Automatic avoidance strategy generation method, system, medium and vehicle for special vehicle

Abstract

The application discloses a special vehicle automatic avoidance strategy generation method, system, medium and vehicle. The method comprises the following steps: obtaining, through a domain controller, a first motion state data set of existence data validity sent by a special vehicle autonomously, and a second motion state data set corresponding to the special vehicle and collected by a vehicle; matching and comparing the first motion state data set and the second motion state data set to obtain a basic motion state data set meeting matching requirements, and generating fusion data containing accurate motion state of the special vehicle by using the basic motion state data set, and inputting the fusion data into a planning control module; receiving, by the planning control module, the fusion data containing the accurate motion state of the special vehicle sent by the domain controller, and generating a corresponding automatic avoidance strategy according to preset avoidance judgment requirements. Through the technical scheme of the application, the special vehicle performing a task can be avoided on a road, and the passing efficiency of the special vehicle is improved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a method, system, medium, and vehicle for generating an automatic avoidance strategy for a special vehicle. Background Art

[0002] Special vehicles, such as police cars, fire trucks, ambulances, or engineering rescue vehicles, should enjoy the right of way when performing emergency tasks to ensure the smooth progress of the emergency tasks. Therefore, when encountering special vehicles, ordinary vehicles on the road should give way in a timely manner.

[0003] With the rapid development of autonomous driving technology, autonomous vehicles are becoming a common sight on the roads. The ability for autonomous vehicles to automatically avoid special vehicles performing emergency tasks has become a research focus.

[0004] Existing technologies typically add audio recognition equipment to autonomous vehicles, using this additional audio recognition equipment and software processing units to sense the distance, location, and status of special vehicles. Alternatively, a combination of audio and video is employed to extract special vehicle characteristics from multi-channel, real-time traffic audio and video information using deep learning.

[0005] However, using existing methods requires additional costs for autonomous vehicles, is technically challenging to implement, and cannot guarantee the accuracy of automatic avoidance. Therefore, how to quickly and accurately generate automatic avoidance strategies for special vehicles while ensuring production costs, thereby improving the efficiency of special vehicles, is a pressing issue. Summary of the Invention

[0006] The present invention provides a method, system, medium and vehicle for generating an automatic avoidance strategy for a special vehicle, which can solve the problem of low efficiency and accuracy in generating the automatic avoidance strategy in the prior art.

[0007] According to one aspect of the present invention, a method for generating an automatic avoidance strategy for a special vehicle is provided. The method is applied to a vehicle with an automatic driving function, and the method includes:

[0008] Acquire, through the domain controller, a first motion state data set of validity of existence data autonomously sent by the special vehicle, and a second motion state data set corresponding to the special vehicle collected by the vehicle;

[0009] Matching and comparing the first motion state data set and the second motion state data set by a domain controller to obtain a basic motion state data set that meets the matching requirements, and using the basic motion state data set to generate fused data containing the precise motion state of the special vehicle, and inputting the fused data into a planning control module;

[0010] The planning and control module receives the fusion data containing the precise motion status of special vehicles sent by the domain controller, and generates corresponding automatic avoidance strategies based on the preset avoidance judgment requirements.

[0011] According to another aspect of the present invention, a system for generating an automatic avoidance strategy for a special vehicle is provided, which is applied to a vehicle with an automatic driving function. The system includes:

[0012] The domain controller is configured to obtain a first motion state data set indicating the validity of the existence data autonomously sent by the special vehicle, and a second motion state data set corresponding to the special vehicle collected by the host vehicle; perform matching and comparison on the first motion state data set and the second motion state data set to obtain a basic motion state data set that meets the matching requirements, and use the basic motion state data set to generate fused data containing the precise motion state of the special vehicle, and input the fused data into the planning and control module;

[0013] The planning and control module is used to receive the fusion data sent by the domain controller containing the precise motion status of special vehicles, and generate corresponding automatic avoidance strategies based on preset avoidance judgment requirements.

[0014] According to another aspect of the present invention, there is provided a vehicle, comprising: a domain controller, a planning control module, and one or more processors;

[0015] a storage device for storing one or more programs,

[0016] When the one or more programs are executed by the one or more processors, the one or more processors are able to execute the method for generating an automatic avoidance strategy for a special vehicle as described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for generating an automatic avoidance strategy for a special vehicle described in any embodiment of the present invention when executed.

