Vehicle control method, device and equipment and computer readable storage medium

Abstract

The invention discloses a vehicle control method, device and equipment and a computer readable storage medium. The method comprises the steps that the type of goods borne by a vehicle is determined based on sensing data collected by a multi-mode sensor; obtaining the weight of goods carried by the vehicle and the gradient and length of a ramp on a road in front of the vehicle; and setting driving control parameters of the vehicle based on the type, the weight, the gradient and the length. According to the method and the device, the driving control parameters of the vehicle are adaptively set based on the type and the weight of the goods actually borne by the vehicle in combination with the gradient and the length of the ramp on the road in front of the vehicle, so that the driving safety is improved.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, specifically to a vehicle control method, device, equipment, and computer-readable storage medium. Background Technology

[0002] The driving control parameters of commercial vehicles are generally set to fixed values ​​through calibration before leaving the factory. However, fixed driving control parameters are difficult to adapt to different transportation scenarios, resulting in insufficient driving safety when transporting heavy objects, hazardous chemicals and other goods. Summary of the Invention

[0003] This application provides a vehicle control method, apparatus, device, and computer-readable storage medium, which can solve the technical problem in the prior art that fixed driving control parameters are difficult to adapt to different transportation scenarios.

[0004] In a first aspect, embodiments of this application provide a vehicle control method, the vehicle control method comprising: The type of cargo carried by the vehicle is determined based on sensor data collected by multimodal sensors; The weight of the cargo carried by the vehicle and the slope and length of the uphill section on the road in front of the vehicle are obtained. The driving control parameters of the vehicle are set based on the type, weight, slope, and length.

[0005] In conjunction with the first aspect, in one embodiment, the multimodal sensor includes a vision sensor and a radar sensor, the vehicle's cargo box is a closed cargo box, and the vision sensor and radar sensor are installed inside the cargo box. Determining the type of cargo carried by the vehicle based on the sensing data collected by the multimodal sensor includes: The visual sensing data collected by the visual sensor is input into the first recognition model to obtain the first confidence level output by the first recognition model for each predefined type. The radar sensing data collected by the radar sensor is input into the second recognition model to obtain the second confidence level output by the second recognition model for each predefined type. For each predefined type, the first confidence level and the second confidence level corresponding to the predefined type are weighted and summed according to the preset weight coefficients to obtain the comprehensive confidence level corresponding to the predefined type; The type of goods carried by the vehicle is determined by the predefined type with the highest overall confidence level.

[0006] In conjunction with the first aspect, in one embodiment, the multimodal sensor includes a vision sensor, a radar sensor, and an environmental data sensor; the vehicle's cargo box is not a closed cargo box; and determining the type of cargo carried by the vehicle based on the sensor data collected by the multimodal sensor includes: The preset weighting coefficients are corrected based on the environmental perception data collected by the environmental data sensors to obtain new weighting coefficients; The visual sensing data collected by the visual sensor is input into the first recognition model to obtain the first confidence level output by the first recognition model for each predefined type. The radar sensing data collected by the radar sensor is input into the second recognition model to obtain the second confidence level output by the second recognition model for each predefined type. For each predefined type, the first confidence level and the second confidence level corresponding to the predefined type are weighted and summed according to the new preset weight coefficients to obtain the comprehensive confidence level corresponding to the predefined type; The type of goods carried by the vehicle is determined by the predefined type with the highest overall confidence level.

[0007] In conjunction with the first aspect, in one implementation, the preset weighting coefficients include a first weighting coefficient α corresponding to visual features and a second weighting coefficient β corresponding to radar features, α+β=1; the environmental data sensor includes a rain sensor and / or a light sensor; the step of correcting the preset weighting coefficients based on environmental perception data collected by the environmental data sensor includes: The first weighting coefficient α is adjusted based on the amount of rainfall collected by the rain sensor and / or the intensity of ambient light collected by the light sensor, and the second weighting coefficient β is adjusted synchronously based on the adjusted first weighting coefficient.

