WO2019047650A1 - 无人驾驶车辆的数据采集方法和装置 - Google Patents

无人驾驶车辆的数据采集方法和装置 Download PDF

Info

Publication number
WO2019047650A1
WO2019047650A1 PCT/CN2018/098983 CN2018098983W WO2019047650A1 WO 2019047650 A1 WO2019047650 A1 WO 2019047650A1 CN 2018098983 W CN2018098983 W CN 2018098983W WO 2019047650 A1 WO2019047650 A1 WO 2019047650A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
data
unmanned vehicle
driverless
preset
Prior art date
Application number
PCT/CN2018/098983
Other languages
English (en)
French (fr)
Inventor
郁浩
闫泳杉
郑超
唐坤
张云飞
姜雨
Original Assignee
百度在线网络技术（北京）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 百度在线网络技术（北京）有限公司 filed Critical 百度在线网络技术（北京）有限公司
Publication of WO2019047650A1 publication Critical patent/WO2019047650A1/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
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/005—Handover processes
    • B60W60/0053—Handover processes from vehicle to occupant
    • B60W60/0054—Selection of occupant to assume driving tasks
    • 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
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
    • 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
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
    • B60W30/18—Propelling the vehicle
    • 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
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/02—Control of position or course in two dimensions

Definitions

  • the present application relates to the field of computer technology, and in particular to the technical field of driverless vehicles, and more particularly to a data acquisition method and apparatus for an unmanned vehicle.
  • the driverless vehicle is a new type of intelligent car. It mainly performs precise control and calculation analysis on various parts of the vehicle through vehicular terminal equipment such as ECU (Electronic Control Unit) to realize the fully automatic operation of the vehicle.
  • vehicular terminal equipment such as ECU (Electronic Control Unit) to realize the fully automatic operation of the vehicle.
  • the purpose of the vehicle being unmanned.
  • the vehicle-mounted terminal device is usually trained by using a machine learning method. Therefore, the collection of training data is of great significance for the safe driving of an unmanned vehicle.
  • Negative samples are mainly collected by a simulator, and this method collects The negative sample data is unreal. In real driving scenarios, the vehicle terminal equipment trained by using non-real negative samples will have certain security risks.
  • the purpose of the embodiments of the present application is to provide an improved data acquisition method and apparatus for an unmanned vehicle to solve the technical problems mentioned in the above background art.
  • an embodiment of the present application provides a data collection method for an unmanned vehicle, the method comprising: acquiring vehicle data of an unmanned vehicle; and determining, based on the vehicle data, whether the unmanned vehicle is switched from an unmanned mode To the manual driving mode; in response to determining that the driverless vehicle switches to the manual driving mode, determining a switching moment to switch to the manual driving mode; marking the vehicle data acquired within the preset time period before the switching timing as a negative sample.
  • the vehicle data includes sensor data; and determining whether the driverless vehicle switches from the driverless mode to the manual driving mode comprises: determining whether pressure data collected by the pressure sensor on the steering wheel of the driverless vehicle is greater than a preset pressure threshold; and/or determining whether temperature data collected by the temperature sensor on the steering wheel of the unmanned vehicle is greater than a preset temperature threshold; if so, determining that the unmanned vehicle is switched from the driverless mode to the manual driving mode.
  • the vehicle data includes expected driving data and actual driving data; and determining whether the driverless vehicle switches from the driverless mode to the manual driving mode includes: determining a difference between the expected driving data and the actual driving data Whether it is greater than a preset threshold; if so, it is determined that the unmanned vehicle switches from the driverless mode to the manual driving mode.
  • the method further comprises: training the preset unmanned vehicle brain model with the negative sample, wherein the unmanned vehicle The brain model is used to predict vehicle control commands based on vehicle data.
  • the vehicle data includes a distance between the driverless vehicle and the obstacle collected by the distance sensor; and the method further includes: when the distance is less than the preset distance threshold, the distance is less than the start time of the distance threshold The vehicle data acquired during the previous preset time period is marked as a negative sample.
  • the vehicle data includes road condition information; and the method further comprises: determining, based on the road condition information, whether the driverless vehicle deviates from the driving lane; if so, starting the vehicle acquired within a preset time period before the driving lane time The data is marked as a negative sample.
  • an embodiment of the present application provides a data collection device for an unmanned vehicle, the device comprising: an acquisition unit configured to acquire vehicle data of an unmanned vehicle; and a first determining unit configured to be based on the vehicle Data, determining whether the driverless vehicle is switched from the driverless mode to the manual driving mode; the determining unit configured to determine a switching moment to switch to the manual driving mode in response to determining that the driverless vehicle switches to the manual driving mode; a marking unit configured to mark the vehicle data acquired within a preset time period before the switching time as a negative sample.
  • the vehicle data includes sensor data; and the first determining unit includes: a first determining module configured to determine whether pressure data collected by the pressure sensor on the steering wheel of the driverless vehicle is greater than a preset pressure And a second determining module configured to determine whether the temperature data collected by the temperature sensor on the steering wheel of the unmanned vehicle is greater than a preset temperature threshold; the first determining module is configured to: if the pressure data is greater than the pre- If the pressure threshold and/or temperature data is greater than the preset temperature threshold, it is determined that the driverless vehicle switches from the driverless mode to the manual driving mode.
