An offline time detection method, system and medium based on vehicle desired speed

Abstract

The application relates to an offline time detection method, system and medium based on vehicle expected speed, which comprises the following steps: U1. A vehicle travels on a road, real-time acquisition of driving acceleration of the vehicle and heading angle data information of the vehicle based on a vehicle-mounted IMU, and real-time acquisition of position data information of the vehicle based on a vehicle-mounted GPS; U2. Based on the position data information of the vehicle, the driving acceleration of the vehicle and the heading angle data information of the vehicle, a multivariate vehicle expected speed algorithm is used to calculate the expected value of the vehicle speed at different times and positions, so that the expected speed data information of the vehicle at different times and positions is obtained. The application can accurately detect the offline time of the vehicle, and the detection process is suitable for various and complex environments, has a wide application range, and is beneficial to popularization and use.

Description

Technical Field

[0001] This invention relates to the field of autonomous vehicle technology, and in particular to an offline time detection method, system, and medium based on the desired speed of a vehicle. Background Technology

[0002] With the continuous development of autonomous driving technology, when a driverless vehicle is offline or about to go offline due to insufficient battery power or system malfunction, continuing to operate in this state can pose a danger to the vehicle or cause inconvenience to other vehicles. How to detect when a driverless vehicle enters or is about to enter an offline state has become an urgent problem to be solved.

[0003] In the prior art, patent (application number: 201610143661.9) discloses a user offline detection method and system. The method includes: each member's mobile terminal within a group sends a heartbeat data packet to a server at first preset time intervals. Each time the server receives a heartbeat data packet from a mobile terminal, it creates a user record for the sending mobile terminal and starts timing. The user record includes an expiration time, where the expiration time = first current time + second preset time, and the second preset time is greater than the first preset time. If the server receives an operation instruction from the sending mobile terminal within the expiration time, it obtains the second current time and updates the expiration time using the second current time, where the expiration time = second current time + second preset time. However, client internet access has limited data usage, especially when multiple server services are needed, which may lead to exceeding the data limit. Furthermore, the process for determining whether a vehicle is offline is incomplete.

[0004] In the prior art, a patent (application number: 201410467634.8) discloses an offline detection method for buses. The method involves: Step 1, setting multiple equidistant special coordinate points on a planned bus route, with a distance 'd' between any two special coordinate points; Step 2, setting a square parallel to the latitude and longitude coordinates at each special coordinate point; Step 3, downloading the special coordinate points and their markings to the onboard controller; Step 4, the onboard controller detecting the coordinate information of the onboard GPS; Step 5, prioritizing the judgment of special coordinate points near the current stop; if no match is found, then judging the next special coordinate point; Step 6, when the onboard GPS coordinate information falls within the square of the special coordinate point, the vehicle is considered online; otherwise, the vehicle is considered offline. This patent only utilizes the judgment of coordinate points for offline vehicle detection, which is rather one-sided and inaccurate. Summary of the Invention

[0005] In view of the shortcomings of the prior art, the present invention provides an offline time detection method, system and medium based on the desired speed of a vehicle. It can not only accurately detect the offline time of a vehicle, but also the detection process is applicable to a variety of complex environments, with a wide range of applications, which is conducive to its widespread use.

[0006] To achieve the above and other related objectives, the present invention provides the following technical solution:

[0007] An offline time detection method based on the desired speed of a vehicle, the method comprising:

[0008] U1. When the vehicle is driving on the road, the vehicle's acceleration and heading angle data are acquired in real time based on the onboard IMU, and the vehicle's position data is acquired in real time based on the onboard GPS.

[0009] U2. Based on the vehicle's position data, the vehicle's acceleration and heading angle data, a multivariate vehicle expected speed algorithm is used to calculate the expected values ​​of the vehicle's speed at different times and positions, thereby obtaining the expected speed data of the vehicle at different times and positions.

[0010] U3. Based on the expected speed data of the vehicle at different times and locations, the expected speed at the same location at different times is optimized using the swarm optimization algorithm to obtain the optimized expected speed data of the same location.

[0011] U4. Based on the optimized expected speed data information at the same location, an offline time detection function Q is constructed to detect the real-time speed of the vehicle, obtain the vehicle speed detection data information, and set a preset threshold. If the vehicle speed detection data information is less than the preset threshold, the vehicle is not offline; if it is higher than the preset threshold, the vehicle is in an offline state.