[0008] In conjunction with the first aspect, in one implementation, after obtaining the comprehensive confidence level corresponding to each predefined type, the method further includes: Detect whether the maximum overall confidence level is greater than the threshold; If the value is greater than the threshold, the predefined type corresponding to the maximum comprehensive confidence level will be used as the type of goods carried by the vehicle. If the value is not greater than the threshold, a manual review prompt will be output. In response to manual verification, the type of goods carried by the vehicle is determined.

[0009] In conjunction with the first aspect, in one embodiment, the driving control parameters include a minimum following distance, and setting the driving control parameters of the vehicle based on the type, weight, slope, and length includes: The third weighting coefficient and the type quantization value are determined based on the type. The slope compensation coefficient is determined based on the length. Substituting the third weighting coefficient, type quantification value, weight, slope, and slope compensation coefficient into the correction coefficient calculation formula, we obtain the correction coefficient. The correction coefficient calculation formula is as follows: K=[γ·G+(1-γ)·log(W / W0)]·(1+δ·sinθ) Wherein, γ is the third weighting coefficient, G is the type quantification value, W is the weight, W0 is a fixed value set based on the vehicle category, δ is the slope compensation coefficient, and θ is the slope; The theoretical minimum following distance is corrected based on the correction coefficient to obtain the corrected minimum following distance; The minimum following distance of the vehicle is set based on the modified minimum following distance.

[0010] In conjunction with the first aspect, in one embodiment, the driving control parameters further include maximum deceleration and maximum steering angle, and the setting of the driving control parameters of the vehicle based on the type, weight, slope, and length further includes: Using the type as the key, query the mapping table, which records the mapping relationship between cargo type and maximum deceleration and maximum steering angle; Based on the query results, set the maximum deceleration and maximum steering angle of the vehicle.

[0011] Secondly, embodiments of this application provide a vehicle control device, the vehicle control device comprising: The determination module is used to determine the type of cargo carried by the vehicle based on sensor data collected by multimodal sensors; The acquisition module is used to acquire the weight of the cargo carried by the vehicle and the slope and length of the uphill section on the road in front of the vehicle. The setting module is used to set the driving control parameters of the vehicle based on the type, weight, slope, and length.

[0012] Thirdly, embodiments of this application provide a vehicle control device, which includes a processor, a memory, and a vehicle control program stored in the memory and executable by the processor, wherein when the vehicle control program is executed by the processor, it implements the steps of the vehicle control method as described in the first aspect.

[0013] Fourthly, embodiments of this application provide a computer-readable storage medium storing a vehicle control program, wherein when the vehicle control program is executed by a processor, it implements the steps of the vehicle control method as described in the first aspect.

[0014] The beneficial effects of the technical solutions provided in this application include: In this embodiment, the type of cargo carried by the vehicle is determined based on sensing data collected by multimodal sensors; the weight of the cargo carried by the vehicle and the slope and length of the uphill section on the road ahead of the vehicle are obtained; and the driving control parameters of the vehicle are set based on the type, weight, slope, and length. Through this embodiment, the driving control parameters of the vehicle are adaptively set based on the actual type and weight of the cargo carried by the vehicle, combined with the slope and length of the uphill section on the road ahead of the vehicle, thereby improving driving safety. Attached Figure Description

[0015] Figure 1 This is a schematic flowchart of an embodiment of the vehicle control method of this application; Figure 2 This is a schematic diagram of the functional modules of an embodiment of the vehicle control device of this application; Figure 3 This is a schematic diagram of the hardware structure of the vehicle control device involved in the embodiments of this application. Detailed Implementation

[0016] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0018] In a first aspect, embodiments of this application provide a vehicle control method.

[0019] In one embodiment, reference is made to Figure 1 , Figure 1 This is a schematic flowchart of an embodiment of the vehicle control method of this application. Figure 1 As shown, the vehicle control method includes: Step S10: Determine the type of cargo carried by the vehicle based on the sensing data collected by the multimodal sensors; In this embodiment, multimodal sensors collect data in different modalities, such as image data and point cloud data, and the type of cargo carried by the vehicle is determined by combining the data from different modalities. The sensing range of the multimodal sensors is the cargo-carrying area of ​​the vehicle.