  • the vehicle data includes expected driving data and actual driving data; and a first determining unit, comprising: a third determining module configured to determine whether a difference between the expected driving data and the actual driving data is greater than a preset The second determining module is configured to determine that the unmanned vehicle switches from the driverless mode to the manual driving mode if the difference is greater than a preset threshold.
  • the apparatus further includes a training unit configured to train the preset driverless vehicle brain model with the negative sample, wherein the driverless vehicle brain model is for predicting vehicle control commands based on the vehicle data.
  • the vehicle data includes a distance between the driverless vehicle and the obstacle collected by the distance sensor; and the apparatus further includes: a second marking unit configured to when the distance is less than a preset distance threshold, The vehicle data acquired within a preset time period before the start time less than the distance threshold is marked as a negative sample.
  • the vehicle data includes road condition information; and the apparatus further includes: a second determining unit configured to determine whether the driverless vehicle deviates from the driving lane based on the road condition information; and the third marking unit is configured to When the person driving the vehicle deviates from the driving lane, the vehicle data acquired within the preset time period before starting to deviate from the driving lane time is marked as a negative sample.
  • the embodiment of the present application further provides a server or a terminal, including: one or more processors; and a storage device, configured to store one or more programs, when the one or more programs are one or more of the foregoing
  • the processor executes such that the one or more processors described above implement the data acquisition method of the driverless vehicle provided by the present application.
  • the embodiment of the present application further provides a computer readable storage medium, where a computer program is stored thereon, and when the program is executed by the processor, the data collection method of the unmanned vehicle provided by the present application is implemented.
  • the data acquisition method and device for an unmanned vehicle provided by the embodiment of the present application, by acquiring vehicle data of an unmanned vehicle, and then determining whether the unmanned vehicle is switched from the driverless mode to the manual driving mode based on the vehicle data, If it is determined that the mode is switched to the manual driving mode, the switching time to the manual driving mode is determined, and finally the vehicle data in the preset time period before the switching time is marked as a negative sample, thereby effectively utilizing the vehicle data and achieving more accurate The collection of negative sample data.
  • FIG. 1 is an exemplary system architecture diagram to which the present application can be applied;
  • FIG. 2 is a flow chart of one embodiment of a data collection method for an unmanned vehicle according to the present application
  • FIG. 3 is a schematic diagram of an application scenario of a data acquisition method of an unmanned vehicle according to the present application
  • FIG. 4 is a flow chart of still another embodiment of a data collection method of an unmanned vehicle according to the present application.
  • FIG. 5 is a schematic structural diagram of an embodiment of a data collection device of an unmanned vehicle according to the present application.
  • FIG. 6 is a schematic structural diagram of a computer system suitable for implementing a server or a terminal device of an embodiment of the present application.
  • FIG. 1 illustrates an exemplary system architecture 100 of an embodiment of a data acquisition method of an unmanned vehicle or an embodiment of a data acquisition device for an unmanned vehicle to which the present application may be applied.
  • the system architecture 100 may include an in-vehicle terminal device 101, a network 102, and a cloud server 103 that supports the in-vehicle terminal device 101.
  • the network 102 is used to provide a medium for a communication link between the in-vehicle terminal device 101 and the cloud server 103.
  • Network 102 may include various types of connections, such as wireless communication links, global positioning systems, or fiber optic cables, to name a few.
  • the in-vehicle terminal device 101 interacts with the cloud server 103 via the network 102 to receive or transmit a message or the like.
  • the in-vehicle terminal device 101 can transmit the marked negative samples to the cloud server 103 to cause the cloud server 103 to train the in-vehicle terminal device 101 with the negative samples.
  • the vehicle terminal device 101 may first acquire vehicle data of the driverless vehicle; after that, based on the vehicle data, it may be determined whether the driverless vehicle switches from the driverless mode to the manual driving mode; if switching to the manual driving mode, it may be determined to switch to The switching time of the manual driving mode; finally, the vehicle data acquired within the preset time period before the switching time may be marked as a negative sample, and the marked negative samples may be sent to the cloud server 103.
  • the cloud server 103 may be a server that provides various services, such as a background server that receives a negative sample transmitted by the in-vehicle terminal device 101 or a background server that determines a negative sample for training of the in-vehicle terminal device 101.
  • the background server may analyze and analyze the vehicle data of the driverless vehicle acquired from the in-vehicle terminal device 101, and perform corresponding processing on the in-vehicle terminal device 101 using the processing result (for example, a negative sample).
  • the data collection method of the driverless vehicle may be performed by the vehicle-mounted terminal device 101 or may be performed by the cloud server 103. Accordingly, the data acquisition device of the driverless vehicle may be set to The in-vehicle terminal device 101 may be provided in the cloud server 103.
  • in-vehicle terminal devices, networks, and cloud servers in FIG. 1 is merely illustrative. Depending on the implementation needs, there can be any number of in-vehicle terminal devices, networks and cloud servers.
  • the data acquisition method of the unmanned vehicle includes the following steps:
  • Step 201 Acquire vehicle data of an unmanned vehicle.
  • the electronic device (for example, a cloud server or an unmanned vehicle brain) on which the data acquisition method of the driverless vehicle runs can acquire vehicle data of the driverless vehicle.
  • the electronic device may acquire vehicle data of each driverless vehicle through a wireless connection; when the electronic device is an unmanned vehicle brain, the electronic device may read from the vehicle data storage hard disk.
  • the vehicle data may include, but is not limited to, vehicle speed, engine data (eg, engine speed, engine power, engine torque), steering wheel steering angle, braking torque, air conditioning temperature, fault information, environmental information (eg, road information, traffic lights) information).
