WO2023098828A1 - 车速拼接方法、装置、电子设备及存储介质 - Google Patents

车速拼接方法、装置、电子设备及存储介质 Download PDF

Info

Publication number
WO2023098828A1
WO2023098828A1 PCT/CN2022/135975 CN2022135975W WO2023098828A1 WO 2023098828 A1 WO2023098828 A1 WO 2023098828A1 CN 2022135975 W CN2022135975 W CN 2022135975W WO 2023098828 A1 WO2023098828 A1 WO 2023098828A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle speed
acceleration
coefficient
vehicle
normal distribution
Prior art date
Application number
PCT/CN2022/135975
Other languages
English (en)
French (fr)
Inventor
邵军杰
Original Assignee
北京罗克维尔斯科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京罗克维尔斯科技有限公司 filed Critical 北京罗克维尔斯科技有限公司
Publication of WO2023098828A1 publication Critical patent/WO2023098828A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
    • B60W40/105—Speed
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/10—Longitudinal speed
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Definitions

  • the present disclosure relates to the technical field of vehicle speed prediction, and in particular to a vehicle speed splicing method, device, electronic equipment, and storage medium.
  • the future trip includes multiple road sections, and the average speed of each road section can be obtained. Because the speeds of adjacent road sections are different, it is necessary to splice the speeds of adjacent road sections to obtain the speed information of the entire trip.
  • the present disclosure provides a vehicle speed splicing method, device, electronic equipment and storage medium, so as to improve the accuracy of vehicle speed splicing.
  • the disclosed technical scheme is as follows:
  • an embodiment of the present disclosure provides a vehicle speed splicing method, including:
  • the average vehicle speed of each road section included in the itinerary information is obtained;
  • the average speed of two adjacent road sections is used as the starting speed and the ending speed respectively;
  • vehicle speed splicing is performed on the starting vehicle speed and the ending vehicle speed to obtain a spliced vehicle speed curve.
  • an embodiment of the present disclosure provides a vehicle speed splicing device, including:
  • An average vehicle speed acquisition module configured to obtain the average vehicle speed of each road section included in the itinerary information according to the itinerary information
  • the vehicle speed acquisition module to be spliced is used to use the average vehicle speeds of two adjacent road sections as the initial vehicle speed and the terminal vehicle speed respectively;
  • An acceleration preference acquisition module configured to acquire the target acceleration preference corresponding to the initial vehicle speed and the terminal vehicle speed based on a preset algorithm model
  • the vehicle speed splicing module is configured to perform splicing of the starting vehicle speed and the ending vehicle speed based on the target acceleration preference to obtain a spliced vehicle speed curve.
  • an embodiment of the present disclosure provides an electronic device, including: at least one processor; and a memory communicated with the at least one processor; wherein, the memory stores information that can be used by the at least one processor Executable instructions, the instructions are executed by the at least one processor, so that the at least one processor can execute the vehicle speed splicing method described in the embodiment of the first aspect of the present disclosure.
  • the embodiments of the present disclosure provide a non-transitory computer-readable storage medium storing computer instructions, the computer instructions are used to make the computer execute the vehicle speed splicing method described in the embodiments of the first aspect of the present disclosure.
  • an embodiment of the present disclosure provides a computer program product, including computer instructions, and when the computer instruction is executed by a processor, implements the vehicle speed stitching method described in the embodiment of the first aspect of the present disclosure.
  • an embodiment of the present disclosure provides a computer program, the computer program includes computer program code, and when the computer program code is run on a computer, the computer executes the vehicle speed control described in the embodiment of the first aspect of the present disclosure. stitching method.
  • the vehicle speed splicing of adjacent road sections can be performed to obtain predicted vehicle speed information that is more in line with the user's actual acceleration and deceleration behavior.
  • Fig. 1 is a flow chart of a vehicle speed stitching method according to an embodiment of the present disclosure.
  • Fig. 2 is an effect diagram showing vehicle speed splicing according to an embodiment of the present disclosure.
  • Fig. 3 is a flow chart showing a vehicle speed stitching method according to another embodiment of the present disclosure.
  • Fig. 4 is a flow chart showing a vehicle speed stitching method according to yet another embodiment of the present disclosure.
  • Fig. 5 is a flow chart showing a vehicle speed stitching method according to yet another embodiment of the present disclosure.
  • Fig. 6 is a block diagram of a vehicle speed splicing device according to an embodiment of the present disclosure.
  • Fig. 7 is a block diagram of a vehicle speed splicing device according to another embodiment of the present disclosure.
  • Fig. 8 is a block diagram of an electronic device according to an embodiment of the present disclosure.
  • Speed splicing refers to splicing the average speed of the vehicle's future trips to obtain a smooth speed curve.
  • the xgboost (eXtreme Gradient Boosting, extreme gradient boosting) algorithm is a very effective machine learning method.
  • the embodiments of the present disclosure provide a vehicle speed splicing method, device, electronic equipment, and storage medium, which is a vehicle speed splicing method based on the driver's actual driving characteristics, so as to achieve the same speed change interval.
  • Different speed splicing effects are produced by different vehicles, which is more in line with the current driving behavior of drivers, so that the speed splicing can achieve "thousands of people and thousands of faces”.
  • Fig. 1 is a flowchart of a vehicle speed stitching method according to an embodiment of the present disclosure. It should be noted that the vehicle speed splicing method of the embodiment of the present disclosure can be applied to the vehicle speed splicing device of the embodiment of the present disclosure.
  • the vehicle speed splicing device can be configured on electronic equipment. As shown in FIG. 1 , the vehicle speed splicing method may include the following steps: S101-S104.
  • step S101 according to the travel information, the average vehicle speed of each road section included in the travel information is obtained.
  • each link information includes mileage and time consumption. For example, the mileage of each road segment is 2 kilometers and takes 2 minutes.
  • the average speed of the two road sections needs to be obtained first.
  • the average speed of each road section can be obtained according to the mileage and time-consuming.
  • step S102 the average vehicle speeds of two adjacent road sections are used as the starting vehicle speed and the ending vehicle speed respectively.
  • the average speeds of two adjacent road sections are different, and when the speeds are spliced, it is equivalent to an accelerated road section. For example, from a start speed through acceleration to a stop speed.
  • the acceleration section includes a section realized by accelerating from a low speed to a high speed, and also includes a section realized by decelerating from a high speed to a low speed. That is to say, in the embodiments of the present disclosure, the acceleration may be a positive number or a negative number, and when the acceleration is a negative number, it is characterized as deceleration.
  • the average vehicle speeds of two adjacent road sections are used as the start acceleration speed and end acceleration speed of splicing speed respectively.
  • step S103 based on the preset algorithm model, the target acceleration preference corresponding to the starting vehicle speed and the ending vehicle speed is obtained.
  • a preset algorithm model for calculating the target acceleration preference is obtained according to the historical driving data.
  • the acceleration preference actually corresponds to an acceleration value.
  • the preset algorithm model may include a preset machine learning model obtained according to the historical driving data of the vehicle, a normal distribution model of the driving aggressiveness coefficient of the vehicle obtained according to the historical driving data of the vehicle, and a normal distribution model obtained according to the historical driving data of the vehicle. At least one of the normal distribution models of the driving aggressiveness coefficients of other vehicles obtained from the historical driving data of other vehicles.
  • the driving aggressiveness coefficient is the product of vehicle speed and acceleration.
  • the preset algorithm model is a model that can express the user's acceleration preference in different speed ranges.
  • the preset algorithm model can be a machine learning model, or a normal distribution of the driving aggressiveness coefficient of the user's historical driving habits.
  • the preset algorithm model formed by the driving aggressiveness coefficient of other vehicles can also be used.
  • step S104 based on the target acceleration preference, the initial vehicle speed and the final vehicle speed are spliced to obtain a spliced vehicle speed curve.
  • the specific vehicle speed splicing method is as follows:
  • the total acceleration distance S is calculated based on the initial vehicle speed, the terminal vehicle speed and the acceleration preference;
  • the initial vehicle speed and the end vehicle speed are spliced to obtain the vehicle speed curve.
  • the vehicle speed splicing method of the embodiments of the present disclosure obtains user acceleration preferences based on vehicle historical driving data, and performs splicing of vehicle speeds on adjacent road sections based on user acceleration preferences to obtain predicted vehicle speed information that is more in line with the user's actual acceleration and deceleration behavior.
  • the spliced vehicle speed information is applied to the energy consumption simulation model, so that the energy consumption simulation results are more in line with the actual vehicle energy consumption.
  • Fig. 3 is a flowchart of a vehicle speed stitching method according to another embodiment of the present disclosure. As shown in FIG. 3 , the vehicle speed splicing method may include the following steps: S201-S205.
  • step S201 according to the travel information, the average vehicle speed of each road section included in the travel information is acquired.
  • step S202 the average vehicle speeds of two adjacent road sections are used as the starting vehicle speed and the ending vehicle speed respectively.
  • the implementation process of the above step S201-step S202 may refer to the description of the implementation process of the above-mentioned step S101-step S102, which will not be repeated here.
  • step S203 the prediction confidence of the preset machine learning model is acquired.
  • the preset machine learning model may use an existing machine learning algorithm, such as xgboost, or a linear regression algorithm, etc., which is not limited here.
  • the input of the preset machine learning model is the initial acceleration speed and the final acceleration speed, and the output is acceleration, that is, the target acceleration preference.
  • the preset machine learning model is trained in advance.
  • the preset machine learning model is obtained through the training of the vehicle's historical driving data.
  • the training process is as follows:
  • sample data is obtained based on the historical driving data of the vehicle; wherein, the sample data includes initial acceleration vehicle speed, terminal acceleration vehicle speed and acceleration of several acceleration sections;
  • the prediction confidence of the preset machine learning model is verified by the verification sample to obtain the prediction confidence of the preset machine learning model.
  • prediction confidence can be understood as the prediction accuracy of the preset machine learning model.