[0020] Further, in one embodiment, the multimodal sensor includes a vision sensor and a radar sensor, the vehicle's cargo box is a closed cargo box, and the vision sensor and radar sensor are installed inside the cargo box. Step S10 includes: Step S1011: Input the visual sensing data collected by the visual sensor into the first recognition model to obtain the first confidence level output by the first recognition model for each predefined type; Step S1012: Input the radar sensing data collected by the radar sensor into the second recognition model to obtain the second confidence level output by the second recognition model for each predefined type; In this embodiment, the multimodal sensor includes a vision sensor and a radar sensor. When the vehicle's cargo box is a closed cargo box, the vision sensor and the radar sensor are installed inside the cargo box, specifically on the top inside the closed cargo box.

[0021] For vision sensors, the visual sensing data they collect is images. Using images or image features as input to the first recognition model, the first confidence level output by the first recognition model for each predefined type can be obtained. The predefined types are the types of goods that the first recognition model can recognize, and are determined during the training process.

[0022] For radar sensors, the collected radar sensing data is point cloud data. Specifically, the radar sensor emits frequency-modulated continuous waves and receives the echoes reflected from the surface of the cargo; through signal processing, the echoes are converted into point cloud data; each point contains information such as range, azimuth, elevation, radial velocity (Doppler effect), and reflection intensity. Using the point cloud data as input to the second recognition model, the second confidence level output by the second recognition model for each predefined type can be obtained. The predefined types are the types of cargo that the second recognition model can recognize, determined by the training process.

[0023] The underlying model of the first / second recognition model mentioned above can be a traditional machine learning model (such as a support vector machine or random forest) or a simple neural network classification model. By training the selected underlying model using conventional training methods, the first / second recognition model can be obtained.

[0024] Step S1013: For each predefined type, the first confidence level and the second confidence level corresponding to the predefined type are weighted and summed according to the preset weight coefficients to obtain the comprehensive confidence level corresponding to the predefined type. Step S1014: The predefined type with the highest overall confidence level is selected as the type of goods carried by the vehicle.

[0025] In this embodiment, the preset weighting coefficients are assumed to be 0.7 and 0.3, where 0.7 is used to weight the first confidence level corresponding to the visual features, and 0.3 is used to weight the second confidence level corresponding to the radar features. For example, for predefined type 1, the first confidence level is 0.9 and the second confidence level is 0.7, then the comprehensive confidence level corresponding to predefined type 1 is 0.7 × 0.9 + 0.3 × 0.6 = 0.81. Similarly, the comprehensive confidence level corresponding to each predefined type can be obtained, and the predefined type with the highest comprehensive confidence level is taken as the type of cargo carried by the vehicle.

[0026] Furthermore, in one embodiment, the multimodal sensor includes a vision sensor, a radar sensor, and an environmental data sensor, and the vehicle's cargo box is not a closed cargo box. Step S10 includes: Step S1021: Correct the preset weighting coefficients based on the environmental perception data collected by the environmental data sensor to obtain new weighting coefficients; Further, in one embodiment, the preset weighting coefficients include a first weighting coefficient α corresponding to visual features and a second weighting coefficient β corresponding to radar features, α+β=1; the environmental data sensor includes a rain sensor and / or a light sensor; step S1021 includes: The first weighting coefficient α is adjusted based on the amount of rainfall collected by the rain sensor and / or the intensity of ambient light collected by the light sensor, and the second weighting coefficient β is adjusted synchronously based on the adjusted first weighting coefficient.