  • Step 202 Based on the vehicle data, determine whether the driverless vehicle switches from the driverless mode to the manual driving mode.
  • the electronic device may determine whether the unmanned vehicle is switched from the driverless mode to the manual driving mode, and when it is determined to switch to the manual driving mode, step 203 may be performed.
  • the brain of the driverless vehicle can give a control command to the driverless vehicle based on the preset driving parameters.
  • the unmanned vehicle is in the driverless mode;
  • the unmanned vehicle can perform the corresponding operation according to the manual control command.
  • the manual driving mode has the priority control right.
  • the personnel in the unmanned vehicle can take corresponding countermeasures to manually take over the unmanned vehicle.
  • the person inside the vehicle can manually take over the steering wheel and turn the steering wheel back to the correct position.
  • the vehicle returns to normal, switch to the driverless mode;
  • the vehicle personnel finds that there is an obstacle in front of the driverless vehicle or that the vehicle is still red light and the vehicle is still not decelerating, the vehicle personnel can immediately brake the brakes to control the speed of the vehicle.
  • the vehicle is running normally, switch to the driverless. mode.
  • the electronic device when the electronic device is a cloud server, the electronic device may establish a driving pattern recognition model in advance, and the driving pattern recognition model may be used to represent a correspondence between the vehicle data and the driving mode, wherein the driving model may include Driverless mode and manual driving mode.
  • the electronic device may first acquire vehicle data generated during manual driving, for example, a vehicle travel route, a maximum vehicle speed, a braking torque, and the like; after that, the vehicle data generated during the driverless driving may be acquired;
  • the electronic device can use the machine learning method to input the vehicle data generated during the manual driving and the vehicle data generated during the above-mentioned driving, respectively, and output the artificial driving mode and the unmanned mode as training outputs respectively.
  • Driving pattern recognition model when the electronic device is a cloud server, the electronic device may establish a driving pattern recognition model in advance, and the driving pattern recognition model may be used to represent a correspondence between the vehicle data and the driving mode, wherein the driving model may include Driverless mode and manual driving mode.
  • the electronic device may first acquire vehicle data
  • the electronic device may input the acquired vehicle data into the driving mode recognition model to obtain a driving mode of the unmanned vehicle, thereby determining whether the unmanned vehicle switches from the driverless mode to the manual. Driving mode.
  • the electronic device may acquire a driving pattern recognition model from a cloud server that stores a driving pattern recognition model.
  • the electronic device may first acquire the interior temperature of the unmanned vehicle, when the difference between the interior temperature and the temperature data collected by the temperature sensor on the steering wheel is greater than a preset temperature difference threshold. Then, it can be judged that the above-mentioned unmanned vehicle is switched from the driverless mode to the manual driving mode.
  • the temperature data collected by the temperature sensor on the steering wheel is basically the same as the temperature inside the vehicle.
  • the temperature on the steering wheel changes until it is controlled by the person controlling the steering wheel. The temperature of the hand is kept consistent.
  • the temperature data collected by the temperature sensor is too different from the temperature inside the vehicle, it can be determined that the above-mentioned unmanned vehicle switches to the manual driving mode.
  • the temperature difference threshold is 6, the temperature data collected by the temperature sensor is 36 degrees, and the current interior temperature is 27 degrees, it can be determined that the unmanned vehicle is switched to the manual driving mode.
  • Step 203 determining a switching moment to switch to the manual driving mode.
  • the electronic device may determine a switching moment when the unmanned vehicle switches to the manual driving mode, where the switching moment may be that the unmanned vehicle is The moment of manual takeover.
  • the electronic device may first input the vehicle data into the driving mode recognition model to obtain a driving mode in which the unmanned vehicle is located; and then the electronic device may acquire the driving mode of the unmanned vehicle in the manual driving mode.
  • the electronic device can determine whether the unmanned vehicle is in an unmanned mode at a previous moment of the manual driving time, and if so, the time can be determined as Switch to the switching moment of the manual driving mode.
  • the electronic device may further determine that the time when the difference between the temperature in the vehicle and the temperature data collected by the temperature sensor on the steering wheel is equal to the temperature difference threshold is a switching time to switch to the manual driving mode.
  • Step 204 Mark the vehicle data acquired within the preset time period before the switching time as a negative sample.
  • the electronic device may mark the vehicle data acquired in the preset time period before the switching time as a negative sample, that is, mark the vehicle data when the vehicle has an abnormal situation or a dangerous situation as a negative sample, based on the multiple times.
  • the predetermined period of time may be, for example, 2 seconds or 3 seconds.
  • the electronic device may send the marked negative sample to the cloud server.
  • the electronic device when the electronic device is a cloud server, the electronic device may use the negative sample to train a preset brain model of the driverless vehicle, and the brain model of the driverless vehicle may be used. Predicting vehicle control commands based on vehicle data. Specifically, the electronic device may acquire a vehicle control instruction corresponding to the negative sample, and when acquiring the current vehicle data including the vehicle data in the negative sample, the brain model of the driverless vehicle may not issue the above to the unmanned vehicle. The vehicle control command corresponding to the negative sample.
  • the vehicle data may further include a distance between the unmanned vehicle and the obstacle collected by the distance sensor.
  • the electronic device may determine whether the distance is less than a preset distance threshold (for example, 0.2 meters). When the distance is less than the distance threshold, the vehicle may be acquired within a preset time period before the time when the distance starts to be smaller than the time threshold. The data is marked as a negative sample.