[0018] The technical solution of the embodiment of the present invention obtains a first motion state data set of validity of existence data autonomously sent by special vehicles, and a second motion state data set corresponding to the special vehicles actually collected by the vehicle itself, through a domain controller; then, the first motion state data set and the second motion state data set are matched and compared to obtain a basic motion state data set that meets the matching requirements, and the basic motion state data set is used to generate fused data containing the precise motion state of the special vehicle, and the fused data is input into a planning control module; thereafter, the fused data containing the precise motion state of the special vehicle sent by the domain controller is received by the planning control module, and a corresponding automatic avoidance strategy is generated according to preset avoidance judgment requirements, thereby solving the problem of low generation efficiency and accuracy of the automatic avoidance strategy for special vehicles, and being able to quickly and accurately generate automatic avoidance strategies for special vehicles for autonomous driving vehicles on the basis of ensuring production costs, thereby improving the traffic efficiency of special vehicles.

[0019] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 This is a flow chart of a method for generating an automatic avoidance strategy for a special vehicle provided in accordance with the first embodiment of the present invention;

[0022] Figure 2 This is a flow chart of a method for generating an automatic avoidance strategy for a special vehicle provided in accordance with a second embodiment of the present invention;

[0023] Figure 3 This is a flow chart of a method for generating fused data according to the second embodiment of the present invention;

[0024] Figure 4 This is a flowchart of an optional method for generating an automatic avoidance strategy for a special vehicle according to a second embodiment of the present invention;

[0025] Figure 5 This is a flow chart of a method for implementing an automatic avoidance strategy for a special vehicle provided in accordance with a second embodiment of the present invention;

[0026] Figure 6It is a structural schematic diagram of an automatic avoidance strategy generation system of a special vehicle according to the third embodiment of the present application.

[0027] Figure 7 It is a structural schematic diagram of a vehicle for implementing an automatic avoidance strategy generation method of a special vehicle according to the third embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to enable personnel in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative labor should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first", "second", "base", "initial" and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to only those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0030] It should be noted that the acquisition, storage, use, processing and the like of data in the technical solutions of the present application all comply with the relevant provisions of national laws and regulations.

[0031] Embodiment one

[0032] Figure 1 A flowchart of an automatic avoidance strategy generation method of a special vehicle according to the first embodiment of the present application is provided, the present embodiment can be applicable to a case where a vehicle with automatic driving function performs road avoidance on a special vehicle performing an emergency task, the method can be executed by an automatic avoidance strategy generation system of the special vehicle, the automatic avoidance strategy generation system of the special vehicle can be realized in the form of hardware and / or software, and the automatic avoidance strategy generation system of the special vehicle can be configured in a vehicle with automatic driving function. As shown in the figure, the method comprises: Figure 1

[0033] ​S110. Obtain, through the domain controller, a first motion state data set of validity data autonomously sent by the special vehicle, and a second motion state data set corresponding to the special vehicle actually collected by the vehicle.

[0034] Among them, the domain controller can refer to a highly autonomous driving (HAD) controller that analyzes data collected by sensors such as cameras, millimeter-wave radars, or ultrasonic radars to understand the scene.

[0035] Among them, special vehicles may refer to vehicles that perform emergency tasks. For example, they may include police cars, fire trucks, ambulances, or engineering rescue vehicles. The first motion state data set may refer to a data set that contains motion state data collected by the special vehicle itself and has data validity. For example, the first motion state data set may include the identity document (ID) of the special vehicle, the special vehicle's speed, direction, location information, acceleration, vehicle size, vehicle type, and timestamp information.

[0036] The host vehicle may refer to an intelligent vehicle with an automatic driving function that needs to avoid a special vehicle on the road. The second motion state data set may refer to a data set containing motion state data of the special vehicle collected by the host vehicle.

[0037] S120. Match and compare the first motion state data set and the second motion state data set through the domain controller to obtain a basic motion state data set that meets the matching requirements, and use the basic motion state data set to generate fused data containing the precise motion state of the special vehicle, and input the fused data into the planning control module.

[0038] The basic motion state dataset may refer to a dataset consisting of a first motion state dataset and a second motion state dataset that meet the matching requirements. For example, the first motion state dataset and the second motion state dataset may be matched one-to-one based on timestamp information. If the first motion state dataset and the second motion state dataset successfully match under the same timestamp information, the first motion state dataset and the second motion state dataset are added to the basic motion state dataset.

