Path planning method and device, equipment and storage medium

Abstract

The invention provides a path planning method, and relates to the technical field of artificial intelligence, in particular to the technical fields of map navigation, automatic driving, intelligent traffic and the like. The method comprises the steps of calculating a health index of a mechanical state based on current data corresponding to the mechanical state of a target vehicle; determining a risk weight coefficient of the mechanical state based on the health index, and determining a risk index of the mechanical state according to the risk weight coefficient; and planning the path of the target vehicle according to the risk index to obtain a target navigation path. The method improves the safety of vehicle driving.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, specifically to technical fields such as map navigation, autonomous driving, and intelligent transportation, and particularly to a path planning method, apparatus, device, and storage medium. Background Art

[0002] Traditional vehicles generally perform vehicle risk assessment based on a method of judging by fixed thresholds, and the risk assessments of various mechanical states are independent of each other. For example, a risk warning is generated when the remaining thickness of the brake pads is less than 3 millimeters, or a risk warning is generated when the tire pressure is greater than 250 kpa (kilopascals). And the decision-making system of the vehicle is often a separate module, that is, when the vehicle makes a decision, it often cannot refer to the risk assessment results of other modules. Summary of the Invention

[0003] The present disclosure provides a path planning method, apparatus, device, and storage medium.

[0004] According to a first aspect of the present disclosure, there is provided a path planning method, including: calculating a health index of a mechanical state based on current data corresponding to the mechanical state of a target vehicle; determining a risk weight coefficient of the mechanical state based on the health index, and determining a risk index of the mechanical state according to the risk weight coefficient; planning a path of the target vehicle according to the risk index to obtain a target navigation path.

[0005] According to a second aspect of the present disclosure, there is provided a path planning apparatus, including: a health index calculation module configured to calculate a health index of a mechanical state based on current data corresponding to the mechanical state of a target vehicle; a risk index calculation module configured to determine a risk weight coefficient of the mechanical state based on the health index, and determine a risk index of the mechanical state according to the risk weight coefficient; a path planning module configured to plan a path of the target vehicle according to the risk index to obtain a target navigation path.

[0006] According to a third aspect of the present disclosure, there is provided an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in any implementation manner of the first aspect.

[0007] According to a fourth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the method described in any implementation manner of the first aspect.

[0008] According to a fifth aspect of the present disclosure, there is provided a computer program product, including a computer program which, when executed by a processor, implements the method described in any implementation manner of the first aspect.

[0009] According to a sixth aspect of the present disclosure, there is provided a vehicle, including: a sensor array, the sensor array including at least two of the following: a brake pad monitoring sensor, a tire pressure monitoring sensor, a suspension monitoring sensor, wherein the brake pad monitoring sensor is configured to collect current data of the brake pad state of the target vehicle, the tire pressure monitoring sensor is configured to collect current data of the tire pressure state of the target vehicle, and the suspension monitoring sensor is configured to collect current data of the suspension state of the target vehicle; and an electronic device as described in the third aspect.

[0010] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The drawings are used to better understand the solution and do not constitute a limitation to the present disclosure. Among them: Figure 1 is an exemplary system architecture diagram to which the present disclosure can be applied; Figure 2 is a flowchart of an embodiment of the path planning method according to the present disclosure; Figure 3 is a flowchart of another embodiment of the path planning method according to the present disclosure; Figure 4 is Figure 3 a flowchart of step 303 in Figure 5 is Figure 4 a flowchart of step 403 in Figure 6 is a schematic structural diagram of an embodiment of the path planning device according to the present disclosure; Figure 7 is a block diagram of an electronic device for implementing the path planning method of the embodiments of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0012] The following makes an explanation of the exemplary embodiments of the present disclosure in conjunction with the drawings. Various details of the embodiments of the present disclosure are included to help understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted below.

[0013] It should be noted that, without conflict, the embodiments in the present disclosure and the features in the embodiments may be combined with each other. The following will describe the present disclosure in detail with reference to the drawings and in combination with the embodiments.

[0014] Figure 1 Fig. 4 shows an exemplary system architecture 100 of an embodiment in which the path planning method or path planning device of the present disclosure can be applied.

[0015] As Figure 1 shown, the system architecture 100 may include terminal devices 101, 102, 103, 104, a network 105, and a server 106. The network 105 is used as a medium to provide a communication link between the terminal devices 101, 102, 103, 104 and the server 106. The network 105 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0016] Users can use the terminal devices 101, 102, 103, 104 to interact with the server 106 through the network 105 to receive or send information, etc. Various client applications may be installed on the terminal devices 101, 102, 103, 104.

[0017] The terminal devices 101, 102, 103, 104 may be hardware or software. When the terminal devices 101, 102, 103, 104 are hardware, they may be various electronic devices, including but not limited to smart phones, tablet computers, laptop portable computers, and desktop computers, etc. When the terminal devices 101, 102, 103, 104 are software, they may be installed in the above-mentioned electronic devices. They may be implemented as multiple software or software modules, or may be implemented as a single software or software module. No specific limitation is made here.

[0018] The server 106 may provide various services. For example, the server 106 may analyze and process the current data corresponding to the mechanical state of the target vehicle obtained from the terminal devices 101, 102, 103, 104, and generate a processing result (such as generating a target navigation path).

[0019] It should be noted that the server 106 may be hardware or software. When the server 106 is hardware, it may be implemented as a distributed server cluster composed of multiple servers, or may be implemented as a single server. When the server 106 is software, it may be implemented as multiple software or software modules (such as used to provide distributed services), or may be implemented as a single software or software module. No specific limitation is made here.

[0020] It should be noted that the path planning method provided by the embodiments of the present disclosure is generally executed by the server 106. Correspondingly, the path planning device is generally set in the server 106.

[0021] It should be understood that Figure 1 the number of terminal devices, networks, and servers in

[0022] Continuing to refer to Figure 2 , which shows a flow 200 of an embodiment of a path planning method according to the present disclosure. The path planning method includes the following steps: Step 201, calculating a health index of the mechanical state based on current data corresponding to the mechanical state of the target vehicle.