  • the vehicle data may further include road condition information, where the road condition information may include traffic sign information, traffic signal information, driving lane information, and the like, and the electronic device may be installed in the unmanned Monitor the road condition information by driving the camera in all directions.
  • the electronic device may first determine whether the unmanned vehicle deviates from the driving lane based on the road condition information.
  • the driving lane information may be collected by a camera installed in front of or below the driverless vehicle. When it is detected that the driverless vehicle is currently located on a straight road, and the steering wheel steering angle is greater than a preset angle threshold, the above may be determined.
  • the unmanned vehicle deviates from the driving lane; when it is detected that the wheel of the unmanned vehicle is pressed against the solid line on the road, it can be judged that the unmanned vehicle deviates from the driving lane. If it is determined that the above-described unmanned vehicle deviates from the driving lane, the vehicle data acquired within a preset period before starting to deviate from the driving lane timing may be marked as a negative sample.
  • FIG. 3 is a schematic diagram of an application scenario of a data acquisition method of an unmanned vehicle according to the present embodiment.
  • the server 301 first acquires the vehicle data 302 of the driverless vehicle as the in-vehicle temperature of 26 degrees and the temperature collected by the temperature sensor on the steering wheel by 35 degrees; after that, the server 301 determines that the interior temperature is 26 degrees and The temperature difference between the temperature of 35 degrees collected by the temperature sensor on the steering wheel is greater than the preset temperature difference threshold of 6 degrees, and then the unmanned vehicle is determined to switch from the driverless mode 303 to the manual driving mode 304; then, the server 301 The time when the temperature difference between the temperature inside the vehicle and the temperature collected by the temperature sensor on the steering wheel is 6 degrees is determined as the switching time 305 at which the driverless vehicle switches to the manual driving mode 304, and the switching time 305 is 2:24:23. Secondly, the server 301 marks the vehicle data acquired in the preset time period 2 minutes 24 minutes 21 seconds
  • the above-described embodiment of the present application provides a method for determining whether an unmanned vehicle is switched from an unmanned mode to an artificial driving mode by using vehicle data, and marking a vehicle data mark within a preset time period before switching to a switching timing of the manual driving mode It is a negative sample, which improves the accuracy of negative sample data collection.
  • the process 400 of the data acquisition method of the unmanned vehicle includes the following steps:
  • Step 401 Acquire vehicle data of an unmanned vehicle.
  • step 401 is substantially the same as the operation of step 201, and details are not described herein again.
  • Step 402 Determine whether the pressure data collected by the pressure sensor on the steering wheel of the unmanned vehicle is greater than a preset pressure threshold.
  • the above vehicle data may include sensor data.
  • the electronic device may determine whether the pressure data collected by the pressure sensor on the steering wheel of the unmanned vehicle is greater than a preset pressure threshold. If the pressure threshold is greater than the pressure threshold, step 405 may be performed.
  • the pressure data collected by the pressure sensor on the steering wheel of the unmanned vehicle is usually a predetermined value, and when there is artificially controlling the steering wheel, the pressure data collected by the pressure sensor is usually If the value is greater than a certain value, the pressure threshold may be obtained according to a plurality of tests.
  • the electronic device determines that the pressure data collected by the pressure sensor is greater than the pressure threshold, determining that the unmanned vehicle switches to the manual driving mode, the step may be performed. 405.
  • the electronic device may also determine whether the amount of change in pressure data collected by the pressure sensor on the steering wheel is greater than a preset pressure change amount threshold within a preset time period.
  • the pressure data collected by the pressure sensor on the steering wheel of the unmanned vehicle is usually a predetermined value, and when the steering wheel is artificially controlled, the pressure sensor on the steering wheel collects The pressure data generally increases rapidly.
  • the above-mentioned unmanned vehicle can be determined to switch to the manual driving mode.
  • Step 403 Determine whether the temperature data collected by the temperature sensor on the steering wheel of the unmanned vehicle is greater than a preset temperature threshold.
  • the electronic device may determine whether the temperature data collected by the temperature sensor on the steering wheel of the unmanned vehicle is greater than a preset temperature threshold. If the temperature is greater than the temperature threshold, step 405 may be performed.
  • the temperature data collected by the temperature sensor on the steering wheel of the driverless vehicle is usually a predetermined value.
  • the temperature data collected by the temperature sensor is usually If the electronic device determines that the temperature data collected by the temperature sensor is greater than the temperature threshold, it is determined that the unmanned vehicle switches to the manual driving mode, and the step may be performed. 405.
  • the electronic device may further determine whether the amount of change in temperature data collected by the temperature sensor on the steering wheel of the unmanned vehicle is greater than a preset temperature change threshold during a preset time period, if the value is greater than the above
  • the temperature change amount threshold may be performed in step 405.
  • the temperature data collected by the temperature sensor on the steering wheel of the driverless vehicle is usually less than a predetermined value.
  • the temperature sensor on the steering wheel The collected temperature data generally increases rapidly.
  • the unmanned vehicle can be determined to switch to the manual driving mode.
  • Step 404 Determine whether the difference between the expected driving data and the actual driving data is greater than a preset threshold.
  • the vehicle data may include expected driving data and actual driving data
  • the expected driving data may be pre-planned driving parameters, such as a driving route, a driving direction, a speed, a minimum distance to be kept with an obstacle, and the like.
