Vehicle control method, apparatus, and medium based on lidar life prediction
By acquiring the operating parameters of the LiDAR to predict the failure rate and combining them with the threshold of the operating scenario to formulate vehicle control strategies, the impact of aging of the vehicle-mounted LiDAR on driving safety is solved, and the safety of autonomous vehicles is improved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- UISEE TECH BEIJING LTD
- Filing Date
- 2021-11-30
- Publication Date
- 2026-05-12
AI Technical Summary
The lack of effective monitoring of aging of vehicle-mounted lidar in existing technologies affects vehicle driving safety, especially when lidar malfunctions may cause traffic accidents.
The sensor data acquisition and processing module acquires the operating parameters of the LiDAR, uses a preset server to predict the current failure rate, and combines multiple thresholds for different working scenarios to formulate vehicle control strategies, including operations such as alerts, speed reduction, maintenance, or parking.
It improves vehicle driving safety by accurately predicting the failure rate of lidar and adapting to the aging rate in different working scenarios, thereby reducing the occurrence of traffic accidents.
Smart Images
Figure CN116198532B_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of autonomous driving technology, and in particular to a vehicle control method, apparatus, electronic device, and storage medium based on lidar lifetime prediction. Background Technology
[0002] In the field of autonomous driving, ensuring vehicle safety is paramount. The aging of any component can negatively impact driving safety. For example, aging of the onboard LiDAR can have a significant impact on vehicle safety.
[0003] However, there is currently no solution for monitoring the aging of vehicle-mounted LiDAR. Summary of the Invention
[0004] To solve the above-mentioned technical problems, or at least partially solve them, this disclosure provides a vehicle control method, device, electronic device, and storage medium based on lidar lifetime prediction, thereby achieving the goal of improving vehicle driving safety.
[0005] In a first aspect, embodiments of this disclosure provide a vehicle control method based on lidar lifetime prediction, the method comprising:
[0006] When the vehicle-mounted lidar is in operation, the operating parameters of the vehicle-mounted lidar are determined by the sensor data acquisition and processing module.
[0007] The sensor data acquisition and processing module sends the operating parameters to a preset server, so that the preset server can predict the current failure rate of the vehicle-mounted lidar based on the operating parameters, or the operating parameters and the factory data of the vehicle-mounted lidar.
[0008] The autonomous driving decision-making and planning module receives the current failure rate of the vehicle-mounted LiDAR from the preset server.
[0009] The autonomous driving decision planning module determines a vehicle control strategy based on the current failure rate and multiple preset thresholds that match the working scenario of the vehicle-mounted LiDAR, and controls the vehicle based on the vehicle control strategy.
[0010] Secondly, embodiments of this disclosure also provide a vehicle control device based on lidar lifetime prediction, the device comprising:
[0011] The sensor data acquisition and processing module is used to determine the operating parameters of the vehicle-mounted LiDAR when it is in operation, and send the operating parameters to a preset server so that the preset server can predict the current failure rate of the vehicle-mounted LiDAR based on the operating parameters, or the operating parameters and the factory data of the vehicle-mounted LiDAR.
[0012] The autonomous driving decision planning module is used to receive the current failure rate of the vehicle-mounted LiDAR from the preset server, and determine the vehicle control strategy based on the current failure rate and multiple preset thresholds that match the working scenario of the vehicle-mounted LiDAR, so as to control the vehicle based on the vehicle control strategy.
[0013] Thirdly, embodiments of this disclosure also provide an electronic device, the electronic device comprising: one or more processors; a storage device for storing one or more programs; and when the one or more programs are executed by the one or more processors, causing the one or more processors to implement the vehicle control method based on lidar lifetime prediction as described above.
[0014] Fourthly, embodiments of this disclosure also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the vehicle control method based on lidar lifetime prediction as described above.
[0015] The vehicle control method based on lidar lifetime prediction provided in this disclosure improves vehicle safety by determining the operating parameters of the vehicle-mounted lidar through a sensor data acquisition and processing module when the lidar is in operation; sending the operating parameters to a preset server through the sensor data acquisition and processing module; predicting the current failure rate of the vehicle-mounted lidar based on the operating parameters, or the operating parameters and the factory data of the vehicle-mounted lidar, through the preset server; receiving the current failure rate of the vehicle-mounted lidar from the preset server through an autonomous driving decision-making and planning module; and determining a vehicle control strategy based on the current failure rate and multiple preset thresholds matching the operating scenario of the vehicle-mounted lidar through the autonomous driving decision-making and planning module. Specifically, by determining the current failure rate of the vehicle-mounted lidar in conjunction with its operating scenario, the accuracy of predicting the current failure rate of the vehicle-mounted lidar is improved; and by controlling the vehicle based on multiple thresholds matching the operating scenario of the vehicle-mounted lidar, the goal of improving vehicle safety is achieved. Attached Figure Description
[0016] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.
[0017] Figure 1 This is a flowchart of a vehicle control method based on lidar lifetime prediction in an embodiment of this disclosure;
[0018] Figure 2 This is a flowchart of a vehicle control method based on lidar lifetime prediction in an embodiment of this disclosure;
[0019] Figure 3 This is a schematic diagram of data flow interaction for a vehicle control method based on lidar lifetime prediction in an embodiment of this disclosure;
[0020] Figure 4 This is a schematic diagram of the structure of a vehicle control device based on lidar lifetime prediction in an embodiment of this disclosure;
[0021] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of this disclosure. Detailed Implementation
[0022] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.
[0023] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.
[0024] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.