[0023] In this embodiment, the execution subject of the path planning method (such as Figure 1 the server 106 shown) will first collect the current data corresponding to the mechanical state of the target vehicle. Here, the target vehicle is the vehicle itself. The vehicle mechanical state refers to the working state and performance of each mechanical component of the vehicle, including key components such as the engine, transmission, braking system, and tires. Regularly checking and maintaining the mechanical state of the vehicle is crucial for ensuring driving safety and extending the service life of the vehicle. Since the path planning method of this embodiment aims to comprehensively refer to the risk assessment results of multiple modules when performing path planning, therefore, there are two or more mechanical states in this embodiment. Since the brake pad state, tire (tire pressure) state, and suspension state are all main indicators of vehicle detection, therefore, the above mechanical states may include at least two of the brake pad state, tire (tire pressure) state, and suspension state. Among them, the brake pad state is used to characterize the wear condition of the vehicle's brake pads, the tire pressure state is used to characterize the wear condition of the vehicle's tires, and the suspension state is used to characterize the vibration condition of the vehicle's suspension system. The suspension system refers to the general term for all force transmission connection devices between the vehicle's frame and the axle or wheels.

[0024] A sensor array can be pre-set on the target vehicle. The sensor array includes a brake pad monitoring sensor, a tire monitoring sensor, and / or a suspension monitoring sensor. The brake pad monitoring sensor is generally a laser displacement sensor, which is generally arranged on both sides of the brake caliper to form triangulation. The sampling frequency of this sensor is generally 100 Hz (Hertz), and the sampling accuracy is generally 5 mm (millimeters). The brake pad detection sensor can obtain the thickness data of the brake pads in real time (the unit is millimeters).

[0025] The tire monitoring sensor is generally a hub-integrated sensor, which can detect the tire pressure (kPa) of the vehicle, the temperature (°C) of the vehicle's tires, the tread thickness (mm), etc. in real time.

[0026] The suspension monitoring sensor generally uses a distributed fiber optic grating sensor, and generally 5 groups are linearly arranged along the shock absorber piston rod of the vehicle, with a spacing of generally 50 mm, so as to realize full-stroke stress monitoring, and the suspension monitoring sensor will obtain the suspension strain data of the vehicle in real time.

[0027] After obtaining the current data of the mechanical state of the target vehicle, the above-mentioned execution entity will calculate the health index of the mechanical state according to the current data and historical data. Specifically, the above-mentioned execution entity will obtain the historical monitoring data of the mechanical state in the past ten days, then determine the historical maximum value and historical minimum value from the historical monitoring data, and then calculate the health index of the mechanical state according to the current data, historical maximum value and historical minimum value. For example, the difference between the current data and the historical minimum value can be calculated first, denoted as the first difference, and then the difference between the historical maximum value and the historical minimum value can be calculated, denoted as the second difference, and then the ratio of the first difference to the second difference is used as the health index of the mechanical state. When there are multiple mechanical states, the health index of each mechanical state can be calculated separately according to the above method.

[0028] As an example, assume that the mechanical state is the brake pad state, the current thickness of the brake pad is 5.2 mm, its corresponding historical minimum value is 3.0 mm, and the historical maximum value is 10 mm, then the brake pad health index can be calculated as follows: =(5.2 3.0) / (10.0 3.0)=0.314.

[0029] As an example, assume that the mechanical state is the tire pressure state, the current value of the tire pressure is 220 kPa, its corresponding historical minimum value is 180 kPa, and the historical maximum value is 260 kPa, then the tire pressure health index can be calculated as follows: =(220 180) / (260 180)=0.5.

[0030] As an example, assume that the mechanical state is the suspension state, the current value of the suspension state is 750 με (the unit symbol of microstrain), its corresponding historical minimum value is 500 με, and the historical maximum value is 1200 με, then the suspension health index can be calculated as follows: =(750 - 500) / (1200 - 500)=0.357.

[0031] It can be seen that the closer the health index of the mechanical state is to 1, the better the condition of the subsystem corresponding to the mechanical state, and the closer it is to 0, the worse the condition. For example, when the brake pad health index is 1, it means that the current brake pad state parameter is equal to the historical best state value (i.e., the historical minimum value), that is, the brake pad is hardly worn and is in a brand-new state.

[0032] Step 202: Determine the risk weight coefficient of the mechanical state based on the health index, and determine the risk index of the mechanical state according to the risk weight coefficient.

[0033] In this embodiment, the above-mentioned execution entity will determine the risk weight coefficient of the mechanical state according to the calculated health index, and then determine the risk index of the mechanical state according to the risk weight coefficient. For example, the above-mentioned execution entity can use the particle swarm optimization algorithm and the health index to determine the risk weight coefficient of the mechanical state.

[0034] It should be noted that the particle swarm optimization algorithm (PSO), also known as the particle swarm algorithm, is a global optimization algorithm that simulates the foraging behavior of bird flocks in nature and belongs to a kind of swarm intelligence algorithm. Taking the foraging of a bird flock as an example, in the particle swarm optimization algorithm, each little bird in the bird flock is called a "particle", and like a little bird, it has speed and position. By randomly generating a certain number of particles as effective solutions in the problem search space, and then performing iterative search, the fitness value of the particle is determined through the fitness function corresponding to the problem to obtain the optimization result. Specifically, the above-mentioned execution entity will initialize multiple groups of risk weight coefficients, generate a weight vector corresponding to each group of risk weight coefficients, and use each group of weight vectors as a particle. Initializing the particle is to assign values to the speed and position of the particle, and set the historical best pBest of the individual to the current position, and the best individual in the group is the global best gBest. Then in each generation of evolution, calculate the fitness function value of each particle. If the current fitness function value is better than the historical best value, then update pBest; if the current fitness function value is better than the global historical best value, then update gBest. Update the speed and position of the d-th dimension of each particle i according to the preset update formula respectively. Repeat the above iterative process until the fitness value meets the preset requirements. At this time, determine the risk weight coefficient according to the weight vector corresponding to the fitness value that meets the preset requirements.

[0035] After determining the risk weight coefficient of the mechanical state, the above-mentioned execution entity can calculate the risk index of the mechanical state according to the risk weight coefficient and the health index. The risk index can also be called the hazard index. For example, the difference between 1 and the health index can be multiplied by the risk weight coefficient, and the obtained value can be used as the risk index.

[0036] As an example, assume the health index of the brake pad = 0.4, and the risk weight coefficient corresponding to the brake pad is 0.5. Then the risk index of the brake pad can be calculated = 0.5 (1 - 0.4) = 0.3.

[0037] Step 203: Plan the path of the target vehicle according to the risk index to obtain the target navigation path.

[0038] In this embodiment, the above-mentioned execution entity will plan the path of the target vehicle according to the calculated risk index, so as to obtain the target navigation path of the target vehicle. That is, the above-mentioned execution entity will determine the risk level according to the relationship between the value of the risk index of the mechanical state and the preset threshold, and then perform corresponding route planning.