  • the prediction confidence value of the preset machine learning model determines whether to obtain the target acceleration preference through the preset machine learning model, and if the prediction confidence is not enough, choose another method to obtain the target acceleration preference.
  • the prediction confidence of the preset machine learning model does not reach the preset confidence threshold
  • the target acceleration preference obtained by the preset machine learning model is inaccurate and cannot be used. Therefore, when using the preset machine learning model to obtain the target acceleration preference, it is first necessary to judge whether the prediction confidence reaches the confidence threshold.
  • step S204 in response to the prediction confidence being greater than or equal to the confidence threshold, the starting vehicle speed and the ending vehicle speed are input into the preset machine learning model to obtain the target acceleration preference.
  • 80% is selected as the confidence threshold.
  • the initial vehicle speed is 30km/h
  • the final vehicle speed is 50km/h.
  • the preset machine learning model After inputting the preset machine learning model, the preset machine learning model outputs an acceleration value such as 2m/s2.
  • step S205 based on the target acceleration preference, the initial vehicle speed and the final vehicle speed are spliced to obtain a spliced vehicle speed curve.
  • the implementation process of the above step S205 may refer to the description of the implementation process of the above step S104, which will not be repeated here.
  • a trained preset machine learning model is obtained based on vehicle historical driving data.
  • the user's acceleration preference is obtained through the preset machine learning model, and the vehicle speed of adjacent road sections is spliced based on the user's acceleration preference, so that the predicted vehicle speed information that is more in line with the user's actual acceleration and deceleration behavior can be obtained.
  • Fig. 4 is a flow chart of a vehicle speed stitching method according to yet another embodiment of the present disclosure. As shown in Fig. 4, the vehicle speed splicing method may include the following steps: S301-S305.
  • step S301 according to the travel information, the average vehicle speed of each road section included in the travel information is acquired.
  • step S302 the average vehicle speeds of two adjacent road sections are used as the starting vehicle speed and the ending vehicle speed respectively.
  • the implementation process of the above step S301-step S302 may refer to the description of the implementation process of the above-mentioned step S101-step S102, which will not be repeated here.
  • step S303 based on the normal distribution model of the vehicle's driving aggressiveness coefficient, a target driving aggressiveness coefficient corresponding to a preset scene threshold is selected.
  • the driving aggressiveness coefficient is the product of vehicle speed and acceleration.
  • the prediction confidence of the obtained preset machine learning model is compared with the confidence threshold. If the prediction confidence is less than the confidence threshold, it means that the accuracy of the preset machine learning model is not enough, and other methods are selected to obtain Target acceleration preference.
  • the embodiment of the present disclosure selects the normal distribution based on the driving aggressiveness coefficient of the host vehicle to obtain the target acceleration preference. Therefore, it is first necessary to determine whether there is a normal distribution model of the driving aggressiveness coefficient of the own vehicle in the preset algorithm model.
  • the normal distribution of the driving aggressiveness coefficient of the vehicle is obtained in advance according to the historical driving data of the vehicle.
  • the method of obtaining is as follows:
  • the driving aggressiveness coefficient is the product of vehicle speed and acceleration
  • the abscissa of the normal distribution of the driving aggressiveness coefficient of the vehicle is the driving aggressiveness coefficient
  • the vertical axis is frequency.
  • the target driving aggressiveness coefficient corresponding to the preset scene threshold is selected according to the normal distribution of the driving aggressiveness coefficient of the own vehicle.
  • the preset scene threshold is determined according to the area of the normal distribution, and the larger the area, the larger the coverage of the user scene.
  • the driving aggressiveness coefficient that can cover 90% of the scenarios of the user is selected according to the results of the normal distribution.
  • step S304 the target acceleration preference is obtained based on the target driving aggressiveness coefficient and the starting vehicle speed and the ending vehicle speed.
  • the driving aggressiveness coefficient in the embodiment of the present disclosure is the product of vehicle speed and acceleration. Based on the target driving aggressiveness coefficient, the starting speed and the ending speed, the method for obtaining the target acceleration preference is as follows:
  • the average of the starting vehicle speed and the ending vehicle speed is calculated
  • the quotient of the target driving aggressiveness coefficient and the average value is taken as the target acceleration preference.
  • the acceleration preference obtained by combining the intermediate value of the initial vehicle speed and the terminal vehicle speed with the target driving aggressiveness coefficient will be more accurate.
  • step S305 based on the target acceleration preference, the initial vehicle speed and the final vehicle speed are spliced to obtain a spliced vehicle speed curve.
  • the implementation process of the above step S305 may refer to the description of the implementation process of the above step S104, which will not be repeated here.
  • the vehicle speed splicing method of the embodiment of the present disclosure obtains a well-trained preset machine learning model based on the historical driving data of the vehicle.
  • the data obtained from the normal distribution of the driving aggressiveness coefficient of the ego vehicle According to the normal distribution, the driving aggressiveness coefficient covering most of the user's scenes is obtained, so as to obtain the user's acceleration preference, and based on the user's acceleration preference, the vehicle speed of adjacent road sections can be spliced, and the predicted vehicle speed information that is more in line with the user's actual acceleration and deceleration behavior can be obtained.
  • FIG. 5 is a flowchart of a vehicle speed stitching method according to yet another embodiment of the present disclosure. As shown in FIG. 5 , the vehicle speed splicing method may include the following steps: S501-S508.
  • step S501 according to the travel information, the average vehicle speed of each road section included in the travel information is obtained.
  • step S502 the average vehicle speeds of two adjacent road sections are used as the starting vehicle speed and the ending vehicle speed respectively.
  • step S503 the prediction confidence of the preset machine learning model is acquired.
  • step S504 in response to the prediction confidence being less than the confidence threshold, it is judged whether there is a normal distribution model of the vehicle's driving aggressiveness coefficient in the preset algorithm model; wherein, the driving aggressiveness coefficient is the product of vehicle speed and acceleration.
  • the implementation process of the above step S501-step S504 may refer to the description of the implementation process of the above-mentioned step S301-step S304, which will not be repeated here.
  • step S505 in response to the fact that there is no normal distribution of the driving aggressiveness coefficient of the own vehicle, the normal distribution of the driving aggressiveness coefficient of the other vehicle is acquired.
  • the normal distribution of the driving aggressiveness coefficient of which is constructed based on the obtained historical driving data of all other vehicles, belongs to statistical data and conforms to the driving habits of most users, that is, it conforms to the acceleration preferences of most users.
  • the normal distribution of the driving aggressiveness coefficients of other vehicles is obtained in advance, and the normal distribution of the driving aggressiveness coefficients of a large number of users is obtained according to the acquired historical driving data of all other vehicles.
  • the specific acquisition process of the normal distribution is as follows:
  • the driving aggressiveness coefficient is the product of vehicle speed and acceleration
  • the abscissa of the normal distribution of the driving aggressiveness coefficient of other vehicles is the driving aggressiveness coefficient
  • the vertical axis is the frequency
  • step S506 based on the normal distribution of the driving aggressiveness coefficients of other vehicles, the target driving aggressiveness coefficient corresponding to the preset scene threshold is selected.
  • the driving aggressiveness coefficient that can cover 90% of the scenarios is selected, that is, the driving aggressiveness coefficient that meets the driving habits of most users is selected.
  • the driving aggressiveness coefficient of most of the user's driving habits is used as the target driving aggressiveness coefficient of the vehicle.
  • step S507 the target acceleration preference is acquired based on the target driving aggressiveness coefficient, the starting vehicle speed and the ending vehicle speed.
  • step S508 based on the target acceleration preference, the initial vehicle speed and the final vehicle speed are spliced to obtain a spliced vehicle speed curve.
  • the implementation process of the above step S508 may refer to the description of the implementation process of the above step S104, and details are not repeated here.
  • the vehicle speed splicing method of the embodiment of the present disclosure obtains a well-trained preset machine learning model based on the historical driving data of the vehicle.
  • the historical driving data is insufficient, that is, the prediction confidence of the preset machine learning model is not enough and the driving aggressiveness of the vehicle is not formed.
  • the normal distribution of the coefficient the normal distribution of the driving aggressiveness coefficient of other vehicles obtained from the historical driving data of a plurality of other vehicles is selected.
  • the driving aggressiveness coefficient covering most users is obtained, so as to obtain the user acceleration preference, and based on the user acceleration preference, the vehicle speed splicing of adjacent road sections can be obtained, and the predicted vehicle speed information that is more in line with the user's actual acceleration and deceleration behavior can be obtained.
  • Fig. 6 is a block diagram of a vehicle speed splicing device according to an embodiment of the present disclosure.
  • the vehicle speed splicing device may include: an average vehicle speed acquisition module 601 , a vehicle speed to be spliced acquisition module 602 , an acceleration preference acquisition module 603 and a vehicle speed splicing module 604 .
  • the average vehicle speed acquisition module 601 is configured to acquire the average vehicle speed of each road section included in the itinerary information according to the itinerary information;
  • the vehicle speed acquisition module 602 to be spliced is used to use the average vehicle speeds of two adjacent road sections as the initial vehicle speed and the terminal vehicle speed respectively;
  • An acceleration preference acquisition module 603, configured to acquire the target acceleration preference corresponding to the initial vehicle speed and the terminal vehicle speed based on a preset algorithm model;
  • the vehicle speed splicing module 604 is used for splicing the initial vehicle speed and the ending vehicle speed based on the target acceleration preference to obtain the spliced vehicle speed curve.
  • the vehicle speed splicing device of the embodiment of the present disclosure obtains the user's acceleration preference based on the vehicle's historical driving data, and performs splicing of vehicle speeds on adjacent road sections based on the user's acceleration preference, so as to obtain predicted vehicle speed information that is more in line with the user's actual acceleration and deceleration behavior.
  • the spliced vehicle speed information is applied to the energy consumption simulation model, so that the energy consumption simulation results are more in line with the actual vehicle energy consumption.