[0039] The fused data may refer to data obtained by fusing the first motion state dataset and the second motion state dataset in the basic motion state dataset that meet the matching requirements. Since the first motion state dataset and the second motion state dataset in the basic motion state dataset are motion state data that meet the matching requirements, fused data containing the precise motion state of the special vehicle can be obtained by fusing the first motion state dataset and the second motion state dataset in the basic motion state dataset.

[0040] S130. Receive, through the planning control module, the fusion data including the precise motion state of the special vehicle sent by the domain controller, and generate a corresponding automatic avoidance strategy according to the preset avoidance judgment requirements.

[0041] The planning and control module may refer to a module that makes decisions on the avoidance strategy of the host vehicle. The planning and control module may determine whether the host vehicle needs to avoid a special vehicle and the avoidance strategy to be executed when avoiding a special vehicle.

[0042] The preset avoidance determination requirement may refer to a pre-set requirement for assessing whether the host vehicle needs to yield to a special vehicle. For example, the determination may be based on the special vehicle's position relative to the host vehicle. Specifically, if the special vehicle performing an emergency mission is directly behind the host vehicle, the host vehicle needs to yield. Similarly, if the special vehicle performing an emergency mission is not in the same lane as the host vehicle, the host vehicle does not need to yield.

[0043] The automatic avoidance strategy may refer to a strategy for implementing an avoidance path for the host vehicle to avoid a special vehicle performing an emergency task. For example, if the special vehicle is directly behind the host vehicle and there are no other vehicles in front of the host vehicle, an automatic avoidance strategy may be generated to accelerate forward.

[0044] The technical solution of the embodiment of the present invention obtains a first motion state data set of validity of existence data autonomously sent by special vehicles, and a second motion state data set corresponding to the special vehicles actually collected by the vehicle itself, through a domain controller; then, the first motion state data set and the second motion state data set are matched and compared to obtain a basic motion state data set that meets the matching requirements, and the basic motion state data set is used to generate fused data containing the precise motion state of the special vehicle, and the fused data is input into a planning control module; thereafter, the fused data containing the precise motion state of the special vehicle sent by the domain controller is received by the planning control module, and a corresponding automatic avoidance strategy is generated according to preset avoidance judgment requirements, thereby solving the problem of low generation efficiency and accuracy of the automatic avoidance strategy for special vehicles, and being able to quickly and accurately generate automatic avoidance strategies for special vehicles for autonomous driving vehicles on the basis of ensuring production costs, thereby improving the traffic efficiency of special vehicles.

[0045] Example 2

[0046] Figure 2 The flowchart of the method for generating an automatic avoidance strategy for a special vehicle provided in the second embodiment of the present invention is a refinement of the above embodiment. In this embodiment, the operation of obtaining the first motion state data set of the validity of the existence data autonomously sent by the special vehicle through the domain controller is specifically refined. Specifically, it may include: obtaining the vehicle data corresponding to the vehicle through the domain controller, and the initial motion state set autonomously sent by the special vehicle; judging the validity of the initial motion state set based on the vehicle data through the domain controller, and using the initial motion state set that meets the validity judgment requirements as the first motion state data set corresponding to the special vehicle. Figure 2 As shown, the method includes:

[0047] S210. Obtain the vehicle data corresponding to the vehicle and the initial motion state set autonomously sent by the special vehicle through the domain controller.

[0048] Among them, the vehicle data may refer to the vehicle's motion state data collected by the vehicle through sensing devices such as cameras, lidars or millimeter-wave radars. Generally, different timestamps correspond to a set of vehicle data. The initial motion state set may refer to a set of motion state data collected by special vehicles through their own vehicle sensing devices. Exemplarily, the initial motion state set may include the vehicle ID, location information, speed information, direction information, acceleration, vehicle size, vehicle type and timestamp information of the special vehicle. Among them, the direction information may refer to the direction of travel of the special vehicle relative to the vehicle. For example, in the same direction or in the opposite direction. The position information may refer to the lane position of the special vehicle relative to the vehicle. For example, behind, to the left or to the right of the vehicle, etc.