[0039] For example, for the brake pad state, if its risk index is less than 30%, it is determined to be a low risk. At this time, no avoidance or prompt is made during path planning; if the risk index is in (30%, 70%), it is determined to be a medium risk. At this time, during route planning, sections with a downhill length exceeding 100 meters will be avoided, that is, from all optional routes, sections with a downhill length exceeding 100 meters will be avoided, so as to obtain the target navigation path, and the following distance reported will be extended to 2.45 meters, and it will also be recommended to reduce the vehicle speed to 56 km / h. If the risk index is greater than 70%, it is determined to be a high risk. At this time, during route planning, sections with a slope greater than 3° will be automatically avoided from all optional routes, so as to obtain the target navigation path, and the brake assist system will be turned on, and the maximum vehicle speed limit is 60 km / h. Thus, the risk brought by the brake pad state is avoided by reducing the situation of sudden braking.

[0040] Another example, for the tire pressure state, if its risk index is less than 30%, it is determined to be a low risk. At this time, no avoidance or prompt is made during path planning; if the risk index is in (30%, 70%), it is determined to be a medium risk. At this time, during route planning, sections with a bend turning radius greater than 100 meters will be avoided from all optional routes, so as to obtain the target navigation path, and the vehicle speed will be automatically reduced to 80 km / h, and it will also be voice-reported to check the tire pressure. If the risk index is greater than 70%, it is determined to be a high risk. At this time, during route planning, it will be strongly prompted that the risk of driving in rainy days is high, and the user will be prompted to turn on the anti-skid mode and replace the tires immediately. Thus, the risk brought by the tire pressure state is avoided by reducing the situation of sharp turns.

[0041] For another example, for the suspension state, if its risk index is less than 30%, it is determined to be a low risk. At this time, during path planning, no avoidance or prompt is made. If the risk index is in the range of (30%, 70%), it is determined to be a medium risk. At this time, during the route planning process, flat road sections will be preferentially selected (if not available, slightly bumpy road sections can be selected). If the risk index is greater than 70%, it is determined to be a high risk. At this time, during the route planning process, non-flat road sections are avoided from all candidate driving routes (non-flat road sections are not selected at all), so as to obtain the target navigation route, and a voice broadcast is used to prompt the user to immediately check the suspension system. Thus, the risk brought by the suspension state is avoided by reducing the bumpy situation.

[0042] It should be noted that multiple target navigation paths can be obtained through path planning. At this time, the user can select the final navigation path by himself / herself.

[0043] The path planning method provided by the embodiments of the present disclosure first calculates the health index of the mechanical state based on the current data corresponding to the mechanical state of the target vehicle; then determines the risk weight coefficient of the mechanical state based on the health index, and determines the risk index of the mechanical state according to the risk weight coefficient; finally, plans the path of the target vehicle according to the risk index to obtain the target navigation path. In the path planning method of this embodiment, by monitoring the mechanical state of the vehicle in real time, the health index and risk index of the mechanical state are calculated in real time, realizing the real-time prediction of the mechanical loss of the vehicle, and then comprehensively considering the real-time performance of the vehicle and the road attributes to perform route planning, improving the safety of vehicle driving.

[0044] In addition, in the technical solutions involved in the present disclosure, the acquisition, storage, use, processing, transportation, provision, and disclosure of the user's personal information (such as the current data and historical data corresponding to the mechanical state of the target vehicle involved in the present disclosure) and other processes all comply with the regulations of relevant laws and regulations and do not violate public order and good customs.

[0045] Continue to refer to Figure 3 , Figure 3 shows the flow 300 of another embodiment of the path planning method according to the present disclosure. The path planning method includes the following steps: Step 301, determine the historical maximum data and historical minimum data from the historical data corresponding to the mechanical state.

[0046] In this embodiment, the execution subject of the path planning method (such as Figure 1The server 106) shown will first obtain the historical data corresponding to the mechanical state. For example, the monitoring data of the mechanical state in the past ten days can be used as the historical data, and then the historical maximum value (i.e., the maximum value in the historical data) and the historical minimum value (i.e., the minimum value in the historical data) are determined from the historical data. Specifically, let i represent the mechanical state, and the current data, historical maximum value data, and historical minimum value data of the mechanical state can be respectively represented as and .

[0047] Step 302: Calculate the health index of the mechanical state according to the current data, historical maximum value data, and historical minimum value data.

[0048] In this embodiment, the above-mentioned execution entity will calculate the health index of the mechanical state according to the current data, historical maximum value data, and historical minimum value data , and specifically, it can be calculated through formula (1): = , = 1, 2, 3…N; (1) Wherein, The value range of is (0, 1).

[0049] As an example, assume that the mechanical state is the brake pad state, which is represented by i = 1, and the current thickness of the brake pad = 5.2 mm, its corresponding historical minimum value = 3.0 mm, and the historical maximum value is = 10 mm, then the brake pad health index can be calculated as follows: =(5.2 3.0) / (10.0 3.0)= 0.314.

[0050] Thus, the collected parameters are normalized through the current data, historical maximum value data, and historical minimum value data of the mechanical state, and the health index of the mechanical state is obtained. Since the current data and historical data are combined when calculating the health index, the accuracy of the Jiangkang index is improved.

[0051] In some alternative implementation manners of this embodiment, the above path planning method further includes: performing time synchronization on the acquisition timestamp of the current data to obtain the first data; converting the first data to the vehicle coordinate system to obtain the second data; performing outlier processing on the second data to obtain the processed data; and step 302 further includes: calculating the health index of the mechanical state according to the processed data, historical maximum value data, and historical minimum value data.

[0052] In this implementation, since there are generally two or more mechanical states, and each mechanical state corresponds to a current data, the current data of different mechanical states are generally collected by different sensors. Therefore, the above-mentioned execution entity will synchronize the collection timestamps of the current data to obtain the first data. Specifically, the timestamps of multi-sensor data can be aligned based on the GPS (Global Positioning System) timing signal to ensure that the time error of different sensors is <1ms, thereby obtaining the synchronized sensor data, that is, the first data.

[0053] Then, the above-mentioned execution entity will transform the synchronized sensor data into the vehicle coordinate system to obtain the second data. The synchronized sensor data of each sensor can be unified into the body coordinate system (the origin is at the centroid, and the X-axis is the vehicle forward direction) through the vehicle coordinate system transformation matrix, thereby obtaining the spatially calibrated sensor data, that is, the second data.

[0054] After that, the above-mentioned execution entity will also perform outlier detection on the spatially calibrated sensor data. The Hampel filtering algorithm can be used to remove the burst noise in the spatially calibrated sensor data and only retain the effective features, and then obtain the denoised mechanical state data, that is, the processed data.