[0025] In autonomous vehicles, onboard LiDAR can be used to detect static and dynamic obstacles around the vehicle in real time. It then uses point cloud classification algorithms to segment and classify these obstacles, outputting the results to the vehicle's autonomous driving decision-making and planning module. This module makes different behavioral decisions based on the different obstacles, such as controlling the vehicle to follow, overtake, or stop. Therefore, if the onboard LiDAR malfunctions and cannot function, it will directly affect the safe operation of the autonomous vehicle.
[0026] Typically, when the aging level of the vehicle's LiDAR (understandably, the greater the aging level, the higher the probability of malfunction) reaches a certain threshold, the autonomous vehicle will immediately stop. However, this approach can be dangerous; for example, vehicles behind the vehicle may be involved in a chain-reaction collision due to the sudden stop, leading to traffic congestion. Therefore, it is necessary to continuously monitor the aging level of the vehicle's LiDAR. When the aging level is detected to reach a certain value, timely measures such as reminders and maintenance should be taken, including repairing or replacing the LiDAR, or temporarily relocating the vehicle to a safe location to wait, to ensure vehicle safety and prevent traffic accidents caused by improper handling.
[0027] To address the aforementioned problems, this disclosure provides a vehicle control method based on lidar lifetime prediction, aiming to improve vehicle safety. Specifically, it predicts the current failure rate of the vehicle-mounted lidar and applies different control measures to the vehicle based on the predicted current failure rate. The method is described below with reference to specific embodiments. Figure 1 This is a flowchart illustrating a vehicle control method based on lidar lifetime prediction, as described in an embodiment of this disclosure. The method can be executed by a vehicle control device based on lidar lifetime prediction, which can be implemented in software and / or hardware and can be configured in an electronic device.
[0028] like Figure 1 As shown, the method may specifically include the following steps:
[0029] Step 110: When the vehicle-mounted LiDAR is in working condition, the operating parameters of the vehicle-mounted LiDAR are determined by the sensor data acquisition and processing module.
[0030] Among them, the sensor data acquisition and processing module is a functional module in the autonomous driving system responsible for collecting sensor data, processing and forwarding the collected sensor data.
[0031] The operating parameters of an automotive LiDAR include, for example, the ambient temperature and humidity during operation. In this embodiment, the ambient temperature and humidity during operation are defined as the current temperature and current humidity. Operating parameters may also include the vibration intensity experienced by the automotive LiDAR during operation. In this embodiment, the vibration intensity experienced by the automotive LiDAR during operation is defined as the current vibration intensity, which can be determined by the vehicle's acceleration and angular velocity. These operating parameters are closely related to the service life of the automotive LiDAR, or in other words, they are closely related to its aging rate. Therefore, determining the operating parameters of the automotive LiDAR when it is in operation provides a data basis for obtaining a more accurate current failure rate.
[0032] Step 120: The sensor data acquisition and processing module sends the operating parameters to a preset server, so that the preset server can predict the current failure rate of the vehicle-mounted LiDAR based on the operating parameters, or the operating parameters and the factory data of the vehicle-mounted LiDAR.
[0033] In this process, for different models of lidar, manufacturers place sample lidars under specific test conditions to measure the distribution of failures over time. By analyzing the life test data, they determine the lidar's life characteristics and failure distribution patterns, obtaining reliability indicators such as failure rate and mean lifespan. However, the data obtained in this way is relatively ideal. In reality, the aging degree of the same lidar varies due to factors such as vibration, operating time, and environment, resulting in different failure rates. Therefore, the technical solution of this disclosure, based on the lidar reliability indicators provided by the manufacturer, uses a remaining effective lifespan prediction algorithm to monitor and predict the aging process of the lidar and report it to the vehicle.
[0034] Remaining effective lifetime prediction algorithms include physical model-based prediction algorithms, data-driven prediction algorithms, and statistical reliability-based prediction algorithms. Among them, the data-driven prediction algorithm and the statistical reliability-based prediction algorithm use information from observation data to identify degraded mathematical models and predict the remaining effective lifetime of the lidar based on these mathematical models.
[0035] It should be noted that in this embodiment, the remaining effective lifespan of the lidar is expressed using the current failure rate. It is understood that the longer the remaining effective lifespan, the lower the current failure rate, meaning a lower probability of a current failure.
[0036] Step 130: Receive the current failure rate of the vehicle-mounted LiDAR from the preset server through the autonomous driving decision planning module.
[0037] Step 140: The autonomous driving decision planning module determines a vehicle control strategy based on the current failure rate and multiple preset thresholds that match the working scenario of the vehicle-mounted LiDAR, so as to control the vehicle based on the vehicle control strategy.
[0038] Among them, the autonomous driving decision planning module is the functional module responsible for decision planning in the autonomous driving system, such as whether to control the vehicle to overtake or slow down.
[0039] Understandably, the aging rate of the same model of LiDAR varies in different operating scenarios, thus the definition of the threshold also differs in different scenarios. For example, for the same threshold 'a', in a relatively ideal operating scenario (e.g., where the ambient temperature, humidity, and vibration intensity experienced by the LiDAR are moderate, resulting in a lower aging rate), when the current failure rate of the LiDAR reaches threshold 'a', the LiDAR may still have a relatively long remaining lifespan before failure, allowing the vehicle to continue driving. However, in a less ideal operating scenario (e.g., where the ambient temperature, humidity, and vibration intensity experienced by the LiDAR are extreme, resulting in a higher aging rate), when the current failure rate reaches threshold 'a', the LiDAR may fail very quickly, meaning a shorter remaining lifespan. In this case, the vehicle needs to be stopped in a safe area as soon as possible and should not continue driving.