[0027] In this embodiment, the multimodal sensors include a vision sensor, a radar sensor, and an environmental data sensor. When the vehicle's cargo box is not enclosed, the vision sensor and radar sensor can be installed at the rear of the cab, with the sensing area being the cargo loading area of ​​the cargo box. In this case, the vision sensor is susceptible to environmental interference; for example, heavy rainfall or low ambient light intensity can reduce the sensor's acquisition accuracy, leading to a decrease in the accuracy of cargo type prediction based on visual sensor data. Therefore, it is necessary to adjust the first weighting coefficient α based on the amount of rainfall collected by the rain sensor and / or the ambient light intensity collected by the light sensor.

[0028] For example, a functional relationship can be set up with the magnitude of ambient rainfall and / or the magnitude of ambient light intensity as independent variables and α as the dependent variable. The adjusted α can be obtained by substituting the actual collected ambient rainfall and / or ambient light intensity into this functional relationship. Setting this functional relationship must follow the principle that α decreases as ambient rainfall increases and / or α decreases as ambient light intensity decreases.

[0029] The initial values ​​of α and β are 0.7 and 0.3, respectively. When the ambient rainfall is less than 2 mm / h and the ambient light intensity is greater than 5000 Lux, the value of α decreases by 0.1 for every 5 mm / h increase in ambient rainfall (A); and the value of α decreases by 0.1 for every 1000 Lux decrease in ambient light intensity (A) from 5000 Lux. The minimum value of α is 0.2. It should be noted that the above values ​​are illustrative and do not constitute a limitation of this application.

[0030] Step S1022: Input the visual sensing data collected by the visual sensor into the first recognition model to obtain the first confidence level output by the first recognition model for each predefined type; Step S1023: Input the radar sensing data collected by the radar sensor into the second recognition model to obtain the second confidence level output by the second recognition model for each predefined type; Step S1024: For each predefined type, the first confidence level and the second confidence level corresponding to the predefined type are weighted and summed according to the new preset weight coefficients to obtain the comprehensive confidence level corresponding to the predefined type. Step S1025: The predefined type with the highest overall confidence level is selected as the type of cargo carried by the vehicle.

[0031] In this embodiment, the specific implementation of steps S1022 to S1025 can be referred to the implementation of steps S1011 to S1014 above, and will not be repeated here.

[0032] Furthermore, in one embodiment, after step S1013 or step S1024, the method further includes: Check if the maximum overall confidence level is greater than a threshold; if it is greater than the threshold, use the predefined type corresponding to the maximum overall confidence level as the type of goods carried by the vehicle; if it is not greater than the threshold, output a manual review prompt; in response to the manual review operation, determine the type of goods carried by the vehicle.

[0033] In this embodiment, for any predefined type, the higher its overall confidence level, the greater the probability that the type of goods carried by the vehicle is equal to that predefined type. Therefore, a threshold needs to be set. Only when the overall confidence level is greater than the threshold will the predefined type corresponding to the highest overall confidence level be directly used as the type of goods carried by the vehicle. If it is not greater than the threshold, manual review is required, and the result of the manual review will be used as the type of goods carried by the vehicle.

[0034] Step S20: Obtain the weight of the cargo carried by the vehicle and the slope and length of the ramp in front of the vehicle. In this embodiment, the weight of the cargo carried by the vehicle can be obtained based on the existing data acquisition function of the suspension system or electronic braking system. The gradient and length of the uphill section on the road ahead of the vehicle can be determined based on navigation planning and map data.

[0035] Step S30: Set the driving control parameters of the vehicle based on the type, weight, slope, and length.

[0036] In this embodiment, the main consideration is that when a commercial vehicle carries different goods, it is necessary to set appropriate driving control parameters to improve driving safety. Based on this, it is necessary to further consider the impact of cargo weight and the gradient and length of the incline on the road ahead of the vehicle on driving. Therefore, the driving control parameters of the vehicle are set by comprehensively considering the type of cargo, cargo weight, and the gradient and length of the incline on the road ahead of the vehicle.