[0055] Furthermore, the above-mentioned execution entity will calculate the health index of the mechanical state according to the processed data, historical maximum data, and historical minimum data. That is, first perform time synchronization, spatial calibration, and outlier detection processing on the current data of multiple mechanical states, and calculate the health index of the mechanical state according to the processed data, thereby further improving the accuracy and effectiveness of the health index result.

[0056] Step 303, determine the risk weight coefficient of the mechanical state based on the particle swarm optimization algorithm and the health index.

[0057] In this embodiment, the above-mentioned execution entity will use the particle swarm optimization algorithm and the health index to determine the risk weight coefficient of the mechanical state. The particle swarm optimization algorithm, also known as the particle swarm algorithm, is a global optimization algorithm that simulates the foraging behavior of bird flocks in nature and belongs to a kind of swarm intelligence algorithm. Specifically, the above-mentioned execution entity will initialize multiple groups of risk weight coefficients, generate a weight vector corresponding to each group of risk weight coefficients, and regard each group of weight vectors as a particle. Initializing a particle means assigning values to the speed and position of the particle, setting the historical best pBest of the individual to the current position, and the best individual in the group is the global best gBest. Then, in each generation of evolution, calculate the fitness function value of each particle. If the current fitness function value is better than the historical best value, update pBest; if the current fitness function value is better than the global historical best value, update gBest. Update the speed and position of the d-th dimension of each particle i according to the preset update formula respectively. Repeat the above iterative process until the fitness value meets the preset requirements. At this time, determine the risk weight coefficient according to the weight vector corresponding to the fitness value that meets the preset requirements. Let represent the risk weight coefficient corresponding to the mechanical state i.

[0058] Step 304, calculate the risk index of the mechanical state according to the risk weight coefficient and the health index.

[0059] In this embodiment, the above-mentioned execution entity will calculate the risk index of the mechanical state according to the risk weight coefficient and the health index , which can be specifically calculated by the following formula (2) : ; (2) As an example, for the brake pad state, determine its risk weight coefficient =0.5, and its health index =0.4. Then, the risk index corresponding to the brake pad state can be calculated 0.5 (1 - 0.4)=0.3, that is, 30%. For the tire pressure state, determine its risk weight coefficient =0.5, and its health index =0.2. Then, the risk index corresponding to the tire pressure state can be calculated 0.5 (1 - 0.2)=0.4, that is, 40%.

[0060] Determine the risk weight coefficient of the mechanical state through the particle swarm optimization algorithm, so as to determine the optimal combination of risk weight coefficients. Then, calculate the risk index of the mechanical state according to the determined risk weight coefficient and the health index, so that the generated risk index is more targeted, and further makes the result of the safety assessment based on the risk index more accurate.

[0061] Step 305: Plan the path of the target vehicle according to the risk index to obtain the target navigation path.

[0062] Step 305 is basically the same as step 203 of the foregoing embodiment. The specific implementation manner can refer to the description of step 203 above and will not be elaborated here.

[0063] From Figure 3 it can be seen that, compared with the corresponding embodiment of Figure 2 , in the path planning method of this embodiment, the steps of calculating the health index and risk index of the mechanical state are emphasized, so as to determine the risk weight coefficient of the mechanical state through the particle swarm optimization algorithm, determine the combination of the optimal risk weight coefficients, and then calculate the risk index of the mechanical state according to the determined risk weight coefficient and health index, so that the generated risk index is more targeted, and further the result of the safety assessment based on the risk index is more accurate.

[0064] Continue to refer to Figure 4 , Figure 4 shows a process 400 of step 303 in Figure 3 . This step includes: Step 401: Initialize the initial weight coefficients corresponding to multiple groups of mechanical states, and generate the corresponding weight vectors according to the initial weight coefficients.

[0065] In this embodiment, the above execution entity will first initialize the initial weight coefficients corresponding to multiple groups of mechanical states, and generate the corresponding weight vectors according to the initial weight coefficients. Among them, each group of initial weight coefficients satisfies the preset constraint conditions. Here, assuming that the mechanical states are the brake pad state, the tire pressure state, and the suspension state respectively, correspondingly, the risk weight coefficients of these three mechanical states are expressed as , , , then the weight vector corresponding to each group of weight coefficients can be expressed as ( , , ). That is, the above execution entity first randomly generates multiple particles, and each particle represents a group of weight vectors. For example, 20 groups of weight vectors ( , , ) can be randomly generated in the initial stage as the initial particle swarm. Although each group of weight vectors is randomly generated, each group of weight vectors must satisfy the constraint conditions: and 0 ≤ ≤ 1.

[0066] For example, three numbers a, b, and c within the range of [0, 1] can be randomly generated first, and then the weights that meet the conditions can be obtained through normalization processing: = a / (a + b + c), = b / (a + b + c), = c / (a + b + c).

[0067] At the same time, for each dimension of each particle (i.e., , , corresponding dimensions: brake pads, tire pressure, suspension), a velocity value is initialized, where i represents the particle number and d represents the dimension index.

[0068] Specifically, each particle corresponds to a risk assessment strategy, and the sum of the three weight coefficients included in each particle is equal to 1, that is, + + = 1.

[0069] For example: The initialized particle 1 is: = 0.4, = 0.3, = 0.3; Particle 2 is: = 0.2, = 0.5, = 0.3… Thus, through the group collaboration of the initialized 20 particles, the optimal weight combination is searched for.

[0070] Specifically, when the dimension number d = 1, the corresponding weight is , and its physical meaning is: the risk weight coefficient of the brake pads, which needs to meet the constraint condition: 0 ≤ ≤ 1. When the dimension number d = 2, the corresponding weight is , and its physical meaning is: the risk weight coefficient of the tire pressure, which needs to meet the constraint condition: 0 ≤ ≤ 1. When the dimension number d = 3, the corresponding weight is , and its physical meaning is: the risk weight coefficient of the suspension, which needs to meet the constraint condition: 0 ≤ ≤ 1. The sum constraint is: + + = 1.

[0071] In addition, the initial iteration number k = 0, and the velocity value can be randomly generated within a relatively small interval, such as [-1, 1].

[0072] Step 402: Calculate the fitness value corresponding to the weight vector according to the weight vector and the health index.

