate data to obtain a fusion target list.
S1075: the edge calculation module predicts a perception result at the next moment based on the fusion target list and the target data.
Specifically, the edge calculation module performs time synchronization compensation on the fusion target list and the target data to obtain a fusion target list and target data after time alignment, and then performs synchronization and fusion processing on the fusion target list and the target data after time alignment to generate a sensing result with the vehicle as a reference center, and the sensing result is recorded as a sensing result with the vehicle as a reference center
The fusion mode can be preset
Can be obtained according to the following formula
：
The edge calculation module is used for calculating the edge of the vehicle according to the current driving state of the vehicle
Based on the current time, the perception result of the vehicle at the next time (Δ t) is calculated by using the deep learning model and is recorded as
Can be obtained according to the following formula
：
The method comprises the steps of training a large number of fusion target lists and target data in advance, enabling a model to output control strategy data, and taking the model when the output control strategy data meet preset conditions as an actually used deep learning model.
S1077: the edge calculation module determines control strategy data based on a sensing result at the next moment.
Specifically, the edge calculation module is based on
Policies to be taken at a time
Further, the method is decomposed into a cooperative decision, denoted as Di, implemented by all modules (denoted as N) in parallel at the time, and then the following functional relation is obtained:
S109: and at least one client side performs vehicle-road cooperative control according to the control strategy data.
Specifically, as shown in fig. 7, the performing, by at least one client, vehicle-road cooperative control according to the control policy data may include:
s1091: and at least one client determines a corresponding component execution instruction according to the control strategy data.
Specifically, the edge calculation module sends the decision Di that each component (denoted as K) should take to the module corresponding to the corresponding component through the PCIe bus, the module further decomposes the decision Di, converts the decision Di into a corresponding component execution instruction, denoted as Ej, and may obtain Ej according to the following formula:
wherein, (j = [ 0K ])
S1093: and at least one client controls the corresponding component to execute the corresponding component execution instruction.
Specifically, each client is based on
The corresponding components are controlled so as to realize automatic driving control in a continuous period of time.
In the embodiment, the edge computing module broadcasts the initialization instruction to the at least one client, the edge computing module obtains the environment perception data, the at least one client acquires the corresponding vehicle state data based on the initialization instruction, and sends the vehicle state data to the edge computing module through the high-speed communication bus interface module, the edge computing module determines the control strategy data according to the vehicle state data and the environment perception data, and finally the at least one client performs the cooperative vehicle-road control according to the control strategy data to interconnect the independent functional domains at a high speed, so that the resource multiplexing and sharing of the functional domains are realized, and the data processing efficiency during the cooperative vehicle-road high-computation force control is improved.
In a further embodiment, as shown in fig. 8, after the step of S107, the method may include:
s1081: and the edge calculation module disassembles the control strategy data into a component execution instruction corresponding to at least one client.
S1083: and at least one client receives the corresponding component execution instruction and controls the corresponding component to execute the corresponding component execution instruction.
In this embodiment, the control policy data may be disassembled first, and then each client receives the corresponding component execution instruction and controls the corresponding component to execute the corresponding component execution instruction, so that the calculation amount of each client is minimized, the data processing efficiency during high vehicle computing power is improved, and the number of the on-board controllers is reduced.
In further embodiments, as shown in fig. 9, the method may include:
s101: the edge computing module broadcasts an initialization instruction to at least one client through the high-speed communication bus interface module.
S103: the edge calculation module obtains environment perception data.
S105: and at least one client acquires corresponding vehicle state data based on the initialization instruction and sends the vehicle state data to the edge computing module through the high-speed communication bus interface module.
S107: the edge calculation module determines control strategy data according to the vehicle state data and the environment perception data.
S109: and at least one client side performs vehicle-road cooperative control according to the control strategy data.
S201: the at least one client generates execution results and new vehicle state information.
S203: the edge calculation module obtains new context awareness data.
S205: the edge calculation module determines new control strategy data according to the new vehicle state information, the execution result and the new environment perception data.