  • the unmanned vehicle will travel according to the expected driving data
  • the actual driving data may be the actual driving parameters.
  • the electronic device may determine whether the difference between the expected driving data and the actual driving data is greater than a preset threshold. If the threshold is greater than the threshold, step 405 may be performed.
  • the expected steering angle of the unmanned vehicle is 40 degrees left, and the actual steering angle is 20 degrees left, and when the steering angle threshold is 5 degrees, it is determined that the driverless vehicle switches to manual Driving mode.
  • Step 405 determining a switching moment to switch to the manual driving mode.
  • the electronic device may determine that the pressure data begins to be greater than the pressure threshold.
  • the electronic device may determine that the temperature data starts to be greater than the temperature threshold. a time; when it is determined in step 404 that the difference between the expected driving data and the actual driving data is greater than the threshold, the electronic device may determine that the difference between the expected driving data and the actual driving data is greater than the start time of the threshold To switch the moment.
  • Step 406 Mark the vehicle data acquired within the preset time period before the switching time as a negative sample.
  • step 406 is substantially the same as the operation of step 204, and details are not described herein again.
  • the flow 400 of the data acquisition method of the unmanned vehicle in the present embodiment highlights various determination modes of the driving mode switching as compared with the embodiment corresponding to FIG. 2.
  • the solution described in this embodiment can achieve more comprehensive data collection.
  • the present application provides an embodiment of a data acquisition device for an unmanned vehicle, the device embodiment corresponding to the method embodiment shown in FIG.
  • the device can be specifically applied to various electronic devices.
  • the data collection device 500 of the driverless vehicle of the present embodiment includes an acquisition unit 501, a first determination unit 502, a determination unit 503, and a first marking unit 504.
  • the obtaining unit 501 is configured to acquire vehicle data of the driverless vehicle;
  • the first determining unit 502 is configured to determine, according to the vehicle data, whether the driverless vehicle switches from the driverless mode to the manual driving mode;
  • the determining unit 503 is configured And determining a switching moment to switch to the manual driving mode in response to determining that the driverless vehicle switches to the manual driving mode;
  • the first marking unit 504 is configured to mark the vehicle data acquired within the preset time period before the switching timing as a negative sample.
  • the specific processing of the acquiring unit 501, the first determining unit 502, the determining unit 503, and the first marking unit 504 of the data collecting device 500 of the driverless vehicle may refer to step 201 in the corresponding embodiment of FIG. 2, Step 202, step 203 and step 204.
  • the vehicle data may include sensor data.
  • the first determining unit 502 may include a first determining module (not shown), a second determining module (not shown), and a first determining module (not shown).
  • the first determining module may determine whether the pressure data collected by the pressure sensor on the steering wheel of the unmanned vehicle is greater than a preset pressure threshold.
  • the pressure data collected by the pressure sensor on the steering wheel of the unmanned vehicle is usually a predetermined value, and when there is artificially controlling the steering wheel, the pressure data collected by the pressure sensor is usually Will be greater than a certain value, according to multiple tests, you can get the pressure threshold.
  • the second determining module may determine whether the temperature data collected by the temperature sensor on the steering wheel of the unmanned vehicle is greater than a preset temperature threshold.
  • the temperature data collected by the temperature sensor on the steering wheel of the driverless vehicle is usually a predetermined value.
  • the temperature data collected by the temperature sensor is usually Will be greater than a certain value, according to multiple tests, you can get the temperature threshold.
  • the first determining module determines that the pressure data collected by the pressure sensor is greater than the pressure threshold, or when the second determining module determines that the temperature data is greater than the temperature threshold, the first determining module may determine the unmanned vehicle switching. To manual driving mode.
  • the vehicle data may include expected driving data and actual driving data
  • the expected driving data may be pre-planned driving parameters, such as driving route, driving direction, speed, and obstacles.
  • the first determining unit 502 may include a third determining module (not shown) and a second determining module (not shown). The third determining module may determine whether the difference between the expected driving data and the actual driving data is greater than a preset threshold. If the threshold is greater than the threshold, the second determining module may determine that the unmanned vehicle switches to the manual driving mode.
  • the data acquisition device 500 of the unmanned vehicle may further include a training unit (not shown).
  • the training unit may train the preset brain model of the driverless vehicle by using the negative sample, and the brain model of the driverless vehicle may be used for vehicle data based on the vehicle. Predict vehicle control instructions.
  • the training unit may acquire a vehicle control instruction corresponding to the negative sample, and when acquiring the current vehicle data including the vehicle data in the negative sample, the brain model of the unmanned vehicle may not send the above to the unmanned vehicle.
  • the vehicle control command corresponding to the negative sample may be used for vehicle data based on the vehicle.
  • the vehicle data may further include a distance between the unmanned vehicle and the obstacle collected by the distance sensor.
  • the data acquisition device 500 of the above-described unmanned vehicle may further include a second marking unit (not shown).
  • the second marking unit may determine whether the distance is less than a preset distance threshold. When the distance is less than the distance threshold, the vehicle data acquired in the preset time period before the time when the distance starts to be smaller than the distance threshold may be marked as Negative sample.
  • the vehicle data may further include road condition information, where the road condition information may include traffic sign information, traffic signal information, and driving lane information, and the data collecting device 500 of the unmanned vehicle may be The road condition information is monitored by a camera mounted in all directions of the driverless vehicle.
  • the data acquisition device 500 of the above-described unmanned vehicle may further include a second judging unit (not shown) and a third marking unit (not shown). The second determining unit may first determine whether the unmanned vehicle is deviated from the driving lane based on the road condition information.