[0073] In this embodiment, the above-mentioned execution entity calculates the initial risk values of all mechanical states according to formula (3), that is, adding up the risk indices of each mechanical state: ; (3) Then, the fitness is calculated according to formula (4). Here, the fitness function is to minimize the mean square error (MSE) of the historical accident rate and the predicted risk. Assume that the historical accident rate is , and the predicted risk calculated according to the current weight vector is (that is ), then the fitness f can be calculated according to formula (4): f = MSE( , ) = (4) where N is the number of samples, and j is the summation index variable, representing the jth sample, j = 1, 2, 3... N.

[0074] It can be seen from formula (4) that the smaller the fitness f value, the closer the predicted risk under this set of weight vectors is to the historical accident rate, which means that this set of weights is more accurate in risk assessment.

[0075] Step 403: Use the particle swarm optimization algorithm to iteratively update multiple groups of weight vectors, determine the target weight vector according to the update result, and determine the risk weight coefficient of the mechanical state according to the target weight vector.

[0076] In this embodiment, the above-mentioned execution entity uses the particle swarm optimization algorithm to iteratively update multiple groups of weight vectors, so as to determine the target weight vector according to the update result. The above-mentioned execution entity first sets the historical best pBest of the individual to the current position, and the best individual in the group is the global best gBest. Then, in each round of iteration, calculate the fitness function value of each particle. If the current fitness function value is better than the historical best value, update pBest; if the current fitness function value is better than the global historical best value, update gBest. Update the velocity and position of the dth dimension of each particle i according to the preset update formula respectively. Repeat the above iterative process until the fitness value meets the preset requirements. At this time, according to the weight vector corresponding to the fitness value that meets the preset requirements ( , , ) determine the risk weight coefficient , , .

[0077] From Figure 4It can be seen that through the particle swarm optimization algorithm, the optimal combination of risk weight coefficients for multiple mechanical states can be determined quickly and accurately, and the risk weight coefficients corresponding to multiple mechanical states are evaluated through multi-system collaboration, rather than determined in isolation, thereby improving the accuracy of the risk weight vector (i.e., the combination of risk weight coefficients), and further making the results of safety assessment based on the risk index more accurate.

[0078] Continue to refer to Figure 5 , Figure 5 shows Figure 4 a process 500 of step 403 in Step 501, for each particle, compare the current fitness value of the particle with the fitness value at the optimal position the particle has experienced, and determine the individual optimal position of the particle according to the comparison result.

[0079] In this embodiment, for each particle, the above-mentioned execution entity will compare the current fitness value of the particle with the fitness value at the optimal position the particle has experienced, and determine the individual optimal position of the particle according to the comparison result. Among them, the particle is a set of weight vectors in multiple groups of weight vectors. That is, the above-mentioned execution entity will first determine the historical optimal position of the individual (particle) , and compare the fitness value of the current position with the fitness value at , and determine whether to update based on the comparison result. Since it can be seen from formula (4) that the smaller the fitness f value, the closer the predicted risk under this set of weight vectors is to the historical accident rate, which also means that this set of weights is more accurate in risk assessment. Therefore, if 's fitness value is less than 's fitness value, then update to .

[0080] is the optimal position the i-th particle has experienced in the d-th dimension at the k-th iteration. In the particle swarm optimization algorithm, each particle has its own "memory", which will record the position that minimizes the fitness function value during its search process. Guiding the particle to move in the search space towards the optimal solution it has found before helps the particle to perform local search.

[0081] is the current position of the i-th particle in the d-th dimension at the k-th iteration. It corresponds to a certain weight value in a set of weight vectors ( , , ). For example, when d = 1, It is the weight of the braking subsystem in the weight vector represented by the i-th particle. As the algorithm iterates, the positions of the particles will be continuously updated and gradually move to new positions through the velocity update formula and the position update formula.

[0082] Step 502: Compare the current fitness value of the particle with the fitness values at the optimal positions experienced by all particles, and determine the global optimal position of all particles according to the comparison results.

[0083] In this embodiment, the above-mentioned execution entity compares the current fitness value of the particle with the fitness values at the optimal positions experienced by all particles, and determines the global optimal position according to the comparison results. 。

[0084] The global optimal position is the global optimal position found by all particles in the d-th dimension at the k-th iteration. For example: is the optimal value of the tire pressure subsystem weight dimension; is the optimal value of the suspension weight dimension. Assume that the weight value with the minimum fitness function is found in 10 iterations as = 0.4. Then, in the subsequent speed updates, each particle will refer to this value to adjust its speed and position in the tire pressure subsystem weight dimension and try to approach this optimal value.

[0085] Step 503: Update the speed and position of the particle according to the speed and position of the particle, the individual optimal position, and the global optimal position.

[0086] In this embodiment, the above-mentioned execution entity will update the speed and position of the particle according to the speed and position of the particle and the individual optimal position and global optimal position determined in the above steps. Specifically, the speed can be updated based on the speed update formula (5), and the position can be updated according to the position update formula (6): = ω + ( - )+ ( - ); (5) = + ; (6) where ω is the inertia weight, generally taking a value of 0.8, which is used to control the influence degree of the previous speed of the particle on the current speed. and is the acceleration coefficient, generally taking a value of 1.496, which respectively adjusts the step lengths of the particle flying towards its own historical optimal position and the global optimal position. and is a random number between 0 and 1, used to increase the randomness of the search.

[0087] is the velocity, which is the velocity of the i-th particle in the d-th dimension at the k-th iteration. The velocity determines the direction and step length of the particle moving in the search space. It is a dynamically changing value and will be adjusted according to the velocity update formula in each iteration. The positive or negative sign of the velocity indicates the direction of the particle moving in this dimension, and the absolute value indicates the step length.

[0088] Suppose there is a particle swarm containing 20 particles, used to optimize the risk weights of three subsystems: brakes, tires, and suspensions. Now focus on the 5th particle i = 5, at the 10th iteration k = 10. In the dimension of the brake subsystem's weight d = 1, finally, it can be calculated that: = 0.05; = 0.4; = 0.3; = 0.45; Then, based on these above values, the 11th velocity update iteration calculation can be carried out ( and randomly 0.6 and 0.7): = 0.8 + 1.496 0.6 ( - ) + 1.496 0.7 ( - ); = 0.8 0.05 + 1.496 0.6 (0.4 - 0.3) + 1.496 0.7 (0.45 - 0.3); It can be obtained that = 0.28684.

[0089] Substitute the value into formula (6), and the position update can be calculated as: = 0.3 + 0.28684 = 0.58684.

[0090] Similarly, following the above idea, successively calculate the when d = 2 and and, when d = 3 .

[0091] Step 504: Calculate the new fitness value of the particle according to the updated speed and position until the new fitness value meets the preset requirements, and use the weight vector corresponding to the fitness value that meets the preset requirements as the target weight vector.