[0012] Furthermore, in step U2, the calculation of the expected vehicle speed at different times and locations using a multivariate vehicle expected speed algorithm includes:

[0013] U21. Based on the vehicle's position data, acceleration, and heading angle data, a multivariate probability density function G for the vehicle is established.

[0014]

[0015] X = [x t ,y t ,a t ,θ t ,t],

[0016]

[0017] Among them, (x t ,y t ) represents the vehicle's location data at time t, a t Let θ be the acceleration data of the vehicle at time t. t Let be the vehicle's heading angle data at time t, X be the vehicle's state data array, λ be the vehicle's mean state data array over time Δt, and Σ be the vehicle's covariance matrix data. This provides the average vehicle position data over a time interval Δt. This provides the average acceleration data of the vehicle over a time interval Δt. This provides the mean heading angle data for the vehicle over a time interval Δt.

[0018] U22. Based on the multivariate probability density function G of the vehicle, establish the expected value function H of the vehicle speed at different times and locations.

[0019]

[0020] Where X is the vehicle's state data array, X Δt This represents the change in the vehicle's state data array over time Δt.

[0021] U23. Based on the expected value function H of the vehicle speed at different times and locations, obtain the expected speed data information of the vehicle at different times and locations.

[0022] Furthermore, the vehicle covariance matrix data Σ is given by Σ=E[(X-λ)(X-λ)] T ],

[0023] Where X is the vehicle state data array, and λ is the vehicle state mean data array over time Δt.

[0024] Furthermore, the average vehicle position data over the time interval Δt. for,

[0025] The average acceleration data of the vehicle within the time interval Δt. for,

[0026]

[0027] The mean heading angle data of the vehicle within the time interval Δt. for,

[0028]

[0029] Among them, α iLet x be the position weight coefficient of the vehicle at different times. i ,y i Let be the vehicle's location data at time i, and a i Let θ be the acceleration data of the vehicle at time i. i Here is the heading angle data of the vehicle at time i, β i δ represents the weighting coefficient for the vehicle's acceleration at different times. i The weighting coefficients are the heading angles of the vehicle at different times.

[0030] Furthermore, in step U3, the optimization of the desired velocity at the same location at different times using the swarm optimization algorithm includes:

[0031] U31. Based on the expected speed data of the vehicle at different times and locations, the population of the cysts is initialized, the population parameters and boundary conditions are set, and the population data information of the initialized cysts is obtained.

[0032] U32. Based on the population data information of the initialized sac-like structures, establish the fitness function M of the population.

[0033]

[0034] Among them, v t Let v be the expected speed of the vehicle at time t. (x,y) For the expected speed of vehicles at different locations, obtain the fitness value data of individual cysts;

[0035] U33. Based on the fitness value data of the individuals in the cyst population, establish the position update function L for the individuals in the cyst population.

[0036]

[0037] Where c is the adaptive weight value, which obtains the location update data information of the individual cysts;

[0038] U34. Based on the location update data of the individual cysts, the cyst population is optimized to obtain the optimized expected velocity data of the same location.

[0039] Furthermore, the position update function L(t) for the individual sac clusters,

[0040]

[0041] Where, M(t) max Let M(t) be the maximum fitness function of the population at time t. min Let t be the minimum fitness function of the population at time t, and c be the adaptive weight value.

[0042] Furthermore, the adaptive weight value c is,

[0043]

[0044] Where Δt is the time interval between different moments of the vehicle, and t is the vehicle's time.

[0045] Furthermore, in step U4, the offline time detection function Q is constructed as follows:

[0046]

[0047] Among them, v 期 The optimized expected speed data for the same location is represented by v0, which is the vehicle's speed evaluation factor.

[0048] To achieve the above and other related objectives, the present invention also provides an offline time detection system based on vehicle desired speed, including a computer device programmed or configured to perform the steps of any of the offline time detection methods based on vehicle desired speed described above.

[0049] To achieve the above and other related objectives, the present invention also provides a computer-readable storage medium storing a computer program programmed or configured to perform any of the offline time detection methods based on desired vehicle speeds as described above.

[0050] The present invention has the following positive effects:

[0051] 1. This invention uses a multivariate vehicle expected speed algorithm to calculate the expected value of vehicle speed at different times and locations, obtaining expected speed data information of vehicles at different times and locations. In addition, it combines the use of a pod ensemble optimization algorithm to optimize the expected speed at the same location at different times. This not only accurately obtains the expected speed of the vehicle, but also further improves the accuracy of the expected speed of the vehicle by analyzing the expected speed at the same location at different times.