[0040] To address the issues of varying threshold definitions and aging rates of LiDAR in different operating scenarios, this embodiment pre-sets thresholds in the autonomous driving decision-making and planning module that match the operating scenarios of the vehicle-mounted LiDAR. Different operating scenarios correspond to different thresholds. Furthermore, to continuously monitor the aging process of the vehicle-mounted LiDAR and improve vehicle driving safety, the autonomous driving decision-making and planning module pre-sets multiple threshold levels matching the same operating scenario. For example, when the current failure rate reaches the lowest threshold level, the vehicle is alerted to the aging or failure issue of the vehicle-mounted LiDAR; when the current failure rate reaches the medium threshold level, the vehicle slows down and activates its hazard lights to warn following vehicles to maintain a safe distance and increase their attention to the vehicle to prevent it from stopping at any time; when the current failure rate reaches a high threshold level, the vehicle is driven to a designated repair location for repair, or when the current failure rate reaches an even higher threshold level, the vehicle is driven to a designated parking location for parking. It should be noted that the threshold for the same level differs in different operating scenarios.
[0041] The vehicle control method based on lidar lifetime prediction provided in this embodiment sets different thresholds according to different working scenarios of the vehicle-mounted lidar, and adopts different vehicle control strategies according to different thresholds reached by the current failure rate. This solves the problem of inaccurate judgment of the current failure rate of the vehicle-mounted lidar due to different working scenarios, improves the accuracy of determining the current failure rate of the vehicle-mounted lidar, and thus improves the driving safety of the vehicle.
[0042] Figure 2 This is a flowchart of another vehicle control method based on lidar lifetime prediction in this disclosure. Based on the above embodiments, this embodiment provides a specific implementation of step 130, "The autonomous driving decision-making and planning module determines the vehicle control strategy based on the current failure rate and multiple preset thresholds matching the working scenario of the onboard lidar," to improve vehicle driving safety. Figure 2 As shown, the vehicle control method based on lidar lifetime prediction specifically includes the following steps:
[0043] Step 210: When the vehicle-mounted LiDAR is in working condition, the operating parameters of the vehicle-mounted LiDAR are determined by the sensor data acquisition and processing module, and the operating parameters are sent to the preset server.
[0044] The preset server predicts the current failure rate of the vehicle-mounted LiDAR based on the operating parameters, or the operating parameters and the factory data of the vehicle-mounted LiDAR.
[0045] Step 220: Receive the current failure rate of the vehicle-mounted LiDAR from the preset server through the autonomous driving decision planning module.
[0046] Step 230a: If the current failure rate reaches the first-level threshold matching the working scenario of the vehicle-mounted LiDAR but does not reach the second-level threshold matching the working scenario of the vehicle-mounted LiDAR, determine that the vehicle control strategy is to control the vehicle to issue a prompt message.
[0047] Step 230b: If the current failure rate reaches the second-level threshold but does not reach the third-level threshold that matches the working scenario of the vehicle-mounted LiDAR, determine that the vehicle control strategy is to control the vehicle to slow down and turn on the hazard lights.
[0048] Step 230c: If the current failure rate reaches the third-level threshold but does not reach the fourth-level threshold that matches the working scenario of the vehicle-mounted LiDAR, determine that the vehicle control strategy is to control the vehicle to drive to the set maintenance location for maintenance.
[0049] Step 230d: If the current failure rate reaches the fourth level threshold, determine that the vehicle control strategy is to control the vehicle to drive to the set parking position and park.
[0050] Step 240: Execute the vehicle control strategy through the autonomous driving chassis control module.
[0051] By setting different thresholds according to different working scenarios of vehicle-mounted LiDAR, and setting multiple matching threshold levels for the same working scenario, different vehicle control strategies can be adopted according to the different levels of thresholds reached by the current failure rate in the same working scenario. This can adapt to the problem of different aging rates of the same model of LiDAR in different working scenarios, and improve vehicle driving safety.
[0052] Furthermore, before controlling the vehicle based on the vehicle control strategy, the method further includes: receiving vehicle perception and positioning information sent by the autonomous driving perception and positioning module through the autonomous driving decision planning module; the autonomous driving perception and positioning module determining the vehicle perception and positioning information based on the onboard sensor data sent by the sensor data acquisition and processing module.
[0053] Accordingly, controlling the vehicle based on the vehicle control strategy includes:
[0054] The autonomous driving decision-making and planning module determines the planned driving path of the vehicle based on the vehicle perception and positioning information and the vehicle control strategy, and determines the autonomous driving control command based on the planned driving path; the autonomous driving decision-making and planning module sends the autonomous driving control command to the autonomous driving chassis control module; the autonomous driving chassis control module controls the vehicle according to the autonomous driving control command.
[0055] The control of the vehicle by the autonomous driving chassis control module according to the autonomous driving control command includes at least one of the following: sending a braking control command to the vehicle's brake-by-wire system; sending a steering control command to the vehicle's electronic power steering system; sending a light-off control command to the vehicle's hazard lights; and sending a drive control command to the vehicle's vehicle controller.
[0056] For example, determining the operating parameters of the vehicle-mounted lidar through the sensor data acquisition and processing module includes: acquiring the current temperature and current humidity based on the vehicle-mounted temperature and humidity sensor; acquiring the current acceleration and current angular velocity of the vehicle based on the vehicle's inertial measurement unit, wherein the current acceleration and current angular velocity are used to determine the current vibration intensity; the operating parameters include the current temperature, the current humidity, the current acceleration, and the current angular velocity.