In the embodiment, when the vehicle is in the automatic driving process, the vehicle is cooperatively controlled to generate an execution result, the edge calculation module determines a new control strategy according to the new vehicle state information, the execution result and the new environmental perception data, and adds the execution result as a determination basis of the control strategy, so that the system robustness can be improved.
S207: and at least one client side performs vehicle-road cooperative control according to the new control strategy data.
In further embodiments, as shown in fig. 10, the method may include:
s101: the edge computing module broadcasts an initialization instruction to at least one client through the high-speed communication bus interface module.
S103: the edge calculation module obtains environment perception data.
S105: and at least one client acquires corresponding vehicle state data based on the initialization instruction and sends the vehicle state data to the edge computing module through the high-speed communication bus interface module.
S1061: and the edge calculation module decrypts the environment perception data.
S1063: and carrying out signature verification processing on the decrypted environment perception data.
S1065: and when the verification is passed, the edge calculation module determines control strategy data according to the decrypted environment perception data and the vehicle state data.
S109: and at least one client side performs vehicle-road cooperative control according to the control strategy data.
In this embodiment, based on the consideration of data security, the security authentication is performed on the external data, and the security of the automatic driving of the vehicle can be improved.
The present application additionally provides an embodiment of a storage medium, where at least one instruction or at least one program is stored, and the at least one instruction or the at least one program is loaded and executed by a processor to implement the method according to any one of the above embodiments.
According to the above embodiment, the initialization instruction is broadcast to the at least one client side through the edge computing module, the edge computing module obtains environment sensing data, the at least one client side collects corresponding vehicle state data based on the initialization instruction, the vehicle state data is sent to the edge computing module through the high-speed communication bus interface module, the edge computing module determines control strategy data according to the vehicle state data and the environment sensing data, and finally, the at least one client side performs vehicle-road cooperative control according to the control strategy data to interconnect independent functional domains at a high speed, so that resource multiplexing and sharing of the functional domains are realized, and data processing efficiency during vehicle-road cooperative high-computing force control is improved.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that although embodiments described herein include some features included in other embodiments, not other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the claims of the present invention, any of the claimed embodiments may be used in any combination.
The present invention may also be embodied as apparatus or system programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps or the like not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several systems, several of these systems may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering and these words may be interpreted as names.
Claims (14)
1. A vehicle-road cooperative control system, characterized in that the system comprises:
the system comprises an edge calculation module, a high-speed communication bus interface module and at least one client;
the high-speed communication bus interface module is respectively connected with the edge calculation module and the at least one client;
the high-speed communication bus interface module is used for data interaction between the edge computing module and at least one client;
the edge computing module is used for acquiring environment perception data, broadcasting an initialization instruction to the at least one client through the high-speed communication bus interface module, receiving vehicle state data sent by the at least one client through the high-speed communication bus interface module, and determining control strategy data according to the vehicle state data and the environment perception data;
the at least one client is used for receiving an initialization instruction through a high-speed communication bus interface module, acquiring corresponding vehicle state data based on the initialization instruction, sending the vehicle state data to the edge calculation module through the high-speed communication bus interface module, and performing lane cooperative control according to the control strategy data;
the edge calculation module includes:
the system comprises a communication interface unit, a high-speed communication bus interface unit, a perception fusion processing unit, a decision planning processing unit, a data storage unit, a data acceleration processing unit and a power management unit;
the communication interface unit is respectively connected with the data acceleration processing unit and the perception fusion processing unit, the data acceleration processing unit is respectively connected with the perception fusion processing unit and the data storage unit, the decision planning processing unit is respectively connected with the perception fusion processing unit and the data storage unit, the high-speed communication bus interface unit is respectively connected with the decision planning processing unit and the data acceleration processing unit, and the power management unit is respectively connected with the perception fusion processing unit, the decision planning processing unit and the data acceleration processing unit;
the communication interface unit is used for receiving environment perception data;
the high-speed communication bus interface unit is used for carrying out data interaction with the at least one client;
the perception fusion processing unit is used for carrying out classification preprocessing on the vehicle state data and the environment perception data to obtain intermediate data and target data, receiving a fusion target list and predicting a perception result at the next moment based on the fusion target list and the target data;
the data acceleration processing unit is used for carrying out acceleration calculation on the intermediate data to obtain the fusion target list;
and the decision plan processing unit is used for determining control strategy data based on the sensing result at the next moment.