[0049] Specifically, a special vehicle can collect its own initial motion state set and transmit it to its host vehicle using vehicle-to-vehicle (V2V) technology. Then, when the host vehicle confirms that the special vehicle is performing an emergency task, it can receive the special vehicle's initial motion state set via a telematics box (TBox) or V-Box. This allows V2V to obtain the special vehicle's initial motion state set, providing an effective foundation for subsequent operations.

[0050] It is worth noting that the speed information in the initial motion state set can be the absolute speed of the special vehicle at the current timestamp, or the relative speed of the special vehicle at the current timestamp. However, since data transmission between the special vehicle and the host vehicle is achieved through V2V technology, using relative speed information requires a higher error rate for the V2V technology. Therefore, in this embodiment of the present invention, absolute speed is preferred as the speed information in the initial motion state set.

[0051] S220. Performing a validity judgment on the initial motion state set based on the vehicle data through the domain controller, and using the initial motion state set that meets the validity judgment requirements as the first motion state data set corresponding to the special vehicle; wherein the first motion state data set includes: an identity identifier of the special vehicle.

[0052] Among them, the validity judgment requirement may refer to a pre-set requirement for evaluating whether the data in the initial motion state set is valid. For example, if the speed information is to be judged for validity, the absolute speed information in the initial motion state set may be obtained, and the absolute speed information may be subtracted from the vehicle speed in the vehicle data to obtain the relative speed information. Furthermore, by comparing the changes in the relative speed information of adjacent frames, it is possible to determine whether the speed information is valid. Specifically, if the relative speed information of the previous frame is 50km / h and the relative speed information of the next frame is 120km / h, it can be determined that the speed information is invalid. Similarly, the validity judgment of each data in the initial motion state set can be achieved.

[0053] Therefore, by using the data of this vehicle to judge the validity of each motion state data in the initial motion state set, the accuracy of the motion state data transmitted from the special vehicle to this vehicle can be guaranteed, providing an effective basis for the subsequent generation of fusion data.

[0054] S230. Obtain, through the domain controller, a second motion state data set of the special vehicle that matches the identity identifier and is collected by an on-board radar and / or an on-board camera in the vehicle.

[0055] The vehicle-mounted radar may refer to an intelligent vehicle-mounted millimeter-wave radar in the vehicle, and the vehicle-mounted camera may refer to an intelligent vehicle-mounted panoramic camera in the vehicle.

[0056] Specifically, after the vehicle receives the motion status data sent by the special vehicle, it can use the on-board radar and / or on-board camera in the vehicle to collect the actual motion status data of the special vehicle according to the identity identification corresponding to the special vehicle to form a second motion status data set of the special vehicle.

[0057] Therefore, through perception systems such as vehicle-mounted radar or vehicle-mounted cameras, special vehicles can be identified and their motion status can be identified more accurately, providing a basis for subsequent avoidance.

[0058] S240: Perform a matching comparison on the first motion state data set and the second motion state data set through a domain controller to obtain a basic motion state data set that meets matching requirements.

[0059] Specifically, after obtaining the second motion state data set corresponding to the special vehicle, the first motion state data set at the same timestamp can be matched and compared with the corresponding motion state data in the second motion state data set according to the timestamp information, and then a basic motion state data set that meets the matching requirements can be constructed, providing an effective basis for the subsequent generation of fusion data.

[0060] S250. The domain controller fuses the first basic data set and the second basic data set in the basic motion state data set according to the Kalman filter algorithm to generate fused data containing the precise motion state of the special vehicle, and inputs the fused data into the planning control module.

[0061] The Kalman filter algorithm may refer to an algorithm that utilizes a linear system state equation and system input and output observation data to optimally estimate the motion state data of a special vehicle. The first basic data set may refer to a first motion state data set that meets matching requirements. The second basic data set may refer to a second motion state data set that corresponds to the first motion state data set and meets matching requirements.

[0062] Figure 3 The flowchart of a fusion data generation method provided by an embodiment of the present invention is shown. Specifically, first, the vehicle data corresponding to the vehicle itself and the initial motion state set autonomously transmitted by the special vehicle are obtained. The validity of the initial motion state set is judged based on the vehicle data to obtain a first motion state data set that meets the validity judgment requirements. If the initial motion state set does not meet the validity judgment requirements, the vehicle data is saved to provide a basis for the validity judgment of the next timestamp. Then, a second motion state data set of the special vehicle that matches the identity identifier in the first motion state data set is obtained, collected by the vehicle-mounted radar and / or vehicle-mounted camera of the vehicle itself. The first motion state data set and the second motion state data set are matched and compared to obtain a basic motion state data set that meets the matching requirements. Finally, the first basic data set and the second basic data set in the basic motion state data set are input into the Kalman filter algorithm to generate fusion data containing the precise motion state of the special vehicle.