[0037] Furthermore, in one embodiment, the driving control parameters include the minimum following distance, and step S30 includes: Step S301: Determine the third weighting coefficient and the type quantization value based on the type; In this embodiment, a third weighting coefficient and a type quantization value are preset for each type. Based on the preset information, the third weighting coefficient and type quantization value corresponding to the currently determined type can be obtained. For example, the third weighting coefficient for ordinary goods is 0.1, and the type quantization value is 1; the third weighting coefficient for steel coils is 0.3, and the type quantization value is 2; the third weighting coefficient for hazardous chemicals is 0.5, and the type quantization value is 3.

[0038] Step S302: Determine the slope compensation coefficient based on the length; In this embodiment, the slope compensation coefficient can be set to be proportional to the length, that is, the longer the slope of the road in front of the vehicle, the larger the slope compensation coefficient. The range of the slope compensation coefficient can be limited to [0.1, 0.2].

[0039] Step S303: Substitute the third weighting coefficient, type quantification value, weight, slope, and slope compensation coefficient into the correction coefficient calculation formula to obtain the correction coefficient. The correction coefficient calculation formula is as follows: K=[γ·G+(1-γ)·log(W / W0)]·(1+δ·sinθ) Wherein, γ is the third weighting coefficient, G is the type quantification value, W is the weight, W0 is a fixed value set based on the vehicle category, δ is the slope compensation coefficient, and θ is the slope; In this embodiment, for example, when the vehicle belongs to the category of a tractor, W0=42; when the vehicle belongs to the category of a heavy-duty truck, W0=25; and when the vehicle belongs to the category of a medium-duty truck, W0=18. It should be noted that the values ​​listed here are only illustrative.

[0040] Step S304: Correct the theoretical minimum following distance based on the correction coefficient to obtain the corrected minimum following distance; In this embodiment, the theoretical minimum following distance is determined based on vehicle kinematics formulas, as follows: S0=p·V 2 / 2μg Where S0 is the theoretical minimum following distance, p is the system response coefficient, V is the vehicle speed, μ is the road friction coefficient, and g is the gravitational acceleration.

[0041] Correction calculations can be: S=S0·K Where S is the corrected minimum following distance.

[0042] Step S305: Set the minimum following distance of the vehicle based on the corrected minimum following distance.

[0043] In this embodiment, after determining the corrected minimum following distance S, the minimum following distance of the vehicle can be updated to S, so that the driver has sufficient space to perform deceleration when deceleration is required, avoiding the situation where excessive acceleration causes the cargo to hit the cab due to inertia.

[0044] Furthermore, in one embodiment, the driving control parameters further include maximum deceleration and maximum steering angle, and step S30 further includes: Using the type as the key, query the mapping table, which records the mapping relationship between cargo type and maximum deceleration and maximum steering angle; set the maximum deceleration and maximum steering angle of the vehicle based on the query results.

[0045] In this embodiment, the mapping relationship table is shown in Table 1 below:

[0046] Table 1 By using the type as the key, the corresponding maximum deceleration and maximum steering angle can be obtained by querying the mapping table, and the maximum deceleration and maximum steering angle of the vehicle can be set accordingly. This achieves the limitation of vehicle deceleration and steering angle based on cargo type, thereby ensuring driving safety.

[0047] In this embodiment, the type of cargo carried by the vehicle is determined based on sensing data collected by multimodal sensors; the weight of the cargo carried by the vehicle and the slope and length of the uphill section on the road ahead of the vehicle are obtained; and the driving control parameters of the vehicle are set based on the type, weight, slope, and length. Through this embodiment, the driving control parameters of the vehicle are adaptively set based on the actual type and weight of the cargo carried by the vehicle, combined with the slope and length of the uphill section on the road ahead of the vehicle, thereby improving driving safety.

[0048] Secondly, embodiments of this application also provide a vehicle control device.

[0049] In one embodiment, reference is made to Figure 2 , Figure 2 This is a functional module diagram of an embodiment of the vehicle control device of this application. Figure 2 As shown, the vehicle control device includes: The determination module 10 is used to determine the type of cargo carried by the vehicle based on the sensing data collected by the multimodal sensors. The acquisition module 20 is used to acquire the weight of the goods carried by the vehicle and the slope and length of the uphill road in front of the vehicle. The setting module 30 is used to set the driving control parameters of the vehicle based on the type, weight, slope and length.