2. The system of claim 1, wherein the at least one client comprises:
any one or combination of a plurality of power assembly modules, a vehicle body electronic module, a vehicle safety module, an infotainment module and a data communication module.
3. The system of claim 1, wherein the at least one client comprises:
at least one edge calculation module.
4. The system of claim 1, wherein the edge calculation module further comprises:
and the hardware safety unit is respectively connected with the perception fusion processing unit and the data acceleration processing unit, and is used for performing safety certification on the environment perception data and the vehicle state data, and performing encryption signature and key generation management on the sent control strategy data.
5. The system of claim 1, wherein the sensor accessed by the communication interface unit comprises:
a combination of any one or more of a camera, a millimeter wave radar, a laser radar, an ultrasonic radar, a global positioning system, and an inertial measurement unit.
6. The system of claim 1, wherein the context awareness data comprises:
the vehicle-mounted sensor-based road side equipment comprises environment sensing data collected by the vehicle-mounted sensor, environment sensing data collected by the road side equipment and environment sensing data collected by surrounding vehicles.
7. The system of claim 1, wherein the edge calculation module further comprises:
and the heat dissipation unit is used for dissipating heat and cooling the edge calculation module, wherein the heat dissipation and cooling include heat dissipation and cooling in a passive, air-cooling or liquid-cooling mode.
8. A vehicle-road cooperative control method for performing vehicle-road cooperative control based on the system according to any one of claims 1 to 7, the method comprising:
the edge calculation module broadcasts an initialization instruction to at least one client through the high-speed communication bus interface module;
the edge calculation module acquires environment perception data;
the at least one client acquires corresponding vehicle state data based on the initialization instruction, and sends the vehicle state data to the edge calculation module through a high-speed communication bus interface module;
the edge calculation module determines control strategy data according to the vehicle state data and the environment perception data;
and the at least one client side performs vehicle-road cooperative control according to the control strategy data.
9. The method according to claim 8, wherein after the at least one client performs the cooperative vehicle-road control according to the control strategy data, the method further comprises:
the at least one client generates an execution result and new vehicle state information;
the edge calculation module acquires new environment perception data;
the edge calculation module determines new control strategy data according to the new vehicle state information, the execution result and new environment perception data;
and the at least one client side performs vehicle-road cooperative control according to the new control strategy data.
10. The method of claim 8, wherein the at least one client performing vehicle-to-vehicle cooperative control according to the control strategy data comprises:
the at least one client determines a corresponding component execution instruction according to the control strategy data;
the at least one client controls the corresponding component to execute the corresponding component execution instruction.
11. The method of claim 8, wherein after the edge calculation module determines control strategy data based on the vehicle state data and the environmental awareness data, the method further comprises:
the edge calculation module disassembles the control strategy data into a component execution instruction corresponding to the at least one client;
and the at least one client receives the corresponding component execution instruction and controls the corresponding component to execute the corresponding component execution instruction.
12. The method of claim 8, wherein the edge calculation module determining control strategy data from the vehicle state data and the environmental awareness data comprises:
the edge calculation module carries out classification preprocessing on the vehicle state data and the environment perception data to obtain intermediate data and target data;
the edge calculation module performs accelerated calculation on the intermediate data to obtain a fusion target list;
the edge calculation module predicts a perception result at the next moment based on the fusion target list and the target data;
and the edge calculation module determines control strategy data based on the sensing result at the next moment.