  • Fig. 7 is a block diagram of a vehicle speed splicing device according to another embodiment of the present disclosure.
  • the vehicle speed splicing device may include: an average vehicle speed acquisition module 701 , a vehicle speed to be spliced acquisition module 702 , an acceleration preference acquisition module 703 and a vehicle speed splicing module 704 .
  • the average vehicle speed acquisition module 701, the vehicle speed to be spliced acquisition module 702, the acceleration preference acquisition module 703, and the vehicle speed splicing module 704 in this embodiment are respectively connected with the average vehicle speed acquisition module 601, the vehicle speed to be spliced acquisition module 602, and the acceleration preference acquisition module.
  • the module 603 and the vehicle speed splicing module 604 have the same structure and function.
  • the preset algorithm model includes a preset machine learning model
  • the acceleration preference acquisition module 703 is specifically used for:
  • the initial vehicle speed and the terminal vehicle speed are input into the preset machine learning model to obtain the target acceleration preference.
  • the preset algorithm model includes a normal distribution model of the driving aggressiveness coefficient of the vehicle, and the acceleration preference acquisition module 703 is also used for:
  • the target acceleration preference is obtained.
  • the acceleration preference acquisition module 703 is further configured to:
  • the preset algorithm model includes a normal distribution model of the driving aggressiveness coefficient of the vehicle
  • the normal distribution model of the driving aggressiveness coefficient of the own vehicle is acquired.
  • the preset algorithm model includes a normal distribution model of driving aggressiveness coefficients of other vehicles, and the acceleration preference acquisition module 703 is also used for:
  • the target acceleration preference is obtained.
  • the acceleration preference acquisition module 703 is further configured to:
  • the normal distribution of the driving aggressiveness coefficients of other vehicles is obtained.
  • the vehicle speed splicing module 704 is specifically used for:
  • the initial vehicle speed and the end vehicle speed are spliced to obtain a vehicle speed curve.
  • the device further includes a model training module 705, the model training module 705 is specifically used for:
  • sample data is obtained based on the historical driving data of the vehicle; wherein, the sample data includes the initial acceleration speed, termination acceleration speed and acceleration of several acceleration sections;
  • the prediction confidence of the preset machine learning model is verified by the verification sample to obtain the prediction confidence of the preset machine learning model.
  • the device further includes a first radical coefficient acquisition module 706, the first radical coefficient acquisition module 706 is specifically used for:
  • the driving aggressiveness coefficient is the product of vehicle speed and acceleration
  • the abscissa of the normal distribution of the driving aggressiveness coefficient of the vehicle is the driving aggressiveness coefficient
  • the vertical axis is frequency.
  • the device further includes a second radical coefficient acquisition module 707, and the second radical coefficient acquisition module 707 is specifically used for:
  • the driving aggressiveness coefficient is the product of vehicle speed and acceleration
  • the abscissa of the normal distribution of the driving aggressiveness coefficient of other vehicles is the driving aggressiveness coefficient
  • the vertical axis is the frequency
  • the vehicle speed splicing device in the embodiment of the present disclosure obtains a trained preset machine learning model based on the vehicle's historical driving data, and obtains the user's acceleration preference through the preset machine learning model when the trained preset machine learning model is obtained.
  • the historical driving data is insufficient, that is, the prediction confidence of the preset machine learning model is not enough, or the normal distribution of the driving aggressiveness coefficient of the vehicle is not formed, or the normal distribution of the driving aggressiveness coefficient of the vehicle is not formed
  • the normal distribution of the driving aggressive coefficients of other vehicles obtained according to the historical driving data of multiple other vehicles is selected. According to the normal distribution, the driving aggressiveness coefficient satisfying the conditions is obtained, so as to obtain the user's acceleration preference.
  • the vehicle speed of adjacent road sections is spliced, and the predicted vehicle speed information that is more in line with the user's actual acceleration and deceleration behavior can be obtained.
  • the present disclosure also provides an electronic device and a readable storage medium.
  • FIG. 8 it is a block diagram of an electronic device for implementing a method for vehicle speed splicing according to an embodiment of the present disclosure.
  • Electronic device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers.
  • Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smart phones, wearable devices, and other similar computing devices.
  • the components shown herein, their connections and relationships, and their functions, are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.
  • the electronic device includes: one or more processors 801, a memory 802, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces.
  • the various components are interconnected using different buses and can be mounted on a common motherboard or otherwise as desired.
  • the processor may process instructions executed within the electronic device, including instructions stored in or on the memory to display graphical information of the GUI on an external input/output device such as a display device coupled to an interface.
  • multiple processors and/or multiple buses may be used with multiple memories and multiple memories, if desired.
  • multiple electronic devices may be connected, with each device providing some of the necessary operations (eg, as a server array, a set of blade servers, or a multi-processor system).
  • a processor 801 is taken as an example.
  • the memory 802 is a non-transitory computer-readable storage medium provided in the present disclosure.
  • the memory stores instructions executable by at least one processor, so that the at least one processor executes the vehicle speed stitching method provided in the present disclosure.
  • the non-transitory computer-readable storage medium of the present disclosure stores computer instructions, and the computer instructions are used to make the computer execute the method for splicing vehicle speeds provided in the present disclosure.
  • the memory 802 as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs and modules, such as program instructions/modules corresponding to the vehicle speed splicing method in the embodiment of the present disclosure (for example, 6 shows the average vehicle speed acquisition module 601, the vehicle speed to be spliced acquisition module 602, the acceleration preference acquisition module 603 and the vehicle speed splicing module 604).
  • the processor 801 executes various functions of the server by running non-transitory software programs, instructions and modules stored in the memory 802.
  • the memory 802 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application program required by a function; the data storage area may store data created according to the use of electronic devices spliced according to vehicle speed, etc.
  • the memory 802 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices.
  • the memory 802 may optionally include a memory that is remotely located relative to the processor 801, and these remote memories may be connected to the electronic equipment for vehicle speed splicing through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • the electronic equipment of the method for vehicle speed splicing may further include: an input device 803 and an output device 804 .
  • the processor 801, the memory 802, the input device 803, and the output device 804 may be connected through a bus or in other ways. In FIG. 8, connection through a bus is taken as an example.
  • the input device 803 can receive input numbers or character information, and generate key signal input related to the user settings and function control of the electronic equipment for vehicle speed splicing, such as touch screen, small keyboard, mouse, trackpad, touchpad, indicator stick, a Or multiple mouse buttons, trackballs, joysticks, and other input devices.
  • the output device 804 may include a display device, an auxiliary lighting device (for example, a light emitting diode (LED) and a tactile feedback device (for example, a vibration motor), etc.
  • the display device may include, but is not limited to, a liquid crystal display (LCD, Liquid Crystal Display,), light emitting diode (LED) display, and plasma display. In some embodiments, the display device can be a touch screen.
  • Various implementations of the systems and techniques described herein can be implemented in digital electronic circuitry, integrated circuit systems, application-specific ASICs (Application Specific Integrated Circuits), computer hardware, firmware, software, and/or combinations thereof accomplish. These various embodiments may include being implemented in one or more computer programs executable and/or interpreted on a programmable system including at least one programmable processor, the programmable processor Can be special-purpose or general-purpose programmable processor, can receive data and instruction from storage system, at least one input device, and at least one output device, and transmit data and instruction to this storage system, this at least one input device, and this at least one output device an output device.
  • machine-readable medium and “computer-readable medium” refer to any computer program product, apparatus, and/or means for providing machine instructions and/or data to a programmable processor ( For example, magnetic disks, optical disks, memories, programmable logic devices (PLDs), including machine-readable media that receive machine instructions as machine-readable signals.
  • machine-readable signal refers to any signal used to provide machine instructions and/or data to a programmable processor.
  • the systems and techniques described herein can be implemented on a computer having a display device (e.g., a CRT (Cathode Ray Tube) or LCD (liquid crystal display)) for displaying information to the user. monitor); and a keyboard and pointing device (eg, a mouse or trackball) through which a user can provide input to the computer.
  • a display device e.g., a CRT (Cathode Ray Tube) or LCD (liquid crystal display)
  • keyboard and pointing device eg, a mouse or trackball
  • Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and can be in any form (including Acoustic input, speech input or, tactile input) to receive input from the user.
  • the systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., as a a user computer having a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system.
  • the components of the system can be interconnected by any form or medium of digital data communication, eg, a communication network. Examples of communication networks include: Local Area Network (LAN, Local Area Network), Wide Area Network (WAN, Wide Area Network) and the Internet.
  • a computer system may include clients and servers.
  • Clients and servers are generally remote from each other and typically interact through a communication network.
  • the relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other.
  • a computer program product is also provided.
  • the electronic device can execute the above method.
  • a computer program is also provided, the computer program includes computer program code, and when the computer program code is run on a computer, it causes the computer to execute the above method.
  • the exemplary embodiments mentioned in the present disclosure describe some methods or systems based on a series of steps or devices.
  • the present disclosure is not limited to the order of the above steps, that is, the steps may be performed in the order mentioned in the embodiment, or may be different from the order in the embodiment, or several steps may be performed simultaneously.