[0052] 2. This invention detects the real-time speed of a vehicle by constructing an offline time detection function Q. The detection process is fast and timely, and can provide timely feedback on the status of autonomous vehicles, thereby reducing the accident rate of autonomous vehicles and improving safety. At the same time, it can be applied to a variety of complex environments, has a wide range of applications, and is conducive to its widespread use. Attached Figure Description

[0053] Figure 1 This is a schematic diagram of the method flow of the present invention;

[0054] Figure 2 This is a flowchart illustrating the multivariate vehicle desired speed algorithm of the present invention.

[0055] Figure 3 This is a flowchart illustrating the encapsulation optimization algorithm of the present invention;

[0056] Figure 4 This is a schematic diagram of the system-vehicle communication structure of the present invention. Detailed Implementation

[0057] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0058] Example 1: As Figure 1 As shown, an offline time detection method based on the desired speed of a vehicle is provided, the method comprising:

[0059] U1. When the vehicle is driving on the road, the vehicle's acceleration and heading angle data are acquired in real time based on the onboard IMU, and the vehicle's position data is acquired in real time based on the onboard GPS.

[0060] U2. Based on the vehicle's position data, the vehicle's acceleration and heading angle data, a multivariate vehicle expected speed algorithm is used to calculate the expected values ​​of the vehicle's speed at different times and positions, thereby obtaining the expected speed data of the vehicle at different times and positions.

[0061] U3. Based on the expected speed data of the vehicle at different times and locations, the expected speed at the same location at different times is optimized using the swarm optimization algorithm to obtain the optimized expected speed data of the same location.

[0062] U4. Based on the optimized expected speed data information at the same location, an offline time detection function Q is constructed to detect the real-time speed of the vehicle, obtain the vehicle speed detection data information, and set a preset threshold. If the vehicle speed detection data information is less than the preset threshold, the vehicle is not offline; if it is higher than the preset threshold, the vehicle is in an offline state.

[0063] In this embodiment, as Figure 2 As shown, in step U2, the calculation of the expected vehicle speed at different times and locations using a multivariate vehicle expected speed algorithm includes:

[0064] U21. Based on the vehicle's position data, acceleration, and heading angle data, a multivariate probability density function G for the vehicle is established.

[0065]

[0066] X = [x t ,y t ,a t ,θ t ,t],

[0067]

[0068] Among them, (x t ,y t ) represents the vehicle's location data at time t, a t Let θ be the acceleration data of the vehicle at time t. t Let be the vehicle's heading angle data at time t, X be the vehicle's state data array, λ be the vehicle's mean state data array over time Δt, and Σ be the vehicle's covariance matrix data. This provides the average vehicle position data over a time interval Δt. This provides the average acceleration data of the vehicle over a time interval Δt. This provides the mean heading angle data for the vehicle over a time interval Δt.

[0069] U22. Based on the multivariate probability density function G of the vehicle, establish the expected value function H of the vehicle speed at different times and locations.

[0070]

[0071] Where X is the vehicle's state data array, X Δt This represents the change in the vehicle's state data array over time Δt.

[0072] U23. Based on the expected value function H of the vehicle speed at different times and locations, obtain the expected speed data information of the vehicle at different times and locations.

[0073] In this embodiment, the vehicle covariance matrix data Σ is given by Σ=E[(X-λ)(X-λ)] T ],

[0074] Where X is the vehicle state data array, and λ is the vehicle state mean data array over time Δt.

[0075] In this embodiment, the average vehicle position data (x) over the time interval Δt t ,y t )for,

[0076]

[0077] The average acceleration data of the vehicle within the time interval Δt. for,

[0078]

[0079] The mean heading angle data of the vehicle within the time interval Δt. for,

[0080]

[0081] Among them, α i Let x be the position weight coefficient of the vehicle at different times. i ,y i Let be the vehicle's location data at time i, and a i Let θ be the acceleration data of the vehicle at time i. i Here is the heading angle data of the vehicle at time i, β i δ represents the weighting coefficient for the vehicle's acceleration at different times. i The weighting coefficients are the heading angles of the vehicle at different times.

[0082] Example 2: Based on the offline time detection method based on the desired vehicle speed in Example 1, the present invention will be further explained and described below.