[0057] Correspondingly, see reference as follows Figure 3 The diagram illustrates a data flow interaction of a vehicle control method based on lidar lifetime prediction. The vehicle hardware modules include: lidar 310, temperature and humidity sensor 311, inertial measurement unit (IMU) sensor 312, turn signal / hazard lights 313, vehicle controller unit (VCU) 314, electronic power steering system (EPS) 315, and electro-hydraulic braking (EHB) system 316. The software modules for the autonomous driving system include: sensor data acquisition and processing module 320, autonomous driving decision planning module 321, autonomous driving perception and localization module 322, and autonomous driving chassis control module 323. It also includes a remaining lifetime calculation and monitoring service module 330 hosted on a preset server.
[0058] Specifically, the sensor data acquisition and processing module 320 obtains the operating parameters of the vehicle-mounted lidar from the lidar 310, the temperature and humidity sensor 311, and the inertial measurement unit (IMU sensor) 312. These operating parameters may include: current temperature, current humidity, current vehicle acceleration, current angular velocity (the current acceleration and angular velocity are used to determine the current vibration intensity), operating voltage, operating current, operating temperature, and motor speed of the vehicle-mounted lidar. The sensor data acquisition and processing module 320 sends the acquired operating parameters to the remaining lifespan calculation and monitoring service module 330 on a preset server. Based on these operating parameters, the remaining lifespan calculation and monitoring service module 330 predicts the current failure rate of the vehicle-mounted lidar using relevant algorithms (e.g., data-driven algorithms, statistical reliability-based algorithms). The remaining life calculation and monitoring service module 330 sends the predicted current failure rate to the autonomous driving decision planning module 321. The autonomous driving decision planning module 321 makes a decision based on the current failure rate and multiple thresholds matching the working scenario of the onboard LiDAR. Then, based on the perception and positioning results (determined by the autonomous driving perception and positioning module 322 based on onboard sensor data acquired by the sensor data acquisition and processing module 320), it plans a driving path and sends autonomous driving control commands to the autonomous driving chassis control module 323. The autonomous driving chassis control module 323, based on the autonomous driving control commands, sends a light-off control command to the turn signal / hazard lights 313, a drive control command to the vehicle controller unit (VCU) 314, a steering control command to the electronic power steering system (EPS) 315, and a braking control command to the electro-hydraulic braking (EHB) system 316.
[0059] For example, the preset server predicts the current failure rate of the vehicle-mounted LiDAR based on the operating parameters and the factory data of the vehicle-mounted LiDAR, including: determining an environmental coefficient based on the ratio between the current temperature and a preset reference temperature, the ratio between the current humidity and a preset reference humidity, the ratio between the current vibration intensity and a preset reference vibration intensity, and a preset coefficient; and predicting the current failure rate of the vehicle-mounted LiDAR based on the environmental coefficient and the factory data of the vehicle-mounted LiDAR.
[0060] Specifically, the current failure rate of the vehicle-mounted lidar is determined according to the following formula:
[0061] γ p (t)=γ b(t)π E π Q
[0062] γ b (t)=(m / c)(t / c) (m-1)
[0063]
[0064] Where, γ p (t) represents the current failure rate of the vehicle-mounted LiDAR, t represents the usage time of the vehicle-mounted LiDAR (i.e., the length of time from when the vehicle-mounted LiDAR was put into use to the current moment), and π E π represents the environmental coefficient of the vehicle-mounted lidar. Q γ represents the quality coefficient in the factory data of the vehicle-mounted LiDAR. b (t) represents the basic failure rate of the vehicle-mounted lidar, m represents the Welb shape parameter in the factory data, c represents the Welb scale parameter in the factory data, B represents the preset coefficient, T represents the current temperature, T0 represents the preset reference temperature, H represents the current humidity, H0 represents the preset reference humidity, A represents the current vibration intensity, and A0 represents the preset reference vibration intensity.
[0065] Due to varying operating environments, such as differences in temperature and humidity caused by weather conditions and differences in vibration intensity caused by road surface conditions, the aging rate of a lidar varies. For example, a lidar operating in sunny, warm weather has an aging rate of 1 (as a baseline), but operating in cold, rainy, or snowy weather might have an aging rate of 1.5 to 2. Therefore, the predicted remaining lifespan (current failure rate) will differ depending on the operating environment, and the rate at which it reaches the thresholds for each level will also vary. Thus, it is necessary to determine the current failure rate of the lidar based on its operating environment, and the preset thresholds for multiple levels must also be matched to the operating environment, as the thresholds for the same level will differ in different operating environments.
[0066] Optionally, if the sensor data acquisition and processing module cannot determine the operating parameters of the vehicle-mounted LiDAR, the environmental coefficient is obtained by looking up a table:
[0067] The following steps are taken: First, determine the proportion of each preset climate type, the proportion of each preset weather type, and the proportion of each preset road condition type in the operating scenario of the vehicle-mounted LiDAR. Second, determine the weights corresponding to each preset climate type, each preset weather type, and each preset road condition type by looking up tables. Third, calculate the weighted sum of the proportions of each preset climate type and their corresponding weights in the operating scenario of the vehicle-mounted LiDAR to obtain a first value.
[0068] Here's an example illustrating the process of determining environmental coefficients by looking up a table: Assume the operating scenario of an autonomous vehicle's onboard LiDAR is as follows: Climate type: temperate cold 15% % % warm 55% % % hot and humid 30% ...
[0069] The environmental coefficient is then calculated as follows: (110%*15%+100%*55%+130%*30%)*(100%*40%+110%*40%+130%*30%+120%*10%)*(100%*80%+120%*20%).