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Human Computer Interaction (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
  • Electric Propulsion And Braking For Vehicles (AREA)

Abstract

提供了一种车速拼接方法和装置，其中方法包括：根据行程信息，获取各个路段的平均车速；将相邻两个路段的平均车速分别作为起始车速和终止车速；基于预设算法模型，获取起始车速和终止车速对应的目标加速度偏好；基于目标加速度偏好，对于起始车速和终止车速进行车速拼接，得到拼接后的车速曲线。

Description

车速拼接方法、装置、电子设备及存储介质
相关申请的交叉引用
本申请基于申请号为202111451340.2、申请日为2021年12月1日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本公开涉及车速预测技术领域，具体涉及一种车速拼接方法、装置、电子设备及存储介质。
背景技术
在车辆行驶过程中，为了预测车辆在未来行程中的能耗，需要得到车辆未来行程中的车速信息。未来行程包括多个路段，可以获取每个路段的平均车速，因为相邻路段的车速不同，因此，需要对相邻路段的车速进行拼接，得到整个行程的车速信息。
相关的基于车辆未来行程预测路段平均车速的拼接方法，大都采用固定加速度和减速度进行拼接，也有一些采用基于行车片段特征统计的车速拼接方法。上述方法忽略了不同驾驶员的加减速行为偏好，拼接出来的车速会因为驾驶员不同而导致实际车速与拼接车速，在加速度或减速度的行车阶段偏差较大。
发明内容
本公开提供了一种车速拼接方法、装置、电子设备及存储介质，以提高车速拼接的准确性。本公开的技术方案如下：
第一方面，本公开实施例提供了一种车速拼接方法，包括：
根据行程信息，获取所述行程信息中所包含的各个路段的平均车速；
将相邻两个路段的平均车速分别作为起始车速和终止车速；
基于预设算法模型，获取所述起始车速和终止车速对应的目标加速度偏好；
基于所述目标加速度偏好，对于所述起始车速和终止车速进行车速拼接，得到拼接后的车速曲线。
第二方面，本公开实施例提供了一种车速拼接装置，包括：
平均车速获取模块，用于根据行程信息，获取所述行程信息中所包含的各个路段的平均车速；
待拼接车速获取模块，用于将相邻两个路段的平均车速分别作为起始车速和终止车速；
加速偏好获取模块，用于基于预设算法模型，获取所述起始车速和终止车速对应的目标加速度偏好；
车速拼接模块，用于基于所述目标加速度偏好，对于所述起始车速和终止车速进行车速拼接，得到拼接后的车速曲线。
第三方面，本公开实施例提供了一种电子设备，包括：至少一个处理器；和与所述至少一个处理器通信连接的存储器；其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行本公开第一方面实施例所述的车速拼接方法。
第四方面，本公开实施例提供了一种存储有计算机指令的非瞬时计算机可读存储介质，所述计算机指令用于使所述计算机执行本公开第一方面实施例所述的车速拼接方法。
第五方面，本公开实施例提供了一种计算机程序产品，包括计算机指令，该计算机指令被处理器执行时实现本公开第一方面实施例所述的车速拼接方法。
第六方面，本公开实施例提供了一种计算机程序，所述计算机程序包括计算机程序代码，当所述计算机程序代码在计算机上运行时，使得计算机执行本公开第一方面实施例所述的车速拼接方法。
本公开实施例提供的技术方案至少带来以下有益效果：
基于用户加速度偏好，进行相邻路段的车速拼接，可得到更加符合用户实际加减速行为的预测车速信息。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本公开。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理，并不构成对本公开的不当限定。
图1是根据本公开一实施例示出的一种车速拼接方法的流程图。
图2是根据本公开一实施例示出的车速拼接效果图。
图3是根据本公开另一实施例示出的一种车速拼接方法的流程图。
图4是根据本公开又一实施例示出的一种车速拼接方法的流程图。
图5是根据本公开又一实施例示出的一种车速拼接方法的流程图。
图6是根据本公开一实施例示出的一种车速拼接装置的框图。
图7是根据本公开另一实施例示出的一种车速拼接装置的框图。
图8是根据本公开一实施例示出的一种电子设备的框图。
具体实施方式
为了使本领域普通人员更好地理解本公开的技术方案，下面将结合附图，对本公开实施例中的技术方案进行清楚、完整地描述。
需要说明的是，本公开中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本公开实施例能够以除了在这里图示或描述的那些以外的顺序实施。以下示例性实施例中所描述的实施方式并不代表与本公开相一致的所有实施方式。相反，它们仅是与 如所附权利要求书中所详述的、本公开的一些方面相一致的装置和方法的例子。
在本公开的描述中，术语“多个”指两个或两个以上。
驾驶激进系数，指的是车辆加速度a与车速v的乘积，即驾驶激进系数＝车辆加速度a*车速v。
车速拼接，指的是将车辆未来行程的平均车速进行拼接，以得到平滑车速曲线。
xgboost(eXtreme Gradient Boosting，极端梯度提升)算法，是一种非常有效的机器学习方法。
在某些应用领域，例如车辆的能耗预测方面，需要建立能耗仿真模型，用于根据未来行程的车速信息，预测能耗信息。为了能够更准确地预测能耗，需要预测更准确的车速信息。
相关的基于车辆未来行程预测路段平均车速的拼接方法，大都采用固定加速度和减速度进行拼接，也有一些采用基于行车片段特征统计的车速拼接方法。上述两种方法均忽略了不同驾驶员的加减速行为偏好，拼接出来的车速会因为驾驶员不同而导致实际车速与拼接车速，在加速度或减速度的行车阶段偏差较大。且基于行车片段特征统计的车速拼接方法，需要大量的路况行车信息，因此，很难工程化。
为了解决上述问题，本公开实施例提供了一种车速拼接方法、装置、电子设备及存储介质，为一种基于驾驶员实际驾车特性的车速拼接方法，以做到同一速度变化区间，因驾驶员不同而产生不同的车速拼接效果，更加符合当前驾驶员驾车行为，使车速拼接做到“千人千面”。
图1是根据本公开一个实施例的车速拼接方法的流程图。需要说明的是，本公开实施例的车速拼接方法可应用于本公开实施例的车速拼接装置。该车速拼接装置可被配置于电子设备上。如图1所示，该车速拼接方法可以包括如下步骤：S101-S104。
在步骤S101中，根据行程信息，获取所述行程信息中所包含的各个路段的平均车速。
在一些实施例中，利用现有的导航软件，例如高德导航、百度导航等，输入起点和终点，导航软件会返回未来行程一系列路段的路段信息，每个路段信息包括里程和耗时。例如，每个路段的里程为2公里，耗时2分钟。
为了实现两个相邻路段的车速拼接，需要先获取两个路段的平均车速。可以根据里程和耗时得到每个路段的平均车速。
在步骤S102中，将相邻两个路段的平均车速分别作为起始车速和终止车速。
可以理解，两个相邻路段的平均车速不同，车速拼接时，相当于加速路段。例如，从起始车速通过加速到终止车速。
需要说明的是，在本公开的实施例中，加速路段包括从低速到高速通过加速实现的路段，也包括从高速到低速通过减速实现的路段。也就是说，在本公开的实施例中，加速度可以为正数，也可以为负数，加速度为负数时，表征为减速。
将两个相邻路段的平均车速分别作为拼接车速的起始加速车速和终止加速车速。
在步骤S103中，基于预设算法模型，获取起始车速和终止车速对应的目标加速度偏好。
在本公开的实施例中，根据历史行车数据，得到用于计算目标加速度偏好的预设算法模型。其中，加速度偏好实际对应一个加速度值。
在一些实施例中，所述预设算法模型可以包括根据本车历史行车数据获取的预设机器学习模型、根据本车的历史行车数据得到的本车的驾驶激进系数的正态分布模型以及根据其他车辆的历史行车数据得到的其他车辆的驾驶激进系数的正态分布模型中的至少一种。其中，所述驾驶激进系数为车速与加速度的乘积。