[0092] In this embodiment, the above execution entity calculates the new fitness value of the particle according to the updated speed and position until the new fitness value meets the preset requirements, and uses the weight vector corresponding to the fitness value that meets the preset requirements as the target weight vector.

[0093] After calculating the updated speed and position through the foregoing steps, the preliminary , , can be calculated. Since the sum of the three is equal to 1, normalization processing is required to obtain the weights that meet the conditions: = / ( + ), = / ( + ), = / ( + ). Finally, the optimized weight coefficients , , can be obtained. Table 1 shows the various values in the process of calculating the target weight coefficient: Table 1 Various values corresponding to the calculation process of the target weight coefficient

[0094] That is, the finally determined risk weight coefficient = 0.489, = 0.339, = 0.272.

[0095] It can be seen from Figure 5 that through the particle swarm optimization algorithm, the optimal combination of risk weight coefficients for multiple mechanical states can be determined quickly and accurately, and the risk weight coefficients corresponding to multiple mechanical states are evaluated through multi-system collaboration, rather than determined in isolation, thereby improving the accuracy of the risk weight vector (i.e., the combination of risk weight coefficients), and further making the results of safety assessment based on the risk index more accurate.

[0096] In some alternative implementation manners of this embodiment, when the mechanical state includes the brake pad state, planning the path of the target vehicle according to the risk index includes: In response to determining that the risk index corresponding to the brake pad state is greater than or equal to the first brake risk threshold, during path planning, avoid sections with a slope greater than the preset slope value.

[0097] In this implementation manner, after determining the risk weight coefficient of the brake pad state the above-mentioned execution entity can calculate the risk index of the brake pad state according to the foregoing formula (2) . And further compare the calculated with the preset threshold, so as to perform route planning according to the judgment result.

[0098] Specifically, if is greater than or equal to the first brake risk threshold (for example, 70%), it is determined as a high risk. At this time, during route planning, automatically avoid sections with a slope greater than 3° from all optional routes, so as to obtain the target navigation path, and turn on the brake assist system, with the maximum speed limited to 60 km / h.

[0099] In response to determining that the risk index corresponding to the brake pad state is greater than or equal to the second brake risk threshold and less than the first brake risk threshold, during path planning, avoid downhill sections with a length greater than the preset length value.

[0100] If is greater than or equal to the second brake risk threshold (for example, 30%) and less than the first brake risk threshold (for example, 70%), it is determined as a medium risk. At this time, during route planning, avoid downhill sections with a length exceeding 100 meters, that is, avoid downhill sections with a length exceeding 100 meters from all optional routes, so as to obtain the target navigation path, and the reported following distance will be extended to 2.45 meters, and it will also be recommended to reduce the speed to 56 km / h.

[0101] In addition, if is less than the second brake risk threshold (for example, 30%), it is determined as a low risk. At this time, during route planning, no route avoidance or prompt is made, that is, the route of the target vehicle is planned normally.

[0102] Therefore, when planning the driving path of the target vehicle, corresponding avoidance and risk prompts are made according to different risk indexes of the brake pads, and the risk brought by the brake pad state is avoided by reducing the situation of sudden braking, so as to generate a safer and more comfortable target navigation path for the user, thereby ensuring driving safety and comfort and improving the user experience.

[0103] In some alternative implementation manners of this embodiment, when the mechanical state includes the tire pressure state, planning the path of the target vehicle according to the risk index includes: In response to determining that the risk index corresponding to the tire pressure state is greater than or equal to the first tire pressure risk threshold, output a risk prompt message.

[0104] After determining the risk weight coefficient of the tire pressure state the above-mentioned execution entity may calculate the risk index of the tire pressure state according to the foregoing formula (2) . And further compare the calculated with a preset threshold, so as to perform route planning according to the judgment result.

[0105] Specifically, if is greater than or equal to the first tire pressure risk threshold (for example, 70%), it is determined as a high risk. At this time, during the route planning process, it will strongly prompt that the risk of driving in rainy days is high, and prompt the user to turn on the anti-skid mode and immediately replace the tires.

[0106] In response to determining that the risk index corresponding to the tire pressure state is greater than or equal to the second tire pressure risk threshold and less than the first tire pressure risk threshold, during the path planning process, avoid sections with a turning radius greater than a preset radius value.

[0107] If is greater than or equal to the second tire pressure risk threshold (for example, 30%) and less than the first tire pressure risk threshold (for example, 70%), it is determined as a medium risk. At this time, during the route planning process, from all optional routes, sections with a turning radius of more than 100 meters for the bend will be avoided, so as to obtain the target navigation path, and the vehicle speed will be automatically reduced to 80 km / h, and a voice broadcast will prompt to check the tire pressure.

[0108] In addition, if is less than the second tire pressure risk threshold (for example, 30%), it is determined as a low risk. At this time, during the route planning process, no route avoidance and prompt will be made, that is, the route planning of the target vehicle will be carried out normally.

[0109] Therefore, when planning the driving path of the target vehicle, corresponding avoidance and risk prompts are made according to different risk indexes of the tires. By reducing the situation of sharp turns, the risks brought by the tire pressure state are avoided, so as to generate a safer and more comfortable target navigation path for the user, thus ensuring driving safety and comfort and improving the user experience.

[0110] In some alternative implementation manners of this embodiment, when the mechanical state includes the suspension state, planning the path of the target vehicle according to the risk index includes: In response to determining that the risk index corresponding to the suspension state is greater than or equal to the first suspension risk threshold, during the path planning process, avoid non-flat road sections.

[0111] After determining the risk weight coefficient of the suspension state the above-mentioned execution entity can calculate the risk index of the suspension state according to the foregoing formula (2) . And further compare the calculated with a preset threshold, so as to perform route planning according to the judgment result.

[0112] Specifically, if is greater than or equal to the first suspension risk threshold (for example, 70%), it is determined as a high risk. At this time, during the route planning process, avoid non-flat road sections from all candidate driving routes, that is, do not select non-flat road sections at all, so as to obtain the target navigation route, and voice broadcast to prompt the user to immediately check the suspension system.

[0113] In response to determining that the risk index corresponding to the suspension state is greater than or equal to the second suspension risk threshold and less than the first suspension risk threshold, during the path planning process, select flat road sections, where the second suspension risk threshold is less than the first suspension risk threshold.

[0114] If is greater than or equal to the second suspension risk threshold (for example, 30%) and less than the first suspension risk threshold (for example, 70%), it is determined as a medium risk. At this time, during the route planning process, flat road sections will be preferentially selected. If there are none, slightly bumpy road sections can be selected.