[0070] Table 1: Weighting of each preset climate type, preset weather type, and preset road condition type
[0071]
[0072] In some implementations, the preset server predicts the current failure rate of the vehicle-mounted LiDAR based on the operating parameters, including: inputting the operating parameters into a trained machine learning model to obtain the current failure rate of the vehicle-mounted LiDAR. The operating parameters also include at least one of the following: the operating voltage, operating current, operating temperature, motor speed, current temperature, current humidity, and current vibration intensity of the vehicle-mounted LiDAR during operation.
[0073] Specifically, firstly, a large amount of status indicator data for the entire lifecycle of the LiDAR (the entire lifecycle refers to the time interval from commissioning to failure) is collected. These status indicators include operating current, operating voltage, operating temperature, humidity, vibration intensity, and motor speed. Secondly, the collected data is preprocessed, removing invalid or duplicate data and labeling it to determine the input and output metrics of the machine learning model. The input to the machine learning model includes the collected status indicator data, and the output is the failure rate of the LiDAR corresponding to each labeled data point. The data is grouped, with one part used as the training sample set and the other as the test sample set. Next, a machine learning model is built, using existing machine learning algorithms such as GBDT (Gradient Boosting Decision Tree), SVR (Support Vector Regression), CNN (Convolutional Neural Network), or LSTM (Long-Short Term Memory). Finally, the established machine learning model is trained based on the training sample set, and evaluated based on the test sample set. If the output error of the trained machine learning model meets the preset conditions, it is applied to actual operation to determine the current failure rate of the vehicle-mounted LiDAR. If the output error of the trained machine learning model does not meet the preset conditions, the model is improved or the training sample set is increased to continue training.
[0074] Figure 4 This is a schematic diagram of a vehicle control device based on lidar lifetime prediction, as described in an embodiment of this disclosure. Figure 4 As shown: The device includes: a sensor data acquisition and processing module 410 and an autonomous driving decision planning module 420.
[0075] The sensor data acquisition and processing module 410 is used to determine the operating parameters of the vehicle-mounted LiDAR when it is in operation, and send the operating parameters to a preset server so that the preset server can predict the current failure rate of the vehicle-mounted LiDAR based on the operating parameters, or the operating parameters and the factory data of the vehicle-mounted LiDAR. The autonomous driving decision planning module 420 is used to receive the current failure rate of the vehicle-mounted LiDAR from the preset server, and determine a vehicle control strategy based on the current failure rate and multiple preset thresholds that match the operating scenario of the vehicle-mounted LiDAR, so as to control the vehicle based on the vehicle control strategy.
[0076] Optionally, the autonomous driving decision-making and planning module 420 is specifically configured to: if the current failure rate reaches a first-level threshold matching the working scenario of the vehicle-mounted LiDAR but does not reach a second-level threshold matching the working scenario of the vehicle-mounted LiDAR, determine that the vehicle control strategy is to control the vehicle to issue a prompt message; if the current failure rate reaches the second-level threshold but does not reach a third-level threshold matching the working scenario of the vehicle-mounted LiDAR, determine that the vehicle control strategy is to control the vehicle to slow down and turn on the hazard lights; if the current failure rate reaches the third-level threshold but does not reach a fourth-level threshold matching the working scenario of the vehicle-mounted LiDAR, determine that the vehicle control strategy is to control the vehicle to drive to a set maintenance location for maintenance; if the current failure rate reaches the fourth-level threshold, determine that the vehicle control strategy is to control the vehicle to drive to a set parking location for parking.
[0077] Optionally, before controlling the vehicle based on the vehicle control strategy, the autonomous driving decision planning module 420 is further configured to receive vehicle perception and positioning information sent by the autonomous driving perception and positioning module; the autonomous driving perception and positioning module determines the vehicle perception and positioning information based on the on-board sensor data sent by the sensor data acquisition and processing module.
[0078] Optionally, the autonomous driving decision planning module 420 is further configured to determine the planned driving path of the vehicle based on the vehicle perception and positioning information and the vehicle control strategy, and to determine the autonomous driving control command based on the planned driving path.
[0079] Optionally, it also includes: an autonomous driving chassis control module, used to receive the autonomous driving control instructions sent by the autonomous driving decision planning module 420, and control the vehicle according to the autonomous driving control instructions.
[0080] Optionally, the autonomous driving chassis control module is specifically used for at least one of the following: sending braking control commands to the vehicle's brake-by-wire system; sending steering control commands to the vehicle's electronic power steering system; sending light-off control commands to the vehicle's hazard lights; and sending drive control commands to the vehicle's vehicle controller.
[0081] Optionally, the sensor data acquisition and processing module 410 is specifically used to acquire the current temperature and current humidity based on the vehicle-mounted temperature and humidity sensor; acquire the current acceleration and current angular velocity of the vehicle based on the vehicle's inertial measurement unit, wherein the current acceleration and current angular velocity are used to determine the current vibration intensity; the operating parameters include the current temperature, the current humidity, the current acceleration, and the current angular velocity.
[0082] The vehicle control device based on lidar lifetime prediction provided in this disclosure can execute the steps in the vehicle control method based on lidar lifetime prediction provided in this disclosure, and has the execution steps and beneficial effects, which will not be repeated here.