预设算法模型是能够表达用户在不同的车速变化区间的加速度偏好的模型，该预设算法模型可以是机器学习模型，也可以是用户的历史驾驶习惯行程的驾驶激进系数的正太分布。当然在用户初始使用车辆的阶段，还没有行成用户自己预设算法模型之前，还可以使用其他车辆的驾驶激进系数行成的预设算法模型。
在步骤S104中，基于目标加速度偏好，对于起始车速和终止车速进行车速拼接，得到拼接后的车速曲线。
在获取到目标加速度偏好后，对起始车速和终止车速进行车速拼接。在一些实施例中，具体的车速拼接方法如下：
在一些实施例中，基于起始车速和终止车速以及加速度偏好，计算总加速距离S；
将总加速距离S分割为起始加速距离S/2和终止加速距离S/2；
根据起始加速距离S/2，计算起始加速位置；
根据终止加速距离S/2，计算终止加速位置；
基于起始加速位置、终止加速位置以及加速度偏好，对起始车速和终止车速进行车速拼接，得到车速曲线。
结合图2对起始车速和终止车速进行车速拼接的方法进行说明，如图2所示，起始车速V1和终止车速V2，加速度偏好a，通过公式S＝(V2*V2-V1*V1)/2a计算得到总加速距离S。再从起始车速V1和终止车速V2的分割位置，向起始车速V1所在路段方向移动S/2后，得到起始加速位置；向终止车速V2所在路段方向移动S/2后，得到终止加速位置。从起始加速位置按照加速度偏好a一直加速到终止加速位置，完成车速的拼接。
本公开实施例的车速拼接方法，基于车辆历史行车数据，得到用户加速度偏好，并基于用户加速度偏好进行相邻路段的车速拼接，可得到更加符合用户实际加减速行为的预测车速信息。将拼接后的车速信息应用于能耗仿真模型，使能耗仿真结果更加符合实际车辆能耗。
在本公开实施例中，将预设机器学习模型作为一种优先选择的获取目标加速度偏好的实现方式。图3是根据本公开另一个实施例的车速拼接方法的流程图。如图3所示，该车速拼接方法可以包括如下步骤：S201-S205。
在步骤S201中，根据行程信息，获取所述行程信息中所包含的各个路段的平均车速。
在步骤S202中，将相邻两个路段的平均车速分别作为起始车速和终止车速。
需要说明的是，在本公开的实施例中，上述步骤S201-步骤S202的实现过程可参见上述步骤S101-步骤S102的实现过程的描述，在此不再赘述。
在步骤S203中，获取预设机器学习模型的预测置信度。
在一些实施例中，预设机器学习模型可采用已有的机器学习算法，如xgboost，或者线性回归算法等，在此不做限制。
预设机器学习模型的输入为起始加速车速和终止加速车速，输出为加速度，即目标加速度偏好。
需要说明的是，预设机器学习模型是提前训练好的。该预设机器学习模型是通过本车的历史行车数据训练得到的，训练过程如下：
在一些实施例中，对于预设机器学习模型，基于本车的历史行车数据，获取样本数据；其中，样本数据包括若干加速路段的起始加速车速、终止加速车速和加速度；
将样本数据拆分为训练样本和验证样本；
通过训练样本对预设机器学习模型进行训练；
通过验证样本对预设机器学习模型的预测置信度进行验证，得到预设机器学习模型的预测置信度。
需要说明的是，预测置信度可以理解为预设机器学习模型的预测的准确度。
在一些实施例中，本车的历史行车数据存在1万个样本数据，将其中8千个样本数据作为训练样本，用于预设机器学习模型的训练。将2千个样本数据用于预设机器学习模型的验证。通过8千个训练样本对预设机器学习模型进行训练，训练完毕后，通过2千个验证样本进行预设机器学习模型的验证。例如，将2千个验证样本输入模型中，模型对1600个验证样本的输出是与实际的加速度数据是一致的，即验证结果是正确的，那么说明该模型的预测置信度为80％，即该模型的预测的准确度为80％。
需要说明的是，本车的历史行车数据越少，预测置信度越低。反过来说，样本数据越多，预测置信度高。当本车为新车没有历史行车数据时，或者，历史行车数据很少时，该预设机器学习模型的输出是不准确的，不能用的。但是，需要先根据该预设机器学习模型的预测置信度值判断，是否通过预设机器学习模型获取目标加速度偏好，如果预测置信度不够，在选择其他的方式获取目标加速度偏好。
综上所述，在预设机器学习模型的预测置信度未达到预设的置信度阈值的情况下，预设机器学习模型得到的目标加速度偏好是不准确的，不能采用。因此，在采用预设机器学习模型获取目标加速度偏好时，要先判断预测置信度是否达到置信度阈值。
在步骤S204中，响应于预测置信度大于或等于置信度阈值，将起始车速和终止车速输入预设机器学习模型，获取目标加速度偏好。
将获取的预设机器学习模型的预测置信度与置信度阈值进行比较，在预测置信度大于或等于置信度阈值的情况下，将起始车速和终止车速输入预设机器学习模型，获取目标加速度偏好。
在一些实施例中，置信度阈值选择80％。
在一些实施例中，起始车速为30km/h，终止车速为50km/h，输入预设机器学习模型后，预设机器学习模型输出的一个加速度值如2m/s2。
在步骤S205中，基于目标加速度偏好，对于起始车速和终止车速进行车速拼接，得到拼接后的车速曲线。
需要说明的是，在本公开的实施例中，上述步骤S205的实现过程可参见上述步骤S104的实现过程的描述，在此不再赘述。
本公开实施例的车速拼接方法，基于车辆历史行车数据，得到训练好的预设机器学习模型。通过预设机器学习模型得到用户加速度偏好，并基于用户加速度偏好进行相邻路段的车速拼接，可得到更加符合用户实际加减速行为的预测车速信息。
在上述实施例的基础上，针对预测置信度小于置信度阈值的情况，采用本车的驾驶激进系数获取目标加速度偏好。图4是根据本公开又一个实施例的车速拼接方法的流程图。如图4所示，该车速拼接方法可以包括如下步骤：S301-S305。
在步骤S301中，根据行程信息，获取所述行程信息中所包含的各个路段的平均车速。
在步骤S302中，将相邻两个路段的平均车速分别作为起始车速和终止车速。
需要说明的是，在本公开的实施例中，上述步骤S301-步骤S302的实现过程可参见上述步骤S101-步骤S102的实现过程的描述，在此不再赘述。
在步骤S303中，基于所述本车的驾驶激进系数的正态分布模型，选择预设场景阈值对应的目标驾驶激进系数。
其中，驾驶激进系数为车速与加速度的乘积。
可以理解，将获取的预设机器学习模型的预测置信度与置信度阈值进行比较，在预测置信度小于置信度阈值的情况下，说明预设机器学习模型的准确度不够，选择其他的方式获取目标加速度偏好。本公开实施例选择基于本车的驾驶激进系数的正态分布，来获取目标加速度偏好。因此，首先需要判断该预设算法模型中是否存在本车的驾驶激进系数的正态分布模型。
需要说明的是，本车的驾驶激进系数的正态分布是根据本车的历史行车数据提前获取的。获取方法如下：
基于本车的历史行车数据，构建本车的驾驶激进系数的正态分布，其中，驾驶激进系数为车速与加速度的乘积，本车的驾驶激进系数的正态分布的横坐标为驾驶激进系数，纵坐标为频次数。
在存在本车的驾驶激进系数的正态分布模型的情况下，则根据本车的驾驶激进系数的正态分布，选择预设场景阈值对应的目标驾驶激进系数。
预设场景阈值根据正态分布的面积确定，面积越大，表示覆盖该用户场景范围越大。
在一些实施例中，依据正态分布的结果，选择能涵盖该用户90％场景的驾驶激进系数。
在步骤S304中，基于目标驾驶激进系数以及起始车速和终止车速，获取目标加速度偏好。
本公开实施例中的驾驶激进系数为车速与加速度的乘积，基于目标驾驶激进系数以及起始车速和终止车速，获取目标加速度偏好的方法如下：
在一些实施例中，计算起始车速和终止车速的平均值；
将目标驾驶激进系数与平均值的商作为目标加速度偏好。
在本公开实施例中，通过起始车速和终止车速的中间值，结合目标驾驶激进系数，得到的加速度偏好会更佳准确。
在步骤S305中，基于目标加速度偏好，对于起始车速和终止车速进行车速拼接，得到拼接后的车速曲线。
需要说明的是，在本公开的实施例中，上述步骤S305的实现过程可参见上述步骤S104的实现过程的描述，在此不再赘述。
本公开实施例的车速拼接方法，基于车辆历史行车数据，得到训练好的预设机器学习模型，在历史行车数据不足，即预设机器学习模型的预测置信度不够的情况下，选择通过历史行车数据得到的本车的驾驶激进系数的正态分布。根据该正态分布得到涵盖该用户大部分场景的驾驶激进系数，从而获取用户加速度偏好，并基于用户加速度偏好进行相邻路段的车速拼接，可得到更加符合用户实际加减速行为的预测车速信息。