[0115] In addition, if is less than the second suspension risk threshold (for example, 30%), it is determined as a low risk. At this time, during the route planning process, no route avoidance and prompt are made, that is, the route planning of the target vehicle is carried out normally.

[0116] Therefore, when planning the driving path of the target vehicle, corresponding avoidance and risk prompts are made according to different risk indexes of the suspension system, and the risk brought by the suspension state is avoided by reducing the bumpy situation, so as to generate a safer and more comfortable target navigation path for the user, thus ensuring the driving safety and comfort and improving the user experience.

[0117] Further referring to Figure 6 , as an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a path planning device. This device embodiment corresponds to Figure 2 the method embodiment shown, and this device can be specifically applied to various electronic devices.

[0118] For example Figure 6As shown in the figure, the path planning device 600 of this embodiment includes: a health index calculation module 601, a risk index calculation module 602, and a path planning module 603. Among them, the health index calculation module 601 is configured to calculate the health index of the mechanical state based on the current data corresponding to the mechanical state of the target vehicle; the risk index calculation module 602 is configured to determine the risk weight coefficient of the mechanical state based on the health index, and determine the risk index of the mechanical state according to the risk weight coefficient; the path planning module 603 is configured to plan the path of the target vehicle according to the risk index to obtain the target navigation path.

[0119] In this embodiment, in the path planning device 600: the specific processing of the health index calculation module 601, the risk index calculation module 602, and the path planning module 603 and the technical effects brought by them can be respectively referred to Figure 2 the relevant descriptions of steps 201-203 in the corresponding embodiments, which will not be elaborated here.

[0120] In some optional implementation manners of this embodiment, the health index calculation module 601 includes: an extreme value determination sub-module, configured to determine the historical maximum value data and the historical minimum value data from the historical data corresponding to the mechanical state; a calculation sub-module, configured to calculate the health index of the mechanical state according to the current data, the historical maximum value data, and the historical minimum value data.

[0121] In some optional implementation manners of this embodiment, the above path planning device 600 further includes: a time synchronization module, configured to perform time synchronization on the acquisition timestamp of the current data to obtain the first data; a coordinate conversion module, configured to convert the first data into the vehicle coordinate system to obtain the second data; an anomaly processing module, configured to perform anomaly value processing on the second data to obtain the processed data; and the calculation sub-module is further configured to: calculate the health index of the mechanical state according to the processed data, the historical maximum value data, and the historical minimum value data.

[0122] In some optional implementation manners of this embodiment, the risk index calculation module 602 includes: a coefficient determination sub-module, configured to determine the risk weight coefficient of the mechanical state based on the particle swarm optimization algorithm and the health index; an index determination sub-module, configured to calculate the risk index of the mechanical state according to the risk weight coefficient and the health index.

[0123] In some alternative implementation manners of this embodiment, the coefficient determination sub-module includes: an initialization unit configured to initialize the initial weight coefficients corresponding to multiple groups of mechanical states, and generate corresponding weight vectors according to the initial weight coefficients, where each group of initial weight coefficients satisfies a preset constraint condition; a calculation unit configured to calculate the fitness value corresponding to the weight vector according to the weight vector and the health index; an update unit configured to iteratively update multiple groups of weight vectors by using a particle swarm optimization algorithm, determine a target weight vector according to the update result, and determine the risk weight coefficient of the mechanical state according to the target weight vector, where the target weight vector is a weight vector whose fitness value satisfies a preset condition.

[0124] In some alternative implementation manners of this embodiment, the update unit is further configured to: for each particle, compare the current fitness value of the particle with the fitness value at the optimal position experienced by the particle, and determine the individual optimal position of the particle according to the comparison result, where the particle is a group of weight vectors in multiple groups of weight vectors; compare the current fitness value of the particle with the fitness values at the optimal positions experienced by all particles, and determine the global optimal position of all particles according to the comparison result; update the speed and position of the particle according to the speed and position of the particle, the individual optimal position, and the global optimal position; calculate the new fitness value of the particle according to the updated speed and position until the new fitness value meets the preset requirements, and use the weight vector corresponding to the fitness value that meets the preset requirements as the target weight vector.

[0125] In some alternative implementation manners of this embodiment, the mechanical state includes the brake pad state; and the path planning module 603 is further configured to: in response to determining that the risk index corresponding to the brake pad state is greater than the first brake risk threshold, avoid sections with a slope greater than a preset slope value during the path planning process; in response to determining that the risk index corresponding to the brake pad state is greater than or equal to the second brake risk threshold and less than the first brake risk threshold, avoid downhill sections with a length greater than a preset length value during the path planning process, where the second brake risk threshold is less than the first brake risk threshold.

[0126] In some alternative implementation manners of this embodiment, the mechanical state includes the tire pressure state; and the path planning module 603 is further configured to: in response to determining that the risk index corresponding to the tire pressure state is greater than the first tire pressure risk threshold, output a risk prompt message; in response to determining that the risk index corresponding to the tire pressure state is greater than or equal to the second tire pressure risk threshold and less than the first tire pressure risk threshold, avoid sections with a turning radius greater than a preset radius value during the path planning process, where the second tire pressure risk threshold is less than the first tire pressure risk threshold.

[0127] In some alternative implementations of this embodiment, the mechanical state includes a suspension state; and the path planning module 603 is further configured to: in response to determining that the risk index corresponding to the suspension state is greater than the first suspension risk threshold, avoid uneven road sections during the path planning process; in response to determining that the risk index corresponding to the suspension state is greater than or equal to the second suspension risk threshold and less than the first suspension risk threshold, select flat road sections during the path planning process, where the second suspension risk threshold is less than the first suspension risk threshold.

[0128] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, a computer program product, and a vehicle.

[0129] Figure 7 A schematic block diagram of an exemplary electronic device 700 that can be used to implement the embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementations of the present disclosure described and / or claimed herein.

[0130] As Figure 7 shown, the device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0131] Multiple components in the device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a magnetic disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0132] The computing unit 701 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 executes the various methods and processes described above, such as the path planning method. For example, in some embodiments, the path planning method can be implemented as a computer software program that is tangibly included in a machine-readable medium, such as the storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the path planning method described above can be executed. Alternatively, in other embodiments, the computing unit 701 can be configured to execute the path planning method in any other suitable way (e.g., by means of firmware).