[0063] S260. Receive, through the planning control module, fused data including the precise motion state of the special vehicle sent by the domain controller.

[0064] S270. The planning control module determines the vehicle data and the fusion data according to the preset avoidance determination requirements, generates an avoidance determination result, and generates a corresponding automatic avoidance strategy according to the avoidance determination result.

[0065] The avoidance determination result may refer to the current avoidance requirement of the vehicle, and may include, for example, whether avoidance is required or not.

[0066] Specifically, the vehicle data and the fused data can be judged according to the preset avoidance judgment requirements to determine whether the vehicle needs to avoid the special vehicle. When avoidance is required, an automatic avoidance strategy including specific avoidance implementation measures is generated for the vehicle based on the relative information in the vehicle data and the fused data.

[0067] In an optional embodiment, after the planning control module receives the fusion data containing the precise motion status of the special vehicle sent by the domain controller and generates a corresponding automatic avoidance strategy based on preset avoidance judgment requirements, it also includes: generating a corresponding avoidance reminder based on the automatic avoidance strategy through the planning control module.

[0068] Specifically, after the corresponding automatic avoidance strategy is generated by the planning control module, the human-machine interface (HMI) can also be used to generate an avoidance reminder to promptly remind the driver of the vehicle, thereby improving the traffic efficiency of special vehicles.

[0069] In an optional embodiment, after the planning control module generates a corresponding avoidance reminder according to the automatic avoidance strategy, it also includes: determining whether the vehicle performs an avoidance action through the planning control module, and if not, implementing lateral control or longitudinal control according to the automatic avoidance strategy.

[0070] The lateral control may refer to controlling the lateral direction of the vehicle. For example, the lateral control of the vehicle may be achieved by issuing a control command to an electronic power steering (EPS).

[0071] The longitudinal control may refer to controlling the longitudinal speed of the vehicle. For example, the longitudinal control of the vehicle may be achieved by sending a control command to an intelligent brake system (IBS).

[0072] Specifically, after the planning and control module generates a corresponding avoidance reminder based on the automatic avoidance strategy, it can simultaneously determine whether the host vehicle has taken an avoidance action. If the host vehicle has not taken an avoidance action, lateral control or longitudinal control is implemented according to the automatic avoidance strategy. This allows the host vehicle to automatically perform an avoidance action if the driver ignores the avoidance reminder, improving the traffic efficiency of special vehicles.

[0073] The technical solution of the embodiment of the present invention obtains the vehicle data corresponding to the vehicle and the initial motion state set autonomously sent by the special vehicle through the domain controller, and judges the validity of the initial motion state set based on the vehicle data, and uses the initial motion state set that meets the validity judgment requirements as the first motion state data set corresponding to the special vehicle. Then, the domain controller obtains the second motion state data set of the special vehicle collected by the on-board radar and / or on-board camera in the vehicle and matched with the identity identifier in the first motion state data set, matches and compares the first motion state data set and the second motion state data set to obtain a basic motion state data set that meets the matching requirements, and fuses and processes the basic motion state data set according to the Kalman filter algorithm. The first basic data set and the second basic data set in the dynamic state data set are used to generate fused data containing the precise motion state of the special vehicle, and the fused data is input into the planning and control module. Furthermore, the planning and control module receives the fused data containing the precise motion state of the special vehicle sent by the domain controller, and judges the vehicle data and the fused data according to the preset avoidance judgment requirements to generate an avoidance judgment result, and generates a corresponding automatic avoidance strategy based on the avoidance judgment result, which solves the problem of low generation efficiency and accuracy of the automatic avoidance strategy for special vehicles. On the basis of ensuring production costs, it can quickly and accurately generate automatic avoidance strategies for special vehicles for autonomous driving vehicles, thereby improving the traffic efficiency of special vehicles.