[0083] Based on the above embodiment, the preset server includes: a remaining lifespan calculation and monitoring service module, used to determine an environmental coefficient based on the ratio between the current temperature and a preset reference temperature, the ratio between the current humidity and a preset reference humidity, the ratio between the current vibration intensity and a preset reference vibration intensity, and a preset coefficient; and to predict the current failure rate of the vehicle-mounted lidar based on the environmental coefficient and the factory data of the vehicle-mounted lidar.
[0084] Optionally, if the sensor data acquisition and processing module cannot determine the operating parameters of the vehicle-mounted lidar, the remaining lifetime calculation and monitoring service module is also used to obtain the environmental coefficient by looking up a table.
[0085] Optionally, the remaining lifetime calculation and monitoring service module includes:
[0086] A first determining unit is used to determine the proportion of climate for each preset climate type, the proportion of weather for each preset weather type, and the proportion of road surface for each preset road condition type in the working scene of the vehicle-mounted LiDAR; a lookup unit is used to determine the weights corresponding to each preset climate type, each preset weather type, and each preset road condition type by looking up a table; a first calculation unit is used to perform a weighted summation based on the proportion of climate for each preset climate type and the weights corresponding to each preset climate type in the working scene of the vehicle-mounted LiDAR to obtain a first value; a second calculation unit is used to perform a weighted summation based on the proportion of weather for each preset weather type and the weights corresponding to each preset weather type in the working scene of the vehicle-mounted LiDAR to obtain a second value; a third calculation unit is used to perform a weighted summation based on the proportion of road surface for each preset road condition type and the weights corresponding to each preset road condition type in the working scene of the vehicle-mounted LiDAR to obtain a third value; a second determining unit is used to determine the sum of the first value, the second value, and the third value as the environmental coefficient.
[0087] Optionally, the operating parameters may also include at least one of the following: the operating voltage, operating current, operating temperature, and motor speed of the vehicle-mounted lidar during operation.
[0088] Optionally, the remaining lifespan calculation and monitoring service module is further configured to: input the operating parameters into a trained machine learning model to obtain the current failure rate of the vehicle-mounted LiDAR.
[0089] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of this disclosure. See below for details. Figure 5 It shows a schematic diagram of a structure suitable for implementing the electronic device 500 in the embodiments of this disclosure. Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.
[0090] like Figure 5 As shown, the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 501, which can perform various appropriate actions and processes to implement the methods of the embodiments described herein, based on a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the electronic device 500. The processing device 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.
[0091] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts, thereby implementing the vehicle control method based on lidar lifetime prediction as described above. In such embodiments, the computer program can be downloaded and installed from a network via communication device 509, or installed from storage device 508, or installed from ROM 502. When the computer program is executed by processing device 501, it performs the functions defined in the methods of embodiments of this disclosure.
[0092] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.
[0093] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: determine the operating parameters of the vehicle-mounted LiDAR through a sensor data acquisition and processing module when the vehicle-mounted LiDAR is in operation; send the operating parameters to a preset server through the sensor data acquisition and processing module, so that the preset server predicts the current failure rate of the vehicle-mounted LiDAR based on the operating parameters, or the operating parameters and the factory data of the vehicle-mounted LiDAR; receive the current failure rate of the vehicle-mounted LiDAR from the preset server through an autonomous driving decision-making and planning module; and determine a vehicle control strategy based on the current failure rate and multiple preset thresholds matching the operating scenario of the vehicle-mounted LiDAR through the autonomous driving decision-making and planning module, so as to control the vehicle based on the vehicle control strategy.
[0094] Optionally, when one or more of the above-described procedures are executed by the electronic device, the electronic device may also perform other steps described in the above embodiments.
[0095] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction 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 be, 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 machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
[0096] Option 1: A vehicle control method based on lidar lifetime prediction, the method comprising:
[0097] When the vehicle-mounted lidar is in operation, the operating parameters of the vehicle-mounted lidar are determined by the sensor data acquisition and processing module.
[0098] The sensor data acquisition and processing module sends the operating parameters to a preset server, so that the preset server can predict the current failure rate of the vehicle-mounted lidar based on the operating parameters, or the operating parameters and the factory data of the vehicle-mounted lidar.
[0099] The autonomous driving decision-making and planning module receives the current failure rate of the vehicle-mounted LiDAR from the preset server.
[0100] The autonomous driving decision planning module determines a vehicle control strategy based on the current failure rate and multiple preset thresholds that match the working scenario of the vehicle-mounted LiDAR, and controls the vehicle based on the vehicle control strategy.
[0101] Option 2: According to the method described in Option 1, the autonomous driving decision-making and planning module determines the vehicle control strategy based on the current failure rate and multiple preset thresholds that match the working scenario of the onboard LiDAR, including:
[0102] If the current failure rate reaches the first-level threshold matching the working scenario of the vehicle-mounted LiDAR but does not reach the second-level threshold matching the working scenario of the vehicle-mounted LiDAR, the vehicle control strategy is determined to control the vehicle to issue a prompt message.
[0103] If the current failure rate reaches the second-level threshold but does not reach the third-level threshold that matches the working scenario of the vehicle-mounted LiDAR, the vehicle control strategy is determined to control the vehicle to slow down and turn on the hazard lights.
[0104] If the current failure rate reaches the third-level threshold but does not reach the fourth-level threshold that matches the working scenario of the vehicle-mounted LiDAR, the vehicle control strategy is determined to control the vehicle to drive to the set maintenance location for maintenance.
[0105] If the current failure rate reaches the fourth level threshold, the vehicle control strategy is determined to control the vehicle to drive to the set parking position and park.
[0106] Option 3: According to the method described in Option 2, before controlling the vehicle based on the vehicle control strategy, the method further includes:
[0107] The autonomous driving decision planning module receives vehicle perception and positioning information sent by the autonomous driving perception and positioning module.