  • the driving lane information may be collected by a camera installed in front of or below the driverless vehicle.
  • the above may be determined.
  • the unmanned vehicle deviates from the driving lane; when it is detected that the wheel of the unmanned vehicle is pressed against the solid line on the road, it can be judged that the unmanned vehicle deviates from the driving lane. If it is determined that the unmanned vehicle is deviated from the driving lane, the third marking unit may mark the vehicle data acquired within a preset period before starting to deviate from the driving lane timing as a negative sample.
  • FIG. 6 a block diagram of a computer system 600 suitable for use in implementing a server or in-vehicle terminal device of an embodiment of the present invention is shown.
  • the server or the in-vehicle terminal device shown in FIG. 6 is merely an example, and should not impose any limitation on the function and scope of use of the embodiments of the present application.
  • computer system 600 includes a central processing unit (CPU) 601 that can be loaded into a program in random access memory (RAM) 603 according to a program stored in read only memory (ROM) 602 or from storage portion 608. And perform various appropriate actions and processes.
  • RAM random access memory
  • ROM read only memory
  • RAM random access memory
  • various programs and data required for the operation of the system 600 are also stored.
  • the CPU 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604.
  • An input/output (I/O) interface 605 is also coupled to bus 604.
  • the following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, etc.; an output portion 607 including, for example, a liquid crystal display (LCD) and a speaker; a storage portion 608 including a hard disk or the like; and including, for example, a LAN card, a modem
  • the communication portion 609 of the network interface card performs communication processing via a network such as the Internet.
  • Driver 610 is also coupled to I/O interface 605 as needed.
  • a removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory or the like, is mounted on the drive 610 as needed so that a computer program read therefrom is installed into the storage portion 608 as needed.
  • an embodiment of the present disclosure includes a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for executing the method illustrated in the flowchart.
  • the computer program can be downloaded and installed from the network via communication portion 609, and/or installed from removable media 611.
  • the central processing unit (CPU) 601 the above-described functions defined in the method of the present application are performed.
  • the computer readable medium described above may be a computer readable signal medium or a computer readable storage medium or any combination of the two.
  • the computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of computer readable storage media may include, but are not limited to, electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing.
  • a computer readable storage medium may be any tangible medium that can contain or store a program, which can be used by or in connection with an instruction execution system, apparatus or device.
  • a computer readable signal medium may include a data signal that is propagated in the baseband or as part of a carrier, carrying computer readable program code. Such propagated data signals can take a variety of forms including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • the computer readable signal medium can also be any computer readable medium other than a computer readable storage medium, which can transmit, propagate, or transport a program for use by or in connection with the instruction execution system, apparatus, or device.
  • Program code embodied on a computer readable medium can be transmitted by any suitable medium, including but not limited to wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
  • each block of the flowchart or block diagram can represent a module, a program segment, or a portion of code that includes one or more of the logic functions for implementing the specified.
  • Executable instructions can also occur in a different order than that illustrated in the drawings. For example, two successively represented blocks may in fact be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts can be implemented in a dedicated hardware-based system that performs the specified function or operation. Or it can be implemented by a combination of dedicated hardware and computer instructions.
  • the units involved in the embodiments of the present invention may be implemented by software or by hardware.
  • the described unit may also be provided in the processor, for example, as a processor including an acquisition unit, a first determination unit, a determination unit, and a first marker unit.
  • the names of these units do not in any way constitute a limitation on the unit itself.
  • the acquisition unit may also be described as "a unit that acquires vehicle data of an unmanned vehicle.”
  • the present application also provides a computer readable medium, which may be included in the apparatus described in the above embodiments, or may be separately present and not incorporated into the apparatus.
  • the computer readable medium carries one or more programs, when the one or more programs are executed by the device, causing the device to: acquire vehicle data of the driverless vehicle; and based on the vehicle data, determine whether the driverless vehicle is from The driverless mode is switched to the manual driving mode; in response to determining that the driverless vehicle switches to the manual driving mode, the switching moment of switching to the manual driving mode is determined; the vehicle data acquired within the preset time period before the switching timing is marked as a negative sample.