[0133] The vehicle provided by the present disclosure may include a sensor array and the above-described electronic device as shown, and the electronic device can implement the path planning method described in any of the above embodiments when executed by its processor. Among them, the sensor array includes at least two of the following: a brake pad monitoring sensor, a tire pressure monitoring sensor, and a suspension monitoring sensor. The brake pad monitoring sensor is used to collect the current data of the brake pad state of the target vehicle, the tire pressure monitoring sensor is used to collect the current data of the tire pressure state of the target vehicle, and the suspension monitoring sensor is used to collect the current data of the suspension state of the target vehicle. Figure 7 The various embodiments of the systems and technologies described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a dedicated or general-purpose programmable processor, and can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0134]

[0135] ​The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowchart and / or block diagram are implemented. The program codes can be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0136] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0137] In order to provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0138] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), and the Internet.

[0139] A computer system can include a client and a server. The client and the server are generally far from each other and typically interact through a communication network. The client-server relationship is generated by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, can also be a server of a distributed system, or a server incorporating a blockchain.

[0140] It should be understood that various forms of the processes shown above can be used, steps can be reordered, added, or deleted. For example, the steps recited in this disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and no limitations are imposed herein.

[0141] The above specific embodiments do not constitute a limitation on the protection scope 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 shall be included within the protection scope of this disclosure.

Claims

1. A path planning method, comprising: Calculating a health index of the mechanical state based on current data corresponding to the mechanical state of the target vehicle; Determining a risk weight coefficient of the mechanical state based on the health index, and determining a risk index of the mechanical state according to the risk weight coefficient; Planning a path of the target vehicle according to the risk index to obtain a target navigation path.

2. The method according to claim 1, wherein The calculating a health index of the mechanical state based on current data corresponding to the mechanical state of the target vehicle includes: Determining historical maximum data and historical minimum data from historical data corresponding to the mechanical state; Calculating a health index of the mechanical state according to the current data, the historical maximum data, and the historical minimum data.

3. The method according to claim 1, further comprising: Performing time synchronization on the acquisition timestamp of the current data to obtain first data; Converting the first data to a vehicle coordinate system to obtain second data; Performing outlier processing on the second data to obtain processed data; And The calculating a health index of the mechanical state according to the current data, the historical maximum data, and the historical minimum data includes: Calculating a health index of the mechanical state according to the processed data, the historical maximum data, and the historical minimum data.

4. The method according to claim 1, wherein, The determining a risk weight coefficient of the mechanical state based on the health index, and determining a risk index of the mechanical state according to the risk weight coefficient includes: Determining a risk weight coefficient of the mechanical state based on a particle swarm optimization algorithm and the health index; Calculating a risk index of the mechanical state according to the risk weight coefficient and the health index.

5. The method according to claim 4, wherein, The determining a risk weight coefficient of the mechanical state based on a particle swarm optimization algorithm and the health index includes: Initializing initial weight coefficients corresponding to multiple groups of mechanical states, generating corresponding weight vectors according to the initial weight coefficients, wherein each group of initial weight coefficients satisfies a preset constraint condition; Calculating a fitness value corresponding to the weight vector according to the weight vector and the health index; Iteratively updating the multiple groups of weight vectors by using the particle swarm optimization algorithm, determining a target weight vector according to the update result, and determining a risk weight coefficient of the mechanical state according to the target weight vector, wherein the target weight vector is a weight vector whose fitness value satisfies a preset condition.

6. The method according to claim 5, wherein, The iteratively updating the multiple groups of weight vectors by using the particle swarm optimization algorithm and determining a target weight vector according to the update result includes: For each particle, comparing the current fitness value of the particle with the fitness value at the optimal position experienced by the particle, and determining the individual optimal position of the particle according to the comparison result, wherein the particle is a group of weight vectors in the multiple groups of weight vectors; Comparing the current fitness value of the particle with the fitness values at the optimal positions experienced by all particles, and determining the global optimal position of all particles according to the comparison result. Update the velocity and position of the particle according to the velocity and position of the particle, the individual optimal position, and the global optimal position; Calculate the new fitness value of the particle according to the updated velocity and position, and until the new fitness value meets the preset requirements, use the weight vector corresponding to the fitness value that meets the preset requirements as the target weight vector.

7. The method according to claim 1, wherein The mechanical state includes the brake pad state; and The path planning for the target vehicle according to the risk index includes: In response to determining that the risk index corresponding to the brake pad state is greater than or equal to the first brake risk threshold, avoid sections with a slope greater than the preset slope value during path planning; In response to determining that the risk index corresponding to the brake pad state is greater than or equal to the second brake risk threshold and less than the first brake risk threshold, avoid downhill sections with a length greater than the preset length value during path planning, where the second brake risk threshold is less than the first brake risk threshold.

8. The method according to claim 1, wherein, The mechanical state includes the tire pressure state; and The path planning for the target vehicle according to the risk index includes: In response to determining that the risk index corresponding to the tire pressure state is greater than or equal to the first tire pressure risk threshold, output a risk prompt message; In response to determining that the risk index corresponding to the tire pressure state is greater than or equal to the second tire pressure risk threshold and less than the first tire pressure risk threshold, avoid sections with a turning radius greater than the preset radius value during path planning, where the second tire pressure risk threshold is less than the first tire pressure risk threshold.

9. The method according to claim 1, wherein The mechanical state includes the suspension state; and The path planning for the target vehicle according to the risk index includes: In response to determining that the risk index corresponding to the suspension state is greater than or equal to the first suspension risk threshold, avoid uneven sections during path planning; In response to determining that the risk index corresponding to the suspension state is greater than or equal to the second suspension risk threshold and less than the first suspension risk threshold, select flat sections during path planning, where the second suspension risk threshold is less than the first suspension risk threshold.

10. A path planning device, comprising: A health index calculation module configured to calculate the health index of the mechanical state based on the current data corresponding to the mechanical state of the target vehicle; A risk index calculation module configured to determine the risk weight coefficient of the mechanical state based on the health index and determine the risk index of the mechanical state according to the risk weight coefficient; A path planning module configured to plan the path of the target vehicle according to the risk index to obtain a target navigation path.

11. An electronic device, comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1-9.

12. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the method according to any one of claims 1-9.

13. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-9.

14. A vehicle comprising: A sensor array including at least two of the following: a brake pad monitoring sensor, a tire pressure monitoring sensor, a suspension monitoring sensor, wherein the brake pad monitoring sensor is configured to collect current data on the brake pad state of a target vehicle, the tire pressure monitoring sensor is configured to collect current data on the tire pressure state of the target vehicle, and the suspension monitoring sensor is configured to collect current data on the suspension state of the target vehicle; And an electronic device as claimed in claim 11.

Images