[0108] The autonomous driving perception and positioning module determines the vehicle perception and positioning information based on the onboard sensor data sent by the sensor data acquisition and processing module.
[0109] Option 4: According to the method described in Option 3, controlling the vehicle based on the vehicle control strategy includes:
[0110] The autonomous driving decision planning module determines the planned driving path of the vehicle based on the vehicle perception and positioning information and the vehicle control strategy, and determines the autonomous driving control command based on the planned driving path.
[0111] The autonomous driving decision-making and planning module sends the autonomous driving control command to the autonomous driving chassis control module.
[0112] The autonomous driving chassis control module controls the vehicle according to the autonomous driving control commands.
[0113] Option 5: According to the method described in Option 4, the step of controlling the vehicle through the autonomous driving chassis control module according to the autonomous driving control command includes at least one of the following:
[0114] Send braking control commands to the vehicle's brake-by-wire system;
[0115] Send steering control commands to the vehicle's electronic power steering system;
[0116] Send a light-off control command to the vehicle's hazard lights;
[0117] Send drive control commands to the vehicle's overall controller.
[0118] Option 6: According to any one of Options 1-5, the step of determining the operating parameters of the vehicle-mounted LiDAR through the sensor data acquisition and processing module includes:
[0119] The current temperature and humidity are obtained based on the vehicle's onboard temperature and humidity sensor;
[0120] The vehicle's current acceleration and current angular velocity are obtained based on the vehicle's inertial measurement unit, and the current acceleration and current angular velocity are used to determine the current vibration intensity;
[0121] The operating parameters include the current temperature, the current humidity, the current acceleration, and the current angular velocity.
[0122] Solution 7: According to the method described in Solution 6, the preset server predicts the current failure rate of the vehicle-mounted LiDAR based on the operating parameters and the factory data of the vehicle-mounted LiDAR, including:
[0123] An environmental coefficient is determined based on the ratio between the current temperature and a preset reference temperature, the ratio between the current humidity and a preset reference humidity, the ratio between the current vibration intensity and a preset reference vibration intensity, and a preset coefficient.
[0124] The current failure rate of the vehicle-mounted lidar is predicted based on the environmental coefficient and the factory data of the vehicle-mounted lidar.
[0125] Option 8: According to the method described in Option 7, if the sensor data acquisition and processing module cannot determine the operating parameters of the vehicle-mounted LiDAR, the environmental coefficient is obtained by looking up a table:
[0126] Determine the proportion of climate for each preset climate type, the proportion of weather for each preset weather type, and the proportion of road surface for each preset road condition type in the working scenario of the vehicle-mounted lidar.
[0127] The weights corresponding to each preset climate type, each preset weather type, and each preset road condition type are determined by looking up tables.
[0128] The first value is obtained by weighted summation based on the climate proportion of each preset climate type in the working scenario of the vehicle-mounted lidar and the weight corresponding to each preset climate type.
[0129] The second value is obtained by weighted summation based on the weather proportion of each preset weather type in the working scenario of the vehicle-mounted lidar and the weights corresponding to each preset weather type.
[0130] The third value is obtained by weighted summation based on the road surface proportion of each preset road condition type in the working scenario of the vehicle-mounted lidar and the weight corresponding to each preset road condition type.
[0131] The sum of the first value, the second value, and the third value is determined as the environmental coefficient.
[0132] Option 9: According to the method described in Option 6, the operating parameters further include at least one of the following: the operating voltage, operating current, operating temperature, and motor speed of the vehicle-mounted lidar during operation.
[0133] Option 10: According to the method described in Option 9, the preset server predicts the current failure rate of the vehicle-mounted LiDAR based on the operating parameters, including:
[0134] The operating parameters are input into a trained machine learning model to obtain the current failure rate of the vehicle-mounted LiDAR.
[0135] Option 11: A vehicle control device based on lidar lifetime prediction, comprising:
[0136] The sensor data acquisition and processing module is used to determine the operating parameters of the vehicle-mounted LiDAR when it is in operation, and send the operating parameters to a preset server so that the preset server can predict the current failure rate of the vehicle-mounted LiDAR based on the operating parameters, or the operating parameters and the factory data of the vehicle-mounted LiDAR.
[0137] The autonomous driving decision planning module is used to receive the current failure rate of the vehicle-mounted LiDAR from the preset server, and determine the vehicle control strategy based on the current failure rate and multiple preset thresholds that match the working scenario of the vehicle-mounted LiDAR, so as to control the vehicle based on the vehicle control strategy.
[0138] Option 12: An electronic device, the electronic device comprising:
[0139] One or more processors;
[0140] Storage device for storing one or more programs;
[0141] When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of schemes 1-10.
[0142] Option 13: A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in any one of Options 1-10.
[0143] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.
Claims
1. A vehicle control method based on lidar lifetime prediction, characterized in that, The method includes: When the vehicle-mounted lidar is in operation, the operating parameters of the vehicle-mounted lidar are determined by the sensor data acquisition and processing module. The sensor data acquisition and processing module sends the operating parameters to a preset server, so that the preset server can predict the current failure rate of the vehicle-mounted lidar based on the operating parameters, or the operating parameters and the factory data of the vehicle-mounted lidar. The autonomous driving decision-making and planning module receives the current failure rate of the vehicle-mounted LiDAR from the preset server. The autonomous driving decision planning module determines a vehicle control strategy based on the current failure rate and multiple preset thresholds that match the working scenario of the vehicle-mounted LiDAR, and controls the vehicle based on the vehicle control strategy.