[0083] like Figure 1 As shown, an offline time detection method based on the desired speed of a vehicle is provided, the method comprising:

[0084] U1. When the vehicle is driving on the road, the vehicle's acceleration and heading angle data are acquired in real time based on the onboard IMU, and the vehicle's position data is acquired in real time based on the onboard GPS.

[0085] U2. Based on the vehicle's position data, the vehicle's acceleration and heading angle data, a multivariate vehicle expected speed algorithm is used to calculate the expected values ​​of the vehicle's speed at different times and positions, thereby obtaining the expected speed data of the vehicle at different times and positions.

[0086] U3. Based on the expected speed data of the vehicle at different times and locations, the expected speed at the same location at different times is optimized using the swarm optimization algorithm to obtain the optimized expected speed data of the same location.

[0087] U4. Based on the optimized expected speed data information at the same location, an offline time detection function Q is constructed to detect the real-time speed of the vehicle, obtain the vehicle speed detection data information, and set a preset threshold. If the vehicle speed detection data information is less than the preset threshold, the vehicle is not offline; if it is higher than the preset threshold, the vehicle is in an offline state.

[0088] In this embodiment, as Figure 3 As shown, in step U3, the optimization of the expected velocity at the same location at different times using the swarm optimization algorithm includes:

[0089] U31. Based on the expected speed data of the vehicle at different times and locations, the population of the cysts is initialized, the population parameters and boundary conditions are set, and the population data information of the initialized cysts is obtained.

[0090] U32. Based on the population data information of the initialized sac-like structures, establish the fitness function M of the population.

[0091]

[0092] Among them, v t Let v be the expected speed of the vehicle at time t. (x,y) For the expected speed of vehicles at different locations, obtain the fitness value data of individual cysts;

[0093] U33. Based on the fitness value data of the individuals in the cyst population, establish the position update function L for the individuals in the cyst population.

[0094]

[0095] Where c is the adaptive weight value, which obtains the location update data information of the individual cysts;

[0096] U34. Based on the location update data of the individual cysts, the cyst population is optimized to obtain the optimized expected velocity data of the same location.

[0097] In this embodiment, the position update function L(t) of the sac cluster individuals,

[0098]

[0099] Where, M(t) max Let M(t) be the maximum fitness function of the population at time t. min Let t be the minimum fitness function of the population at time t, and c be the adaptive weight value.

[0100] In this embodiment, the adaptive weight value c is,

[0101]

[0102] Where Δt is the time interval between different moments of the vehicle, and t is the vehicle's time.

[0103] In this embodiment, in step U4, the offline time detection function Q is constructed as follows:

[0104] Among them, v 期 The optimized expected speed data for the same location is represented by v0, which is the vehicle's speed evaluation factor.

[0105] In this embodiment, the present invention provides an offline time detection system based on vehicle expected speed, including a computer device programmed or configured to perform the steps of any of the offline time detection methods based on vehicle expected speed described above.

[0106] like Figure 4 As shown, it includes a vehicle microcontroller unit (MCU), a cloud platform (CloudService), a SIM card (Subscriber Identity Module), and a CAN (Controller Area Network). The MCU configures the offline detection time of the vehicle in the configuration file based on the pre-designed speed of the autonomous driving vehicle. When the MCU program starts, it can load the configuration file and send heartbeat messages to the cloud platform at a fixed frequency according to the time in the configuration file to determine whether the vehicle is online.

[0107] In this embodiment, the present invention provides a computer-readable storage medium storing a computer program programmed or configured to perform any of the offline time detection methods based on desired vehicle speeds described herein.

[0108] Any references to memory, storage, database, or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0109] In summary, this invention can not only accurately detect the offline time of a vehicle, but the detection process is also applicable to a variety of complex environments, making it widely applicable and conducive to its widespread use.

[0110] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. An offline time detection method based on the desired speed of a vehicle, characterized in that, The method includes: U1. When the vehicle is driving on the road, the vehicle's acceleration and heading angle data are acquired in real time based on the onboard IMU, and the vehicle's position data is acquired in real time based on the onboard GPS. U2. Based on the vehicle's position data, the vehicle's acceleration and heading angle data, a multivariate vehicle expected speed algorithm is used to calculate the expected values ​​of the vehicle's speed at different times and positions, thereby obtaining the expected speed data of the vehicle at different times and positions. U3. Based on the expected speed data of the vehicle at different times and locations, the expected speed at the same location at different times is optimized using the swarm optimization algorithm to obtain the optimized expected speed data of the same location. U4. Based on the optimized expected speed data information at the same location, an offline time detection function Q is constructed to detect the real-time speed of the vehicle, obtain the vehicle speed detection data information, and set a preset threshold. If the vehicle speed detection data information is less than the preset threshold, the vehicle is not offline; if it is higher than the preset threshold, the vehicle is in an offline state.