[0074] Figure 4The flowchart of an optional method for generating an automatic avoidance strategy for a special vehicle provided by an embodiment of the present invention is shown. Specifically, first, the domain controller obtains the motion state of the special vehicle acquired by the on-board radar (i.e., intelligent on-board millimeter-wave radar) of the host vehicle, as well as the feature information of the special vehicle extracted by the on-board camera (i.e., intelligent on-board panoramic camera) and deep neural network of the host vehicle. The motion state and feature information are combined to form a second motion state dataset corresponding to the special vehicle. In addition, an initial motion state set autonomously transmitted by the on-board equipment of the special vehicle based on vehicle-to-vehicle technology is obtained. After the validity of the initial motion state set is determined based on the data of the host vehicle, a first motion state dataset corresponding to the special vehicle that meets the validity determination requirements is generated. The first motion state dataset and the second motion state dataset are then input into a Kalman filter algorithm for data fusion to obtain fused data containing the precise motion state of the special vehicle. Finally, the planning and control module determines the host vehicle data and the fused data according to preset avoidance determination requirements, generates an avoidance determination result, and generates a corresponding automatic avoidance strategy based on the avoidance determination result.

[0075] Figure 5 The flowchart of a method for implementing an automatic avoidance strategy for a special vehicle provided by an embodiment of the present invention is shown. Specifically, a first motion state dataset corresponding to the special vehicle, indicating data validity, is acquired through vehicle-to-vehicle technology to achieve vehicle-to-vehicle perception. Furthermore, a second motion state dataset of the special vehicle matching the identity in the first motion state dataset is acquired through on-board radar or a vehicle camera to achieve on-board perception. After fusion prediction is performed based on the first and second motion state datasets to obtain fused data, a planning and control module receives fused data containing the precise motion state of the special vehicle from a domain controller. The fused data is then compared with the host vehicle data and the fused data according to preset avoidance determination requirements to generate an avoidance determination result. When the host vehicle needs to avoid an obstacle, an automatic avoidance strategy is generated based on the avoidance determination result. Furthermore, the planning and control module generates an avoidance reminder based on the automatic avoidance strategy. Simultaneously, a determination is made as to whether the host vehicle has performed an avoidance maneuver. If not, lateral or longitudinal control is implemented according to the automatic avoidance strategy to complete the implementation of the automatic avoidance strategy.

[0076] Example 3

[0077] Figure 6 This is a structural diagram of an automatic avoidance strategy generation system for special vehicles provided in the third embodiment of the present invention. Figure 6 As shown, the system includes: a domain controller 310 and a planning control module 320;

[0078] The domain controller 310 is configured to obtain a first motion state data set indicating the validity of the existence data autonomously sent by the special vehicle, and a second motion state data set corresponding to the special vehicle collected by the host vehicle; perform matching and comparison on the first motion state data set and the second motion state data set to obtain a basic motion state data set that meets the matching requirements; and use the basic motion state data set to generate fused data containing the precise motion state of the special vehicle, and input the fused data into the planning control module 320;

[0079] The planning control module 320 is used to receive the fusion data containing the precise motion status of the special vehicle sent by the domain controller 310, and generate a corresponding automatic avoidance strategy according to the preset avoidance judgment requirements.

[0080] The technical solution of the embodiment of the present invention obtains a first motion state data set of validity of existence data autonomously sent by special vehicles, and a second motion state data set corresponding to the special vehicles actually collected by the vehicle itself, through a domain controller; then, the first motion state data set and the second motion state data set are matched and compared to obtain a basic motion state data set that meets the matching requirements, and the basic motion state data set is used to generate fused data containing the precise motion state of the special vehicle, and the fused data is input into a planning control module; thereafter, the fused data containing the precise motion state of the special vehicle sent by the domain controller is received by the planning control module, and a corresponding automatic avoidance strategy is generated according to preset avoidance judgment requirements, thereby solving the problem of low generation efficiency and accuracy of the automatic avoidance strategy for special vehicles, and being able to quickly and accurately generate automatic avoidance strategies for special vehicles for autonomous driving vehicles on the basis of ensuring production costs, thereby improving the traffic efficiency of special vehicles.

[0081] Optionally, the domain controller 310 may be specifically configured to:

[0082] Obtain the vehicle data corresponding to the vehicle and the initial motion state set sent autonomously by the special vehicle;

[0083] The validity of the initial motion state set is judged based on the vehicle data, and the initial motion state set that meets the validity judgment requirements is used as the first motion state data set corresponding to the special vehicle.