[0050] Further, in one embodiment, the multimodal sensor includes a vision sensor and a radar sensor, the vehicle's cargo box is a closed cargo box, and the vision sensor and radar sensor are installed inside the cargo box. The determination module 10 is specifically used for: The visual sensing data collected by the visual sensor is input into the first recognition model to obtain the first confidence level output by the first recognition model for each predefined type. The radar sensing data collected by the radar sensor is input into the second recognition model to obtain the second confidence level output by the second recognition model for each predefined type. For each predefined type, the first confidence level and the second confidence level corresponding to the predefined type are weighted and summed according to the preset weight coefficients to obtain the comprehensive confidence level corresponding to the predefined type; The type of goods carried by the vehicle is determined by the predefined type with the highest overall confidence level.

[0051] Furthermore, in one embodiment, the multimodal sensor includes a vision sensor, a radar sensor, and an environmental data sensor. The cargo box of the vehicle is not a closed cargo box. The determination module 10 is specifically used for: The preset weighting coefficients are corrected based on the environmental perception data collected by the environmental data sensors to obtain new weighting coefficients; The visual sensing data collected by the visual sensor is input into the first recognition model to obtain the first confidence level output by the first recognition model for each predefined type. The radar sensing data collected by the radar sensor is input into the second recognition model to obtain the second confidence level output by the second recognition model for each predefined type. For each predefined type, the first confidence level and the second confidence level corresponding to the predefined type are weighted and summed according to the new preset weight coefficients to obtain the comprehensive confidence level corresponding to the predefined type; The type of goods carried by the vehicle is determined by the predefined type with the highest overall confidence level.

[0052] Further, in one embodiment, the preset weighting coefficients include a first weighting coefficient α corresponding to visual features and a second weighting coefficient β corresponding to radar features, α+β=1; the environmental data sensor includes a rain sensor and / or a light sensor; the determination module 10 is specifically used for: The first weighting coefficient α is adjusted based on the amount of rainfall collected by the rain sensor and / or the intensity of ambient light collected by the light sensor, and the second weighting coefficient β is adjusted synchronously based on the adjusted first weighting coefficient.

[0053] Furthermore, in one embodiment, the determining module 10 is specifically used for: Detect whether the maximum overall confidence level is greater than the threshold; If the value is greater than the threshold, the predefined type corresponding to the maximum comprehensive confidence level will be used as the type of goods carried by the vehicle. If the value is not greater than the threshold, a manual review prompt will be output. In response to manual verification, the type of goods carried by the vehicle is determined.

[0054] Furthermore, in one embodiment, the driving control parameters include the minimum following distance, and the setting module 30 is specifically used for: The third weighting coefficient and the type quantization value are determined based on the type. The slope compensation coefficient is determined based on the length. Substituting the third weighting coefficient, type quantification value, weight, slope, and slope compensation coefficient into the correction coefficient calculation formula, we obtain the correction coefficient. The correction coefficient calculation formula is as follows: K=[γ·G+(1-γ)·log(W / W0)]·(1+δ·sinθ) Wherein, γ is the third weighting coefficient, G is the type quantification value, W is the weight, W0 is a fixed value set based on the vehicle category, δ is the slope compensation coefficient, and θ is the slope; The theoretical minimum following distance is corrected based on the correction coefficient to obtain the corrected minimum following distance; The minimum following distance of the vehicle is set based on the modified minimum following distance.

[0055] Furthermore, in one embodiment, the driving control parameters further include maximum deceleration and maximum steering angle, and the setting module 30 is specifically used for: Using the type as the key, query the mapping table, which records the mapping relationship between cargo type and maximum deceleration and maximum steering angle; Based on the query results, set the maximum deceleration and maximum steering angle of the vehicle.