2. The offline time detection method based on the desired vehicle speed according to claim 1, characterized in that, In step U2, the calculation of the expected vehicle speed at different times and locations using a multivariate vehicle expected speed algorithm includes: U21. Based on the vehicle's position data, acceleration data, and heading angle data, a multivariate probability density function G for the vehicle is established. ， X=[x t ,y t ,a t ,θ t ,t], ， Among them, (x t ,y t ) represents the vehicle's location data at time t, a t Let θ be the acceleration data of the vehicle at time t. t Let X be the vehicle's heading angle data at time t, λ be the vehicle's state data array, λ be the vehicle's mean state data array over time ∆t, and Σ be the vehicle's covariance matrix data. This provides the average vehicle position data over a time interval ∆t. This provides the average acceleration data of the vehicle over the time interval ∆t. This provides the mean heading angle data for the vehicle over a time interval ∆t. U22. Based on the multivariate probability density function G of the vehicle, establish the expected value function H of the vehicle speed at different times and locations. ， Where X is the vehicle's state data array, X ∆t This represents the change in the vehicle's state data array over time ∆t. U23. Based on the expected value function H of the vehicle speed at different times and locations, obtain the expected speed data information of the vehicle at different times and locations.

3. The offline time detection method based on the desired vehicle speed according to claim 2, characterized in that: The vehicle covariance matrix data Σ is, Σ=E[(X-λ)(X-λ) T ], Where X is the vehicle state data array, and λ is the vehicle state mean data array over time ∆t.

4. The offline time detection method based on the desired vehicle speed according to claim 2, characterized in that: The average vehicle position data within the time interval ∆t for, ， The average acceleration data of the vehicle within the time interval ∆t. for, ， The mean heading angle data of the vehicle within the time interval ∆t for, ， Among them, α i Let x be the position weight coefficient of the vehicle at different times. i ,y i Let be the vehicle's location data at time i, and a i Let θ be the acceleration data of the vehicle at time i. i Here is the heading angle data of the vehicle at time i, β i δ represents the weighting coefficient for the vehicle's acceleration at different times. i The weighting coefficients are the heading angles of the vehicle at different times.

5. The offline time detection method based on the desired vehicle speed according to claim 1, characterized in that, In step U3, the optimization of the expected velocity at the same location at different times using the swarm optimization algorithm includes: U31. Based on the expected speed data of the vehicle at different times and locations, the population of the cysts is initialized, the population parameters and boundary conditions are set, and the population data information of the initialized cysts is obtained. U32. Based on the population data information of the initialized sac-like structures, establish the fitness function M of the population. ， Among them, v t Let v be the expected speed of the vehicle at time t. (x,y) For the expected speed of vehicles at different locations, the fitness values ​​of individual cysts are obtained. U33. Based on the fitness value data of the individuals in the cyst population, establish the position update function L for the individuals in the cyst population. ， Where c is the adaptive weight value, which obtains the location update data information of the individual cysts; U34. Based on the location update data of the individual cysts, the cyst population is optimized to obtain the optimized expected velocity data of the same location.

6. The offline time detection method based on the desired vehicle speed according to claim 5, characterized in that: The position update function L(t) for the individual cysts, ， Where, M(t) max Let M(t) be the maximum fitness function of the population at time t. min Let t be the minimum fitness function of the population at time t, and c be the adaptive weight value.

7. The offline time detection method based on the desired vehicle speed according to claim 6, characterized in that: The adaptive weight value c is, ， Where ∆t is the time interval value of the vehicle at different times, and t is the vehicle's time.

8. The offline time detection method based on the desired vehicle speed according to claim 1, characterized in that, In step U4, the offline time detection function Q is constructed as follows: ， Among them, v 期 The optimized expected speed data for the same location is represented by v0, which is the vehicle's speed evaluation factor.

9. An offline time detection system based on desired vehicle speed, comprising computer equipment, characterized in that, The computer device is programmed or configured to perform the steps of the offline time detection method based on the desired vehicle speed as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is programmed or configured to perform the offline time detection method based on the desired vehicle speed as described in any one of claims 1 to 8.

Images