在本车没有历史行车数据或者只有少量历史行车数据的情况下，即还没有足够的样本数据训练得到预设机器学习模型，或者预设机器学习模型的预测置信度小于置信度阈值的情况下。且本车的历史行车数据也不足以构建本车的驾驶激进系数的正态分布模型的情况下，只能选择其他车辆的驾驶激进系数的正态分布模型来获取目标加速度偏好。图5是根据本公开又一个实施例的车速拼接方法的流程图。如图5所示，该车速拼接方法可以包括如下步骤：S501-S508。
在步骤S501中，根据行程信息，获取所述行程信息中所包含的各个路段的平均车速。
在步骤S502中，将相邻两个路段的平均车速分别作为起始车速和终止车速。
在步骤S503中，获取预设机器学习模型的预测置信度。
在步骤S504中，响应于预测置信度小于置信度阈值，判断所述预设算法模型中是否存在本车的驾驶激进系数的正态分布模型；其中，驾驶激进系数为车速与加速度的乘积。
需要说明的是，在本公开的实施例中，上述步骤S501-步骤S504的实现过程可参见上述步骤S301-步骤S304的实现过程的描述，在此不再赘述。
在步骤S505中，响应于不存在本车的驾驶激进系数的正态分布，获取其他车辆的驾驶激进系数的正态分布。
在本车没有历史行车数据，或者历史行车数据很少，导致预设机器学习模型的预测置信度小于置信度阈值，且还不足及构成本车的驾驶激进系数的正态分布时，选择其他车辆的驾驶激进系数的正态分布，该正态分布是根据获取到的其他所有车辆的历史行车数据构建的，属于统计数据，符合大部分用户的行车习惯，即符合大部分用户的加速度偏好。
需要说明的是，其他车辆的驾驶激进系数的正态分布是提前获取到的，根据获取的所有其他车辆的历史行车数据，得到大量用户的驾驶激进系数的正态分布。在一些实施例中，该正太分布的具体获取过程如下：
基于其他多个车辆的历史行车数据，构建其他车辆的驾驶激进系数的正态分布，其中，驾驶激进系数为车速与加速度的乘积，其他车辆的驾驶激进系数的正态分布的横坐标为驾 驶激进系数，纵坐标为频次数。
在步骤S506中，基于其他车辆的驾驶激进系数的正态分布，选择预设场景阈值对应的目标驾驶激进系数。
在一些实施例中，依据其他车辆的驾驶激进系数的正态分布的结果，选择能涵盖90％场景的驾驶激进系数，即选择符合大部分用户驾驶习惯的驾驶激进系数。将该大部分用户驾驶习惯的驾驶激进系数作为本车的目标驾驶激进系数。
在步骤S507中，基于目标驾驶激进系数以及起始车速和终止车速，获取目标加速度偏好。
需要说明的是，在本公开的实施例中，上述步骤S507的实现过程可参见上述步骤S306的实现过程的描述，在此不再赘述。
在步骤S508中，基于目标加速度偏好，对于起始车速和终止车速进行车速拼接，得到拼接后的车速曲线。
需要说明的是，在本公开的实施例中，上述步骤S508的实现过程可参见上述步骤S104的实现过程的描述，在此不再赘述。
本公开实施例的车速拼接方法，基于车辆历史行车数据，得到训练好的预设机器学习模型，在历史行车数据不足，即预设机器学习模型的预测置信度不够且未形成本车的驾驶激进系数的正态分布的情况下，选择根据多个其他车辆的历史行车数据得到的其他车辆的驾驶激进系数的正态分布。根据该正态分布得到涵盖大部分用户的驾驶激进系数，从而获取用户加速度偏好，并基于用户加速度偏好进行相邻路段的车速拼接，可得到更加符合用户实际加减速行为的预测车速信息。
图6是根据本公开一实施例示出的一种车速拼接装置的框图。参照图6，该车速拼接装置可以包括：平均车速获取模块601、待拼接车速获取模块602、加速偏好获取模块603和车速拼接模块604。
具体地，平均车速获取模块601，用于根据行程信息，获取所述行程信息中所包含的各个路段的平均车速；
待拼接车速获取模块602，用于将相邻两个路段的平均车速分别作为起始车速和终止车速；
加速偏好获取模块603，用于基于预设算法模型，获取所述起始车速和终止车速对应的目标加速度偏好；
车速拼接模块604，用于基于目标加速度偏好，对于起始车速和终止车速进行车速拼接，得到拼接后的车速曲线。
本公开实施例的车速拼接装置，基于车辆历史行车数据，得到用户加速度偏好，并基于用户加速度偏好进行相邻路段的车速拼接，可得到更加符合用户实际加减速行为的预测车速信息。将拼接后的车速信息应用于能耗仿真模型，使能耗仿真结果更加符合实际车辆能耗。
图7是根据本公开另一实施例示出的车速拼接装置的框图。参照图7，该车速拼接装 置可以包括：平均车速获取模块701、待拼接车速获取模块702、加速偏好获取模块703和车速拼接模块704。
需要说明的是，本实施例的平均车速获取模块701、待拼接车速获取模块702、加速偏好获取模块703和车速拼接模块704分别与平均车速获取模块601、待拼接车速获取模块602、加速偏好获取模块603和车速拼接模块604，具体相同的结构和功能。
在本公开的一些实施例中，该预设算法模型包括预设机器学习模型，加速偏好获取模块703，具体用于：
将所述起始车速和终止车速输入所述预设机器学习模型，获取所述目标加速度偏好。
在本公开的一些实施例中，预设算法模型包括本车的驾驶激进系数的正态分布模型，加速偏好获取模块703，还用于：
基于本车的驾驶激进系数的正态分布，选择预设场景阈值对应的目标驾驶激进系数；
基于目标驾驶激进系数以及起始车速和终止车速，获取目标加速度偏好。
在本公开的一些实施例中，加速偏好获取模块703在基于所述本车的驾驶激进系数的正态分布模型，选择预设场景阈值对应的目标驾驶激进系数之前，还用于：
获取预设机器学习模型的预测置信度；
响应于所述预测置信度小于所述置信度阈值，判断所述预设算法模型中是否包括本车的驾驶激进系数的正态分布模型；
响应于所述预设算法模型中包括本车的驾驶激进系数的正态分布模型，获取所述本车的驾驶激进系数的正态分布模型。
在本公开的一些实施例中，预设算法模型包括其他车辆的驾驶激进系数的正态分布模型，加速偏好获取模块703，还用于：
基于其他车辆的驾驶激进系数的正态分布，选择预设场景阈值对应的目标驾驶激进系数；
基于目标驾驶激进系数以及起始车速和终止车速，获取目标加速度偏好。
在本公开的一些实施例中，加速偏好获取模块703在基于所述其他车辆的驾驶激进系数的正态分布，选择预设场景阈值对应的目标驾驶激进系数之前，还用于：
响应于所述预设算法模型中不包括本车的驾驶激进系数的正态分布模型，获取其他车辆的驾驶激进系数的正态分布。
在本公开的一些实施例中，车速拼接模块704，具体用于：
基于所述起始车速和终止车速以及所述加速度偏好，计算总加速距离S；
将所述总加速距离S分割为起始加速距离S/2和终止加速距离S/2；
根据所述起始加速距离S/2，计算起始加速位置；
根据所述终止加速距离S/2，计算终止加速位置；
基于起始加速位置和终止加速位置以及加速度偏好，对所述起始车速和终止车速进行车速拼接，得到车速曲线。
在本公开的一些实施例中，装置还包括模型训练模块705，模型训练模块705，具体用 于：
对于预设机器学习模型，基于本车的历史行车数据，获取样本数据；其中，样本数据包括若干加速路段的起始加速车速、终止加速车速和加速度；
将样本数据拆分为训练样本和验证样本；
通过训练样本对预设机器学习模型进行训练；
通过验证样本对预设机器学习模型的预测置信度进行验证，得到预设机器学习模型的预测置信度。
在本公开的一些实施例中，该装置还包括第一激进系数获取模块706，第一激进系数获取模块706，具体用于：
基于本车的历史行车数据，构建本车的驾驶激进系数的正态分布，其中，驾驶激进系数为车速与加速度的乘积，本车的驾驶激进系数的正态分布的横坐标为驾驶激进系数，纵坐标为频次数。
在本公开的一些实施例中，该装置还包括第二激进系数获取模块707，第二激进系数获取模块707，具体用于：
基于其他多个车辆的历史行车数据，构建其他车辆的驾驶激进系数的正态分布，其中，驾驶激进系数为车速与加速度的乘积，其他车辆的驾驶激进系数的正态分布的横坐标为驾驶激进系数，纵坐标为频次数。
关于上述实施例中的装置，其中各个模块执行操作的具体方式已经在有关该方法的实施例中进行了详细描述，此处将不做详细阐述说明。