13. The method of claim 12, wherein prior to the edge calculation module determining control strategy data based on the vehicle state data and the environmental awareness data, the method further comprises:
the edge calculation module decrypts the environmental perception data;
carrying out signature verification processing on the decrypted environment perception data;
and when the verification is passed, the edge calculation module determines control strategy data according to the decrypted environment perception data and the vehicle state data.
14. A storage medium having stored therein at least one instruction or at least one program, the at least one instruction or the at least one program being loaded and executed by a processor to implement the method of any one of claims 8 to 13.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010943246.8A CN111818189B (en) | 2020-09-09 | 2020-09-09 | Vehicle road cooperative control system, method and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010943246.8A CN111818189B (en) | 2020-09-09 | 2020-09-09 | Vehicle road cooperative control system, method and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111818189A true CN111818189A (en) | 2020-10-23 |
| CN111818189B CN111818189B (en) | 2020-12-25 |
Family
ID=72860147
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010943246.8A Active CN111818189B (en) | 2020-09-09 | 2020-09-09 | Vehicle road cooperative control system, method and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111818189B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112633120A (en) * | 2020-12-18 | 2021-04-09 | 北京理工大学重庆创新中心 | Intelligent roadside sensing system based on semi-supervised learning and model training method |
| CN113301533A (en) * | 2021-07-28 | 2021-08-24 | 武汉理工大学 | Perception information compensation system and method based on vehicle-vehicle communication |
| CN114049767A (en) * | 2021-11-10 | 2022-02-15 | 刘鹏 | Edge calculation method and device and readable storage medium |
| CN115497195A (en) * | 2022-08-09 | 2022-12-20 | 重庆长安汽车股份有限公司 | Data control system, method, device and medium for realizing driving record |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103259868A (en) * | 2013-05-31 | 2013-08-21 | 清华大学 | Data collaborative processing system based on intelligent gateway |
| CN105278371A (en) * | 2015-10-10 | 2016-01-27 | 华南理工大学 | Control system and control method of integrated dual-control module of electric automobile |
| US20160318368A1 (en) * | 2015-04-29 | 2016-11-03 | International Business Machines Corporation | Automatic Vehicle Climate Control Based on Predicted Air Quality |
| CN107886750A (en) * | 2017-10-24 | 2018-04-06 | 北京邮电大学 | A kind of pilotless automobile control method and system based on over the horizon coordinating cognition |
| CN108944865A (en) * | 2018-06-28 | 2018-12-07 | 潍柴动力股份有限公司 | The braking system and its braking method of new energy vehicle |
| CN109164814A (en) * | 2018-11-21 | 2019-01-08 | 安徽江淮汽车集团股份有限公司 | Automatic driving control system towards highway scene |
| CN109866765A (en) * | 2019-01-11 | 2019-06-11 | 苏州工业园区职业技术学院 | A kind of driverless electric automobile safety traffic system |
| CN110239513A (en) * | 2019-05-07 | 2019-09-17 | 浙江吉利控股集团有限公司 | A kind of adaptive Lane Keeping System and method |
| CN111260924A (en) * | 2020-02-10 | 2020-06-09 | 北京中交国通智能交通系统技术有限公司 | Traffic intelligent control and service release strategy method adapting to edge calculation |
-
2020
- 2020-09-09 CN CN202010943246.8A patent/CN111818189B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103259868A (en) * | 2013-05-31 | 2013-08-21 | 清华大学 | Data collaborative processing system based on intelligent gateway |
| US20160318368A1 (en) * | 2015-04-29 | 2016-11-03 | International Business Machines Corporation | Automatic Vehicle Climate Control Based on Predicted Air Quality |
| CN105278371A (en) * | 2015-10-10 | 2016-01-27 | 华南理工大学 | Control system and control method of integrated dual-control module of electric automobile |