[0056] The functions of each module in the above-mentioned vehicle control device correspond to the steps in the above-mentioned vehicle control method embodiment, and their functions and implementation processes will not be described in detail here.

[0057] Thirdly, embodiments of this application provide a vehicle control device, which may be a personal vehicle computer, a vehicle intelligent driving domain controller, or other device with data processing capabilities.

[0058] Reference Figure 3 , Figure 3 This is a schematic diagram of the hardware structure of the vehicle control device involved in the embodiments of this application. In the embodiments of this application, the vehicle control device may include a processor, a memory, a communication interface, and a communication bus.

[0059] The communication bus can be of any type and is used to interconnect the processor, memory, and communication interface.

[0060] Communication interfaces include input / output (I / O) interfaces, physical interfaces, and logical interfaces used to interconnect devices within the vehicle control equipment, as well as interfaces used to interconnect the vehicle control equipment with other devices (such as other computing devices or user equipment). Physical interfaces can be Ethernet interfaces, fiber optic interfaces, ATM interfaces, etc.; user equipment can be displays, keyboards, etc.

[0061] Memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0062] The processor can be a general-purpose processor, which can call the vehicle control program stored in the memory and execute the vehicle control method provided in the embodiments of this application. For example, the general-purpose processor can be a central processing unit (CPU). The method executed when the vehicle control program is called can be referred to in the various embodiments of the vehicle control method of this application, and will not be repeated here.

[0063] Those skilled in the art will understand that Figure 3 The hardware structure shown does not constitute a limitation of this application and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0064] Fourthly, embodiments of this application also provide a computer-readable storage medium.

[0065] The present application has a computer-readable storage medium storing a vehicle control program, wherein when the vehicle control program is executed by a processor, it implements the steps of the vehicle control method as described above.

[0066] The method implemented when the vehicle control program is executed can be referred to in various embodiments of the vehicle control method of this application, and will not be repeated here.

[0067] It should be noted that the sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0068] The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus. The terms "first," "second," and "third," etc., are used to distinguish different objects, etc., and do not indicate a sequence, nor do they limit "first," "second," and "third" to different types.

[0069] In the description of the embodiments of this application, terms such as "exemplary," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary," "for example," or "for instance" is intended to present the relevant concepts in a concrete manner.

[0070] In the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more.

[0071] In some processes described in the embodiments of this application, multiple operations or steps are included in a specific order. However, it should be understood that these operations or steps may not be executed in the order they appear in the embodiments of this application, or they may be executed in parallel. The sequence number of the operation is only used to distinguish different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed sequentially or in parallel, and these operations or steps may be combined.

[0072] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to execute the methods described in the various embodiments of this application.

[0073] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A vehicle control method, characterized in that, The vehicle control method includes: The type of cargo carried by the vehicle is determined based on sensor data collected by multimodal sensors; The weight of the cargo carried by the vehicle and the slope and length of the uphill section on the road in front of the vehicle are obtained. The driving control parameters of the vehicle are set based on the type, weight, slope, and length.

2. The vehicle control method as described in claim 1, characterized in that, The multimodal sensor includes a vision sensor and a radar sensor. The vehicle's cargo box is a closed cargo box, and the vision sensor and radar sensor are installed inside the cargo box. Determining the type of cargo carried by the vehicle based on the sensor data collected by the multimodal sensor includes: The visual sensing data collected by the visual sensor is input into the first recognition model to obtain the first confidence level output by the first recognition model for each predefined type. The radar sensing data collected by the radar sensor is input into the second recognition model to obtain the second confidence level output by the second recognition model for each predefined type. For each predefined type, the first confidence level and the second confidence level corresponding to the predefined type are weighted and summed according to the preset weight coefficients to obtain the comprehensive confidence level corresponding to the predefined type; The type of goods carried by the vehicle is determined by the predefined type with the highest overall confidence level.