本公开实施例的车速拼接装置，基于车辆历史行车数据，得到训练好的预设机器学习模型，在得到训练好的预设机器学习模型的情况下，通过预设机器学习模型得到用户加速度偏好。在历史行车数据不足，即预设机器学习模型的预测置信度不够的情况下，或者本车的驾驶激进系数的正态分布，或者在本车的驾驶激进系数的正态分布也未形成的情况下，选择根据多个其他车辆的历史行车数据得到的其他车辆的驾驶激进系数的正态分布。根据该正态分布得到满足条件的驾驶激进系数，从而获取用户加速度偏好。最后基于用户加速度偏好进行相邻路段的车速拼接，可得到更加符合用户实际加减速行为的预测车速信息。
根据本公开的实施例，本公开还提供了一种电子设备和一种可读存储介质。
如图8所示，是根据本公开实施例的用于实现车速拼接的方法的电子设备的框图。电子设备旨在表示各种形式的数字计算机，诸如，膝上型计算机、台式计算机、工作台、个人数字助理、服务器、刀片式服务器、大型计算机、和其它适合的计算机。电子设备还可以表示各种形式的移动装置，诸如，个人数字处理、蜂窝电话、智能电话、可穿戴设备和其它类似的计算装置。本文所示的部件、它们的连接和关系、以及它们的功能仅仅作为示例，并且不意在限制本文中描述的和/或者要求的本公开的实现。
如图8所示，该电子设备包括：一个或多个处理器801、存储器802，以及用于连接各部件的接口，包括高速接口和低速接口。各个部件利用不同的总线互相连接，并且可以被安装在公共主板上或者根据需要以其它方式安装。处理器可以对在电子设备内执行的指令 进行处理，包括存储在存储器中或者存储器上以在外部输入/输出装置(诸如，耦合至接口的显示设备)上显示GUI的图形信息的指令。在其它实施方式中，若需要，可以将多个处理器和/或多条总线与多个存储器和多个存储器一起使用。同样，可以连接多个电子设备，各个设备提供部分必要的操作(例如，作为服务器阵列、一组刀片式服务器、或者多处理器系统)。图8中以一个处理器801为例。
存储器802即为本公开所提供的非瞬时计算机可读存储介质。其中，所述存储器存储有可由至少一个处理器执行的指令，以使所述至少一个处理器执行本公开所提供的车速拼接的方法。本公开的非瞬时计算机可读存储介质存储计算机指令，该计算机指令用于使计算机执行本公开所提供的车速拼接的方法。
存储器802作为一种非瞬时计算机可读存储介质，可用于存储非瞬时软件程序、非瞬时计算机可执行程序以及模块，如本公开实施例中的车速拼接的方法对应的程序指令/模块(例如，附图6所示的平均车速获取模块601、待拼接车速获取模块602、加速偏好获取模块603和车速拼接模块604)。处理器801通过运行存储在存储器802中的非瞬时软件程序、指令以及模块，从而执行服务器的各种功
存储器802可以包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需要的应用程序；存储数据区可存储根据车速拼接的电子设备的使用所创建的数据等。此外，存储器802可以包括高速随机存取存储器，还可以包括非瞬时存储器，例如至少一个磁盘存储器件、闪存器件、或其他非瞬时固态存储器件。在一些实施例中，存储器802可选包括相对于处理器801远程设置的存储器，这些远程存储器可以通过网络连接至车速拼接的电子设备。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
车速拼接的方法的电子设备还可以包括：输入装置803和输出装置804。处理器801、存储器802、输入装置803和输出装置804可以通过总线或者其他方式连接，图8中以通过总线连接为例。
输入装置803可接收输入的数字或字符信息，以及产生与车速拼接的电子设备的用户设置以及功能控制有关的键信号输入，例如触摸屏、小键盘、鼠标、轨迹板、触摸板、指示杆、一个或者多个鼠标按钮、轨迹球、操纵杆等输入装置。输出装置804可以包括显示设备、辅助照明装置(例如，发光二极管LED(light emitting diode)和触觉反馈装置(例如，振动电机)等。该显示设备可以包括但不限于，液晶显示器(LCD，Liquid Crystal Display，)、发光二极管(LED)显示器和等离子体显示器。在一些实施方式中，显示设备可以是触摸屏。
此处描述的系统和技术的各种实施方式可以在数字电子电路系统、集成电路系统、专用ASIC(Application Specific Integrated Circuit，专用集成电路)、计算机硬件、固件、软件、和/或它们的组合中实现。这些各种实施方式可以包括：实施在一个或者多个计算机程序中，该一个或者多个计算机程序可在包括至少一个可编程处理器的可编程系统上执行和/或解释，该可编程处理器可以是专用或者通用可编程处理器，可以从存储系统、至少一个 输入装置、和至少一个输出装置接收数据和指令，并且将数据和指令传输至该存储系统、该至少一个输入装置、和该至少一个输出装置。
这些计算程序(也称作程序、软件、软件应用、或者代码)包括可编程处理器的机器指令，并且可以利用高级过程和/或面向对象的编程语言、和/或汇编/机器语言来实施这些计算程序。如本文使用的，术语“机器可读介质”和“计算机可读介质”指的是用于将机器指令和/或数据提供给可编程处理器的任何计算机程序产品、设备、和/或装置(例如，磁盘、光盘、存储器、可编程逻辑装置(programmable logic device，PLD))，包括，接收作为机器可读信号的机器指令的机器可读介质。术语“机器可读信号”指的是用于将机器指令和/或数据提供给可编程处理器的任何信号。
为了提供与用户的交互，可以在计算机上实施此处描述的系统和技术，该计算机具有：用于向用户显示信息的显示装置(例如，CRT(Cathode Ray Tube，阴极射线管)或者LCD(液晶显示器)监视器)；以及键盘和指向装置(例如，鼠标或者轨迹球)，用户可以通过该键盘和该指向装置来将输入提供给计算机。其它种类的装置还可以用于提供与用户的交互；例如，提供给用户的反馈可以是任何形式的传感反馈(例如，视觉反馈、听觉反馈、或者触觉反馈)；并且可以用任何形式(包括声输入、语音输入或者、触觉输入)来接收来自用户的输入。
可以将此处描述的系统和技术实施在包括后台部件的计算系统(例如，作为数据服务器)、或者包括中间件部件的计算系统(例如，应用服务器)、或者包括前端部件的计算系统(例如，具有图形用户界面或者网络浏览器的用户计算机，用户可以通过该图形用户界面或者该网络浏览器来与此处描述的系统和技术的实施方式交互)、或者包括这种后台部件、中间件部件、或者前端部件的任何组合的计算系统中。可以通过任何形式或者介质的数字数据通信(例如，通信网络)来将系统的部件相互连接。通信网络的示例包括：局域网(LAN，Local Area Network)、广域网(WAN，Wide Area Network)和互联网。
计算机系统可以包括客户端和服务器。客户端和服务器一般远离彼此并且通常通过通信网络进行交互。通过在相应的计算机上运行并且彼此具有客户端-服务器关系的计算机程序来产生客户端和服务器的关系。
在本公开实施例中，还提供了一种计算机程序产品，当计算机程序产品中的指令由电子设备的处理器执行时，使得电子设备能够执行上述方法。
在本公开实施例中，还提供了一种计算机程序，该计算机程序包括计算机程序代码，当该计算机程序代码在计算机上运行时，使得计算机执行上述方法。
需要说明的是，前述对车速拼接方法的实施例的解释说明也适用于本公开实施例的车速拼接装置、非临时性计算机可读存储介质、电子设备、计算机程序产品和计算机程序，此处不再赘述。
还需要说明的是，本公开中提及的示例性实施例，基于一系列的步骤或者装置描述一些方法或系统。但是，本公开不局限于上述步骤的顺序，也就是说，可以按照实施例中提及的顺序执行步骤，也可以不同于实施例中的顺序，或者若干步骤同时执行。
本领域技术人员在考虑说明书及实践这里公开的实施方案后，将容易想到本公开的其它实施方案。本公开旨在涵盖本公开的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本公开的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的。
应当理解的是，本公开并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。本公开的范围仅由所附的权利要求来限制。
本公开所有实施例均可以单独被执行，也可以与其他实施例相结合被执行，均视为本公开要求的保护范围。