| CN107886750A (en) * | 2017-10-24 | 2018-04-06 | 北京邮电大学 | A kind of pilotless automobile control method and system based on over the horizon coordinating cognition |
| CN108944865A (en) * | 2018-06-28 | 2018-12-07 | 潍柴动力股份有限公司 | The braking system and its braking method of new energy vehicle |
| CN109164814A (en) * | 2018-11-21 | 2019-01-08 | 安徽江淮汽车集团股份有限公司 | Automatic driving control system towards highway scene |
| CN109866765A (en) * | 2019-01-11 | 2019-06-11 | 苏州工业园区职业技术学院 | A kind of driverless electric automobile safety traffic system |
| CN110239513A (en) * | 2019-05-07 | 2019-09-17 | 浙江吉利控股集团有限公司 | A kind of adaptive Lane Keeping System and method |
| CN111260924A (en) * | 2020-02-10 | 2020-06-09 | 北京中交国通智能交通系统技术有限公司 | Traffic intelligent control and service release strategy method adapting to edge calculation |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112633120A (en) * | 2020-12-18 | 2021-04-09 | 北京理工大学重庆创新中心 | Intelligent roadside sensing system based on semi-supervised learning and model training method |
| CN112633120B (en) * | 2020-12-18 | 2022-05-03 | 北京理工大学重庆创新中心 | Model training method of intelligent roadside sensing system based on semi-supervised learning |
| CN113301533A (en) * | 2021-07-28 | 2021-08-24 | 武汉理工大学 | Perception information compensation system and method based on vehicle-vehicle communication |
| CN113301533B (en) * | 2021-07-28 | 2021-11-23 | 武汉理工大学 | Perception information compensation system and method based on vehicle-vehicle communication |
| CN114049767A (en) * | 2021-11-10 | 2022-02-15 | 刘鹏 | Edge calculation method and device and readable storage medium |
| CN115497195A (en) * | 2022-08-09 | 2022-12-20 | 重庆长安汽车股份有限公司 | Data control system, method, device and medium for realizing driving record |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111818189B (en) | 2020-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111818189B (en) | Vehicle road cooperative control system, method and medium | |
| US11652827B2 (en) | Virtualized intrusion detection and prevention in autonomous vehicles | |
| EP3084676B1 (en) | Secure vehicular data management with enhanced privacy | |
| CN107948307B (en) | Safe communication method based on intelligent vehicle-mounted device of Internet of vehicles | |
| Reinhardt et al. | Domain controlled architecture | |
| CN112532574A (en) | Vehicle data validation | |
| KR101802858B1 (en) | Integrated data processing system and method for vehicle | |
| US20230257001A1 (en) | Integrated module for sensor data aggregation and control of sensor support hardware | |
| CN213715751U (en) | Domain controller | |
| US20230198783A1 (en) | Systems and Methods for Onboard Vehicle Certificate Distribution | |
| Elshaer et al. | Autonomous car implementation based on CAN bus protocol for IoT applications | |
| EP3821576A2 (en) | Optimizing size of protocol communication in a vehicle internal networks | |
| Shi et al. | Computing Systems for Autonomous Driving | |
| Kenjić et al. | Connectivity challenges in automotive solutions | |
| CN115509726B (en) | Sensor data access system | |
| Shreyas Ramachandran et al. | Development of flexible autonomous car system using machine learning and blockchain | |
| CN111666133A (en) | Vehicle-mounted infrastructure for automatically driving vehicle | |
| US11488404B2 (en) | Session unique access token for communications with a vehicle | |
| Grubmüller et al. | Predictive energy management on multi-core systems | |
| CN112585583B (en) | Data processing method and device and intelligent vehicle | |
| US11840160B1 (en) | Automatically adjusting ergonomic features of a vehicle seat | |
| US20220215035A1 (en) | Transforming model data | |
| US11792014B2 (en) | Systems and methods for vehicle message signing | |
| Yang et al. | Cames: enabling centralized automotive embedded systems with Time-Sensitive Network | |
| Chaaban et al. | Dynamic reconfiguration for high level in-vehicle applications using IEEE-1394 |
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 |