Abstract

本申请实施例公开了无人驾驶车辆的数据采集方法和装置。该方法的一具体实施方式包括：获取无人驾驶车辆的车辆数据；基于车辆数据，判断无人驾驶车辆是否从无人驾驶模式切换到人工驾驶模式；响应于确定无人驾驶车辆切换到人工驾驶模式，确定切换到人工驾驶模式的切换时刻；将切换时刻之前预设时段内获取的车辆数据标记为负样本。该实施方式实现了更准确的负样本数据的采集。

Description

无人驾驶车辆的数据采集方法和装置
本专利申请要求于2017年9月5日提交的、申请号为201710790002.9、申请人为百度在线网络技术(北京)有限公司、发明名称为“无人驾驶车辆的数据采集方法和装置”的中国专利申请的优先权，该申请的全文以引用的方式并入本申请中。
技术领域
本申请涉及计算机技术领域，具体涉及无人驾驶车辆技术领域，尤其涉及无人驾驶车辆的数据采集方法和装置。
背景技术
无人驾驶车辆是一种新型的智能汽车，主要通过ECU(Electronic Control Unit，电子控制单元)等车载终端设备对车辆中各个部分进行精准的控制与计算分析，从而实现车辆的全自动运行，达到车辆无人驾驶的目的。现有技术中，通常利用机器学习方法对车载终端设备进行训练，因此，训练数据的采集对无人驾驶车辆的安全驾驶而言具有非常重要的意义。
目前，在真实驾驶环境下只能采集到正常的驾驶行为数据(正样本)，而无法采集异常的驾驶行为数据(负样本)，负样本主要是通过模拟器进行采集，而这种方法采集到的负样本数据是非真实的，在真实的驾驶场景中，利用非真实的负样本训练出的车载终端设备会存在一定的安全隐患。
发明内容
本申请实施例的目的在于提出一种改进的无人驾驶车辆的数据采集方法和装置，来解决以上背景技术部分提到的技术问题。
第一方面，本申请实施例提供了一种无人驾驶车辆的数据采集方 法，该方法包括：获取无人驾驶车辆的车辆数据；基于车辆数据，判断无人驾驶车辆是否从无人驾驶模式切换到人工驾驶模式；响应于确定无人驾驶车辆切换到人工驾驶模式，确定切换到人工驾驶模式的切换时刻；将切换时刻之前预设时段内获取的车辆数据标记为负样本。
在一些实施例中，车辆数据包括传感器数据；以及判断无人驾驶车辆是否从无人驾驶模式切换到人工驾驶模式，包括：判断无人驾驶车辆的方向盘上的压力传感器所采集的压力数据是否大于预设的压力阈值；和/或判断无人驾驶车辆的方向盘上的温度传感器所采集的温度数据是否大于预设的温度阈值；若是，则确定无人驾驶车辆从无人驾驶模式切换到人工驾驶模式。
在一些实施例中，车辆数据包括预期驾驶数据和实际驾驶数据；以及判断无人驾驶车辆是否从无人驾驶模式切换到人工驾驶模式，包括：判断预期驾驶数据与实际驾驶数据之间的差值是否大于预设的阈值；若是，则确定无人驾驶车辆从无人驾驶模式切换到人工驾驶模式。
在一些实施例中，在将切换时刻之前预设时段内获取的车辆数据标记为负样本之后，该方法还包括：利用负样本训练预设的无人驾驶车辆大脑模型，其中，无人驾驶车辆大脑模型用于基于车辆数据预测车辆控制指令。
在一些实施例中，车辆数据包括距离传感器所采集的无人驾驶车辆与障碍物之间的距离；以及该方法还包括：当距离小于预设的距离阈值时，将距离小于距离阈值的开始时刻之前的预设时段内获取的车辆数据标记为负样本。
在一些实施例中，车辆数据包括路况信息；以及该方法还包括：基于路况信息，判断无人驾驶车辆是否偏离行驶车道；若是，则将开始偏离行驶车道时刻之前的预设时段内获取的车辆数据标记为负样本。
第二方面，本申请实施例提供了一种无人驾驶车辆的数据采集装置，该装置包括：获取单元，配置用于获取无人驾驶车辆的车辆数据；第一判断单元，配置用于基于车辆数据，判断无人驾驶车辆是否从无人驾驶模式切换到人工驾驶模式；确定单元，配置用于响应于确定无 人驾驶车辆切换到人工驾驶模式，确定切换到人工驾驶模式的切换时刻；第一标记单元，配置用于将切换时刻之前预设时段内获取的车辆数据标记为负样本。
在一些实施例中，车辆数据包括传感器数据；以及第一判断单元，包括：第一判断模块，配置用于判断无人驾驶车辆的方向盘上的压力传感器所采集的压力数据是否大于预设的压力阈值；和/或第二判断模块，配置用于判断无人驾驶车辆的方向盘上的温度传感器所采集的温度数据是否大于预设的温度阈值；第一确定模块，配置用于若压力数据大于预设的压力阈值和/或温度数据大于预设的温度阈值，则确定无人驾驶车辆从无人驾驶模式切换到人工驾驶模式。
在一些实施例中，车辆数据包括预期驾驶数据和实际驾驶数据；以及第一判断单元，包括：第三判断模块，配置用于判断预期驾驶数据与实际驾驶数据之间的差值是否大于预设的阈值；第二确定模块，配置用于若差值大于预设的阈值，则确定无人驾驶车辆从无人驾驶模式切换到人工驾驶模式。
在一些实施例中，该装置还包括：训练单元，配置用于利用负样本训练预设的无人驾驶车辆大脑模型，其中，无人驾驶车辆大脑模型用于基于车辆数据预测车辆控制指令。
在一些实施例中，车辆数据包括距离传感器所采集的无人驾驶车辆与障碍物之间的距离；以及该装置还包括：第二标记单元，配置用于当距离小于预设的距离阈值时，将距离小于距离阈值的开始时刻之前的预设时段内获取的车辆数据标记为负样本。
在一些实施例中，车辆数据包括路况信息；以及该装置还包括：第二判断单元，配置用于基于路况信息，判断无人驾驶车辆是否偏离行驶车道；第三标记单元，配置用于若无人驾驶车辆偏离行驶车道，则将开始偏离行驶车道时刻之前的预设时段内获取的车辆数据标记为负样本。