Claims (13)

  1. 一种车速拼接方法，包括：
    根据行程信息，获取所述行程信息中所包含的各个路段的平均车速；
    将相邻两个路段的平均车速分别作为起始车速和终止车速；
    基于预设算法模型，获取所述起始车速和终止车速对应的目标加速度偏好；
    基于所述目标加速度偏好，对于所述起始车速和终止车速进行车速拼接，得到拼接后的车速曲线。
  2. 根据权利要求1所述的方法，其中，所述预设算法模型包括预设机器学习模型，所述基于预设算法模型，获取所述起始车速和终止车速对应的目标加速度偏好，包括：
    将所述起始车速和终止车速输入所述预设机器学习模型，获取所述目标加速度偏好。
  3. 根据权利要求1所述的方法，其中，所述预设算法模型包括本车的驾驶激进系数的正态分布模型，所述基于预设算法模型，获取所述起始车速和终止车速对应的目标加速度偏好，包括：
    基于所述本车的驾驶激进系数的正态分布模型，选择预设场景阈值对应的目标驾驶激进系数；其中，所述驾驶激进系数为车速与加速度的乘积；
    基于所述目标驾驶激进系数以及所述起始车速和终止车速，获取所述目标加速度偏好。
  4. 根据权利要求3所述的方法，其中，所述基于所述本车的驾驶激进系数的正态分布模型，选择预设场景阈值对应的目标驾驶激进系数之前，还包括：
    获取预设机器学习模型的预测置信度；
    响应于所述预测置信度小于所述置信度阈值，判断所述预设算法模型中是否包括本车的驾驶激进系数的正态分布模型；
    响应于所述预设算法模型中包括本车的驾驶激进系数的正态分布模型，获取所述本车的驾驶激进系数的正态分布模型。
  5. 根据权利要求1所述的方法，其中，所述预设算法模型包括其他车辆的驾驶激进系数的正态分布模型，所述基于预设算法模型，获取所述起始车速和终止车速对应的目标加速度偏好，包括：
    基于所述其他车辆的驾驶激进系数的正态分布，选择预设场景阈值对应的目标驾驶激进系数；其中，所述驾驶激进系数为车速与加速度的乘积；
    基于所述目标驾驶激进系数以及所述起始车速和终止车速，获取所述目标加速度偏好。
  6. 根据权利要求5所述的方法，其中，所述基于所述其他车辆的驾驶激进系数的正态分布，选择预设场景阈值对应的目标驾驶激进系数之前，还包括：
    响应于所述预设算法模型中不包括本车的驾驶激进系数的正态分布模型，获取其他车辆的驾驶激进系数的正态分布。
  7. 根据权利要求1至6中任一项所述的方法，其中，所述基于所述加速度偏好，对于所述起始车速和终止车速进行车速拼接，得到车速曲线，包括：
    基于所述起始车速和终止车速以及所述加速度偏好，计算总加速距离S；
    将所述总加速距离S分割为起始加速距离S/2和终止加速距离S/2；
    根据所述起始加速距离S/2，计算起始加速位置；
    根据所述终止加速距离S/2，计算终止加速位置；
    基于所述起始加速位置和所述终止加速位置以及所述加速度偏好，对所述起始车速和终止车速进行车速拼接，得到车速曲线。
  8. 根据权利要求3或4所述的方法，还包括：
    基于本车的历史行车数据，构建本车的驾驶激进系数的正态分布，其中，所述驾驶激进系数为车速与加速度的乘积，所述本车的驾驶激进系数的正态分布模型的横坐标为驾驶激进系数，纵坐标为频次数。
  9. 一种车速拼接装置，包括：
    平均车速获取模块，用于根据行程信息，获取所述行程信息中所包含的各个路段的平均车速；
    待拼接车速获取模块，用于将相邻两个路段的平均车速分别作为起始车速和终止车速；
    加速偏好获取模块，用于基于预设算法模型，获取所述起始车速和终止车速对应的目标加速度偏好；
    车速拼接模块，用于基于所述目标加速度偏好，对于所述起始车速和终止车速进行车速拼接，得到拼接后的车速曲线。
  10. 一种电子设备，包括：
    至少一个处理器；和
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行权利要求1至8中任一项所述的车速拼接方法。
  11. 一种存储有计算机指令的非瞬时计算机可读存储介质，其中，所述计算机指令用于使所述计算机执行权利要求1至8中任一项所述的车速拼接方法。
  12. 一种计算机程序产品，包括计算机程序，所述计算机程序在被处理器执行时实现根据权利要求1-8中任一项所述的车速拼接方法。
  13. 一种计算机程序，所述计算机程序包括计算机程序代码，当所述计算机程序代码在计算机上运行时，使得计算机执行根据权利要求1-8中任一项所述的车速拼接方法。
PCT/CN2022/135975 2021-12-01 2022-12-01 车速拼接方法、装置、电子设备及存储介质 WO2023098828A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111451340.2A CN116198516A (zh) 2021-12-01 2021-12-01 车速拼接方法、装置、电子设备及存储介质
CN202111451340.2 2021-12-01

Publications (1)

Publication Number Publication Date
WO2023098828A1 true WO2023098828A1 (zh) 2023-06-08

Family

ID=86511772

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/135975 WO2023098828A1 (zh) 2021-12-01 2022-12-01 车速拼接方法、装置、电子设备及存储介质

Country Status (2)

Country Link
CN (1) CN116198516A (zh)
WO (1) WO2023098828A1 (zh)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102837703A (zh) * 2011-06-22 2012-12-26 沃尔沃汽车公司 估算车辆速度曲线的方法和系统及包括该系统的机动车辆
DE102013222748A1 (de) * 2013-06-28 2015-01-15 Hyundai Motor Company Antriebssteuerungsverfahren für ein Hybridfahrzeug
CN108828939A (zh) * 2018-05-31 2018-11-16 重庆大学 一种考虑驾驶员操作特性的车速引导方法
CN109733248A (zh) * 2019-01-09 2019-05-10 吉林大学 基于路径信息的纯电动汽车剩余里程模型预测方法
CN110126841A (zh) * 2019-05-09 2019-08-16 吉林大学 基于道路信息和驾驶风格的纯电动汽车能耗模型预测方法
CN112009499A (zh) * 2020-09-14 2020-12-01 北京罗克维尔斯科技有限公司 一种车辆自动驾驶控制方法及装置
CN112498366A (zh) * 2020-11-20 2021-03-16 苏州智加科技有限公司 自动驾驶车辆、控制方法、装置、设备及存储介质
CN113053135A (zh) * 2019-12-26 2021-06-29 郑州宇通客车股份有限公司 一种全局车速预测方法与装置
CN113561993A (zh) * 2021-08-13 2021-10-29 苏州智加科技有限公司 车速规划方法、装置及电子设备

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102837703A (zh) * 2011-06-22 2012-12-26 沃尔沃汽车公司 估算车辆速度曲线的方法和系统及包括该系统的机动车辆
DE102013222748A1 (de) * 2013-06-28 2015-01-15 Hyundai Motor Company Antriebssteuerungsverfahren für ein Hybridfahrzeug
CN108828939A (zh) * 2018-05-31 2018-11-16 重庆大学 一种考虑驾驶员操作特性的车速引导方法
CN109733248A (zh) * 2019-01-09 2019-05-10 吉林大学 基于路径信息的纯电动汽车剩余里程模型预测方法
CN110126841A (zh) * 2019-05-09 2019-08-16 吉林大学 基于道路信息和驾驶风格的纯电动汽车能耗模型预测方法
CN113053135A (zh) * 2019-12-26 2021-06-29 郑州宇通客车股份有限公司 一种全局车速预测方法与装置
CN112009499A (zh) * 2020-09-14 2020-12-01 北京罗克维尔斯科技有限公司 一种车辆自动驾驶控制方法及装置
CN112498366A (zh) * 2020-11-20 2021-03-16 苏州智加科技有限公司 自动驾驶车辆、控制方法、装置、设备及存储介质
CN113561993A (zh) * 2021-08-13 2021-10-29 苏州智加科技有限公司 车速规划方法、装置及电子设备

Also Published As

Publication number Publication date
CN116198516A (zh) 2023-06-02

Similar Documents

Publication Publication Date Title
US10713491B2 (en) Object detection using spatio-temporal feature maps
KR102487336B1 (ko) 자율주행시스템 테스트 방법, 장치 및 기록 매체
CN107369443B (zh) 基于人工智能的对话管理方法及装置
CN113408141B (zh) 一种自动驾驶测试方法、装置及电子设备
US20210323552A1 (en) Method, device, and medium for training longitudinal dynamics model
JP2022017446A (ja) 自動運転車両の道路テスト方法、装置、機器及び記憶媒体
EP3944211A2 (en) Traffic data analysis method and apparatus, electronic device, vehicle, storage medium and program product
US11151870B2 (en) Traffic scheme control method and device
EP3475890A1 (en) Reward augmented model training
US11443621B2 (en) Method and apparatus for adjusting channelization of traffic intersection
EP4047582A2 (en) Method and apparatus of generating control signal for traffic light, electronic device, and medium
CN111241838B (zh) 文本实体的语义关系处理方法、装置及设备
CN111986490A (zh) 路况预测方法、装置、电子设备和存储介质
US20220244060A1 (en) Method and apparatus for generating route information, device, medium and product
CN114444718B (zh) 机器学习模型的训练方法、信号控制方法和装置
CN110909136B (zh) 满意度预估模型的训练方法、装置、电子设备及存储介质
US20220204000A1 (en) Method for determining automatic driving feature, apparatus, device, medium and program product
WO2023098828A1 (zh) 车速拼接方法、装置、电子设备及存储介质
CN115687764B (zh) 车辆轨迹评估模型的训练方法、车辆轨迹评估方法和装置
CN111553043A (zh) 交通指标计算模型测试方法、交通仿真方法和装置
CN114970949B (zh) 行驶速度预测方法、装置、电子设备及存储介质
JP7372377B2 (ja) 道路情報確定方法及び装置、電子機器、記憶媒体並びにコンピュータプログラム
US20230211776A1 (en) Method for determining attribute value of obstacle in vehicle infrastructure cooperation, device and autonomous driving vehicle
CN116740962A (zh) 交通灯控制方法、无人车导航方法、模型训练方法、装置
CN117116075A (zh) 车辆控制方法、装置、电子设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22900632

Country of ref document: EP

Kind code of ref document: A1