[0084] Optionally, the first motion state data set includes: an identity of a special vehicle;

[0085] The domain controller 310 can be specifically used to obtain a second motion state data set of the special vehicle that matches the identity identifier and is collected by the vehicle-mounted radar and / or vehicle-mounted camera in the vehicle.

[0086] Optionally, the domain controller 310 may be specifically configured to:

[0087] The first basic data set and the second basic data set in the basic motion state data set are fused and processed according to the Kalman filter algorithm to generate fused data containing the precise motion state of the special vehicle.

[0088] Optionally, the planning control module 320 may be specifically configured to:

[0089] The vehicle data and the fusion data are judged according to the preset avoidance judgment requirements to generate an avoidance judgment result, and a corresponding automatic avoidance strategy is generated according to the avoidance judgment result.

[0090] Optionally, the planning control module 320 can also be used to: after receiving the fusion data containing the precise motion status of the special vehicle sent by the domain controller through the planning control module, and generating a corresponding automatic avoidance strategy based on preset avoidance judgment requirements, generate a corresponding avoidance reminder based on the automatic avoidance strategy.

[0091] Optionally, the planning control module 320 can also be used to: after the planning control module generates a corresponding avoidance reminder based on the automatic avoidance strategy, determine whether the vehicle performs an avoidance action; if not, implement lateral control or longitudinal control based on the automatic avoidance strategy.

[0092] The automatic avoidance strategy generation system for special vehicles provided in an embodiment of the present invention can execute the automatic avoidance strategy generation method for special vehicles provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0093] Example 4

[0094] Figure 7 A schematic diagram of the structure of a vehicle provided in the fourth embodiment of the present invention is shown in FIG. Figure 7 As shown, the vehicle includes a processor 410, a memory 420, an input device 430, an output device 440, a domain controller 450 and a planning control module 460; the number of processors 410 in the vehicle can be one or more, Figure 7 In the figure, a processor 410 is used as an example; the processor 410, memory 420, input device 430, output device 440, domain controller 450 and planning control module 460 in the vehicle can be connected via a bus or other means. Figure 7 The bus connection is taken as an example.

[0095] The memory 420, as a computer readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the automatic avoidance strategy generation method of the special vehicle in the embodiment of the application. The processor 410 executes various functional applications and data processing of the vehicle by running the software programs, instructions and modules stored in the memory 420, that is, implements the automatic avoidance strategy generation method of the special vehicle as described above.

[0096] The method comprises:

[0097] The first motion state data set of the existence data autonomously sent by the special vehicle is acquired by the domain controller, and the second motion state data set corresponding to the special vehicle is collected by the host vehicle;

[0098] The first motion state data set and the second motion state data set are matched and compared by the domain controller to obtain a basic motion state data set meeting the matching requirement, and a fusion data containing the accurate motion state of the special vehicle is generated by using the basic motion state data set, and the fusion data is input into the planning control module;

[0099] The fusion data containing the accurate motion state of the special vehicle sent by the domain controller is received by the planning control module, and a corresponding automatic avoidance strategy is generated according to a preset avoidance judgment requirement.

[0100] The memory 420 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system and application programs required by at least one function; the data storage area can store data created according to the use of the terminal and the like. In addition, the memory 420 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some examples, the memory 420 can further include a memory remotely arranged with respect to the processor 410, and these remote memories can be connected to the vehicle through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0101] The input device 430 can be used to receive input digital or character information, and generate key signal input related to user settings and function control of the vehicle. The output device 440 can include a display device such as a display screen.

[0102] Embodiment five

[0103] The embodiment five of the application further provides a storage medium containing computer executable instructions, which, when executed by a computer processor, are used to execute an automatic avoidance strategy generation method of a special vehicle, and the method comprises:

[0104] Acquire, through the domain controller, a first motion state data set of validity of existence data autonomously sent by the special vehicle, and a second motion state data set corresponding to the special vehicle collected by the vehicle;

[0105] Matching and comparing the first motion state data set and the second motion state data set by a domain controller to obtain a basic motion state data set that meets the matching requirements, and using the basic motion state data set to generate fused data containing the precise motion state of the special vehicle, and inputting the fused data into a planning control module;

[0106] The planning and control module receives the fusion data containing the precise motion status of special vehicles sent by the domain controller, and generates corresponding automatic avoidance strategies based on the preset avoidance judgment requirements.