3. The vehicle control method as described in claim 1, characterized in that, The multimodal sensors include vision sensors, radar sensors, and environmental data sensors. The vehicle's cargo box is not a closed cargo box. The determination of the type of cargo carried by the vehicle based on the sensor data collected by the multimodal sensors includes: The preset weighting coefficients are corrected based on the environmental perception data collected by the environmental data sensors to obtain new weighting coefficients; The visual sensing data collected by the visual sensor is input into the first recognition model to obtain the first confidence level output by the first recognition model for each predefined type. The radar sensing data collected by the radar sensor is input into the second recognition model to obtain the second confidence level output by the second recognition model for each predefined type. For each predefined type, the first confidence level and the second confidence level corresponding to the predefined type are weighted and summed according to the new preset weight coefficients to obtain the comprehensive confidence level corresponding to the predefined type; The type of goods carried by the vehicle is determined by the predefined type with the highest overall confidence level.

4. The vehicle control method as described in claim 3, characterized in that, The preset weighting coefficients include the first weighting coefficient α corresponding to visual features and the second weighting coefficient β corresponding to radar features, where α+β=1; Environmental data sensors include rain sensors and / or light sensors; The step of correcting the preset weighting coefficients based on environmental perception data collected by environmental data sensors includes: The first weighting coefficient α is adjusted based on the amount of rainfall collected by the rain sensor and / or the amount of light intensity collected by the light sensor, and the second weighting coefficient β is adjusted synchronously based on the adjusted first weighting coefficient.

5. The vehicle control method as described in claim 2 or 3, characterized in that, After obtaining the overall confidence level for each predefined type, the following is also included: Detect whether the maximum overall confidence level is greater than the threshold; If the value is greater than the threshold, the predefined type corresponding to the maximum comprehensive confidence level will be used as the type of goods carried by the vehicle. If the value is not greater than the threshold, a manual review prompt will be output. In response to manual verification, the type of goods carried by the vehicle is determined.

6. The vehicle control method as described in claim 1, characterized in that, The driving control parameters include the minimum following distance, and the setting of the driving control parameters of the vehicle based on the type, weight, slope, and length includes: The third weighting coefficient and the type quantization value are determined based on the type. The slope compensation coefficient is determined based on the length. Substituting the third weighting coefficient, type quantification value, weight, slope, and slope compensation coefficient into the correction coefficient calculation formula, we obtain the correction coefficient. The correction coefficient calculation formula is as follows: K=[γ·G+(1-γ)·log(W / W0)]·(1+δ·sinθ) Wherein, γ is the third weighting coefficient, G is the type quantification value, W is the weight, W0 is a fixed value set based on the vehicle category, δ is the slope compensation coefficient, and θ is the slope; The theoretical minimum following distance is corrected based on the correction coefficient to obtain the corrected minimum following distance; The minimum following distance of the vehicle is set based on the modified minimum following distance.

7. The vehicle control method as described in claim 6, characterized in that, The driving control parameters also include maximum deceleration and maximum steering angle. Setting the driving control parameters of the vehicle based on its type, weight, gradient, and length further includes: Using the type as the key, query the mapping table, which records the mapping relationship between cargo type and maximum deceleration and maximum steering angle; Based on the query results, set the maximum deceleration and maximum steering angle of the vehicle.

8. A vehicle control device, characterized in that, The vehicle control device includes: The determination module is used to determine the type of cargo carried by the vehicle based on sensor data collected by multimodal sensors; The acquisition module is used to acquire the weight of the cargo carried by the vehicle and the slope and length of the uphill section on the road in front of the vehicle. The setting module is used to set the driving control parameters of the vehicle based on the type, weight, slope, and length.

9. A vehicle control device, characterized in that, The vehicle control device includes a processor, a memory, and a vehicle control program stored in the memory and executable by the processor, wherein when the vehicle control program is executed by the processor, it implements the steps of the vehicle control method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a vehicle control program, wherein when the vehicle control program is executed by a processor, it implements the steps of the vehicle control method as described in any one of claims 1 to 7.

Images