2. The method according to claim 1, characterized in that, The autonomous driving decision-making and planning module determines the vehicle control strategy based on the current failure rate and multiple preset thresholds that match the operating scenario of the onboard LiDAR, including: If the current failure rate reaches the first-level threshold matching the working scenario of the vehicle-mounted LiDAR but does not reach the second-level threshold matching the working scenario of the vehicle-mounted LiDAR, the vehicle control strategy is determined to control the vehicle to issue a prompt message. If the current failure rate reaches the second-level threshold but does not reach the third-level threshold that matches the working scenario of the vehicle-mounted LiDAR, the vehicle control strategy is determined to control the vehicle to slow down and turn on the hazard lights. If the current failure rate reaches the third-level threshold but does not reach the fourth-level threshold that matches the working scenario of the vehicle-mounted LiDAR, the vehicle control strategy is determined to control the vehicle to drive to the set maintenance location for maintenance. If the current failure rate reaches the fourth level threshold, the vehicle control strategy is determined to control the vehicle to drive to the set parking position and park.
3. The method according to claim 2, characterized in that, Before controlling the vehicle based on the vehicle control strategy, the method further includes: The autonomous driving decision planning module receives vehicle perception and positioning information sent by the autonomous driving perception and positioning module. The autonomous driving perception and positioning module determines the vehicle perception and positioning information based on the onboard sensor data sent by the sensor data acquisition and processing module.
4. The method according to claim 3, characterized in that, The control of the vehicle based on the vehicle control strategy includes: The autonomous driving decision planning module determines the planned driving path of the vehicle based on the vehicle perception and positioning information and the vehicle control strategy, and determines the autonomous driving control command based on the planned driving path. The autonomous driving decision-making and planning module sends the autonomous driving control command to the autonomous driving chassis control module. The autonomous driving chassis control module controls the vehicle according to the autonomous driving control commands.
5. The method according to claim 4, characterized in that, The control of the vehicle by the autonomous driving chassis control module according to the autonomous driving control command includes at least one of the following: Send braking control commands to the vehicle's brake-by-wire system; Send steering control commands to the vehicle's electronic power steering system; Send a light-off control command to the vehicle's hazard lights; Send drive control commands to the vehicle's overall controller.
6. The method according to any one of claims 1-5, characterized in that, The process of determining the operating parameters of the vehicle-mounted lidar through the sensor data acquisition and processing module includes: The current temperature and humidity are obtained based on the vehicle's onboard temperature and humidity sensor; The vehicle's current acceleration and current angular velocity are obtained based on the vehicle's inertial measurement unit, and the current acceleration and current angular velocity are used to determine the current vibration intensity; The operating parameters include the current temperature, the current humidity, the current acceleration, and the current angular velocity.
7. The method according to claim 6, characterized in that, The preset server predicts the current failure rate of the vehicle-mounted LiDAR based on the operating parameters and the factory data of the vehicle-mounted LiDAR, including: An environmental coefficient is determined based on the ratio between the current temperature and a preset reference temperature, the ratio between the current humidity and a preset reference humidity, the ratio between the current vibration intensity and a preset reference vibration intensity, and a preset coefficient. The current failure rate of the vehicle-mounted lidar is predicted based on the environmental coefficient and the factory data of the vehicle-mounted lidar.
8. The method according to claim 7, characterized in that, If the sensor data acquisition and processing module cannot determine the operating parameters of the vehicle-mounted lidar, the environmental coefficient is obtained by looking up a table: Determine the proportion of climate for each preset climate type, the proportion of weather for each preset weather type, and the proportion of road surface for each preset road condition type in the working scenario of the vehicle-mounted lidar. The weights corresponding to each preset climate type, each preset weather type, and each preset road condition type are determined by looking up tables. The first value is obtained by weighted summation based on the climate proportion of each preset climate type in the working scenario of the vehicle-mounted lidar and the weight corresponding to each preset climate type. The second value is obtained by weighted summation based on the weather proportion of each preset weather type in the working scenario of the vehicle-mounted lidar and the weights corresponding to each preset weather type. The third value is obtained by weighted summation based on the road surface proportion of each preset road condition type in the working scenario of the vehicle-mounted lidar and the weight corresponding to each preset road condition type. The sum of the first value, the second value, and the third value is determined as the environmental coefficient.
9. The method according to claim 6, characterized in that, The operating parameters also include at least one of the following: the operating voltage, operating current, operating temperature, and motor speed of the vehicle-mounted lidar during operation.
10. The method according to claim 9, characterized in that, The preset server predicts the current failure rate of the vehicle-mounted LiDAR based on the operating parameters, including: The operating parameters are input into a trained machine learning model to obtain the current failure rate of the vehicle-mounted LiDAR.
11. A vehicle control device based on lidar lifetime prediction, characterized in that, include: The sensor data acquisition and processing module is used to determine the operating parameters of the vehicle-mounted LiDAR when it is in operation, and send the operating parameters to a preset server so that the preset server can predict the current failure rate of the vehicle-mounted LiDAR based on the operating parameters, or the operating parameters and the factory data of the vehicle-mounted LiDAR. The autonomous driving decision planning module is used to receive the current failure rate of the vehicle-mounted LiDAR from the preset server, and determine the vehicle control strategy based on the current failure rate and multiple preset thresholds that match the working scenario of the vehicle-mounted LiDAR, so as to control the vehicle based on the vehicle control strategy.
12. An electronic device, characterized in that, The electronic device includes: One or more processors; Storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-10.
13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-10.