[0107] Of course, the storage medium containing computer-executable instructions provided in an embodiment of the present invention is not limited to the method operations described above, and can also execute related operations in the automatic avoidance strategy generation method for special vehicles provided in any embodiment of the present invention.

[0108] Through the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented with the help of software and necessary general-purpose hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0109] It is worth noting that in the embodiment of the automatic avoidance strategy generation system for special vehicles mentioned above, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0110] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0111] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for generating an automatic avoidance strategy for a special vehicle, characterized in that: Applied to a vehicle with an autonomous driving function, the method includes: Acquire, through the domain controller, a first motion state data set of validity of existence data autonomously sent by the special vehicle, and a second motion state data set corresponding to the special vehicle collected by the vehicle; Matching and comparing the first motion state data set and the second motion state data set by a domain controller to obtain a basic motion state data set that meets the matching requirements, and using the basic motion state data set to generate fused data containing the precise motion state of the special vehicle, and inputting the fused data into a planning control module; The planning and control module receives the fusion data containing the precise motion status of the special vehicle sent by the domain controller, and generates the corresponding automatic avoidance strategy according to the preset avoidance judgment requirements; The first motion state data set of the validity of the existence data autonomously sent by the special vehicle is obtained through the domain controller, including: Obtain the vehicle data corresponding to the vehicle through the domain controller, as well as the initial motion state set sent autonomously by the special vehicle; The domain controller performs validity judgment on the initial motion state set based on the vehicle data, and uses the initial motion state set that meets the validity judgment requirements as the first motion state data set corresponding to the special vehicle.

2. The method according to claim 1, characterized in that The first motion state data set includes: an identity identifier of the special vehicle; The second motion state data set corresponding to the special vehicle collected by the vehicle is obtained through the domain controller, including: A second motion state data set of the special vehicle matching the identity identifier is obtained through the domain controller and collected by the vehicle-mounted radar and / or vehicle-mounted camera in the vehicle.

3. The method according to claim 1, characterized in that The domain controller uses the basic motion state data set to generate fused data containing the precise motion state of the special vehicle, including: The domain controller fuses the first basic data set and the second basic data set in the basic motion state data set according to the Kalman filter algorithm to generate fused data containing the precise motion state of the special vehicle.

4. The method according to claim 1, wherein The planning and control module generates corresponding automatic avoidance strategies based on preset avoidance judgment requirements, including: The planning control module judges the vehicle data and the fusion data according to the preset avoidance judgment requirements, generates an avoidance judgment result, and generates a corresponding automatic avoidance strategy based on the avoidance judgment result.

5. The method according to claim 1, wherein After the planning control module receives the fusion data including the precise motion state of the special vehicle sent by the domain controller and generates a corresponding automatic avoidance strategy according to the preset avoidance judgment requirement, the method further includes: The planning control module generates a corresponding avoidance reminder based on the automatic avoidance strategy.

6. The method according to claim 5, characterized in that After the planning control module generates a corresponding avoidance reminder according to the automatic avoidance strategy, the method further includes: The planning control module determines whether the vehicle performs an avoidance action. If not, lateral control or longitudinal control is implemented according to the automatic avoidance strategy.

7. A system for generating automatic avoidance strategies for special vehicles, characterized in that: Applied to a vehicle with an autonomous driving function, the system includes: The domain controller is configured to obtain a first motion state data set indicating the validity of the existence data autonomously sent by the special vehicle, and a second motion state data set corresponding to the special vehicle collected by the host vehicle; perform matching and comparison on the first motion state data set and the second motion state data set to obtain a basic motion state data set that meets the matching requirements, and use the basic motion state data set to generate fused data containing the precise motion state of the special vehicle, and input the fused data into the planning and control module; The planning and control module is used to receive the fusion data sent by the domain controller containing the precise motion status of the special vehicle and generate the corresponding automatic avoidance strategy according to the preset avoidance judgment requirements; Among them, the domain controller is specifically used to: obtain the vehicle data corresponding to the vehicle itself, and the initial motion state set sent autonomously by the special vehicle; judge the validity of the initial motion state set based on the vehicle data, and use the initial motion state set that meets the validity judgment requirements as the first motion state data set corresponding to the special vehicle.

8. A vehicle, characterized in that: The vehicle comprises: domain controller, planning control module, one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method for generating an automatic avoidance strategy for a special vehicle as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for generating an automatic avoidance strategy for a special vehicle according to any one of claims 1 to 6 when executed.

Images