第三方面，本申请实施例还提供了一种服务器或终端，包括：一个或多个处理器；存储装置，用于存储一个或多个程序，当上述一个或多个程序被上述一个或多个处理器执行，使得上述一个或多个处理 器实现本申请提供的无人驾驶车辆的数据采集方法。
第四方面，本申请实施例还提供了一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现本申请提供的无人驾驶车辆的数据采集方法。
本申请实施例提供的无人驾驶车辆的数据采集方法和装置，通过获取无人驾驶车辆的车辆数据，而后基于上述车辆数据，判断无人驾驶车辆是否从无人驾驶模式切换到人工驾驶模式，若判断出切换到人工驾驶模式，则确定切换到人工驾驶模式的切换时刻，最后将上述切换时刻之前的预设时段内的车辆数据标记为负样本，从而有效利用了车辆数据，实现了更准确的负样本数据的采集。
附图说明
通过阅读参照以下附图所作的对非限制性实施例所作的详细描述，本申请的其它特征、目的和优点将会变得更明显：
图1是本申请可以应用于其中的示例性系统架构图；
图2是根据本申请的无人驾驶车辆的数据采集方法的一个实施例的流程图；
图3是根据本申请的无人驾驶车辆的数据采集方法的一个应用场景的示意图；
图4是根据本申请的无人驾驶车辆的数据采集方法的又一个实施例的流程图；
图5是根据本申请的无人驾驶车辆的数据采集装置的一个实施例的结构示意图；
图6是适于用来实现本申请实施例的服务器或终端设备的计算机系统的结构示意图。
具体实施方式
下面结合附图和实施例对本申请作进一步的详细说明。可以理解的是，此处所描述的具体实施例仅仅用于解释相关发明，而非对该发明的限定。另外还需要说明的是，为了便于描述，附图中仅示出了与 有关发明相关的部分。
需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。下面将参考附图并结合实施例来详细说明本申请。
图1示出了可以应用本申请的无人驾驶车辆的数据采集方法或无人驾驶车辆的数据采集装置的实施例的示例性系统架构100。
如图1所示，系统架构100可以包括车载终端设备101、网络102和对车载终端设备101进行支持的云服务器103。网络102用以在车载终端设备101和云服务器103之间提供通信链路的介质。网络102可以包括各种连接类型，例如无线通信链路、全球定位系统或者光纤电缆等等。
车载终端设备101通过网络102与云服务器103交互，以接收或发送消息等。车载终端设备101可以将标记出的负样本发送给云服务器103以使云服务器103利用负样本对车载终端设备101进行训练。车载终端设备101可以首先获取无人驾驶车辆的车辆数据；之后，可以基于车辆数据，判断无人驾驶车辆是否从无人驾驶模式切换到人工驾驶模式；若切换到人工驾驶模式，可以确定切换到人工驾驶模式的切换时刻；最后，可以将切换时刻之前预设时段内获取的车辆数据标记为负样本，并可以将标记出的负样本发送给云服务器103。
云服务器103可以是提供各种服务的服务器，例如接收车载终端设备101发送的负样本的后台服务器或者确定车载终端设备101的训练用负样本的后台服务器。例如，后台服务器可以对从车载终端设备101获取的无人驾驶车辆的车辆数据进行分析等处理，并利用处理结果(例如负样本)对车载终端设备101进行相应的处理。
需要说明的是，本申请实施例所提供的无人驾驶车辆的数据采集方法可以由车载终端设备101执行，也可以由云服务器103执行，相应地，无人驾驶车辆的数据采集装置可以设置于车载终端设备101中，也可以设置于云服务器103中。
应该理解，图1中的车载终端设备、网络和云服务器的数目仅仅是示意性的。根据实现需要，可以具有任意数目的车载终端设备、网 络和云服务器。
继续参考图2，示出了根据本申请的无人驾驶车辆的数据采集方法的一个实施例的流程200。该无人驾驶车辆的数据采集方法，包括以下步骤：
步骤201，获取无人驾驶车辆的车辆数据。
在本实施例中，无人驾驶车辆的数据采集方法运行于其上的电子设备(例如云服务器或者无人驾驶车辆大脑)可以获取无人驾驶车辆的车辆数据。当上述电子设备为云服务器时，上述电子设备可以通过无线连接方式获取各个无人驾驶车辆的车辆数据；当上述电子设备为无人驾驶车辆大脑时，上述电子设备可以从车辆数据存储硬盘中读取车辆数据。上述车辆数据可以包括但不限于车速、发动机数据(如，发动机转速、发动机功率、发动机扭矩)、方向盘转向角度、制动力矩、空调温度、故障信息、外界环境信息(如，道路信息、交通信号灯信息)。
步骤202，基于车辆数据，判断无人驾驶车辆是否从无人驾驶模式切换到人工驾驶模式。
在本实施例中，基于步骤201中获取的车辆数据，上述电子设备可以判断无人驾驶车辆是否从无人驾驶模式切换到人工驾驶模式，当确定切换到人工驾驶模式时，可以执行步骤203。无人驾驶车辆在没有人工控制的情况下，无人驾驶车辆大脑可以基于预先设定好的行驶参数对无人驾驶车辆发出的控制指令，此时，无人驾驶车辆处于无人驾驶模式；当无人驾驶车辆被人工接管时，无人驾驶车辆可以按照人工控制指令执行相应的操作，此时，人工驾驶模式具有优先控制权。当无人驾驶车辆遇到紧急情况或者危险情况时，无人驾驶车辆内的人员可以采取相应的应对措施，对无人驾驶车辆实施人工接管。作为示例，当车内人员发现无人驾驶车辆偏离正确行使车道时，车内人员可以人工接管方向盘，将方向盘拨回到正确的位置，当车身回归正常时，再切换到无人驾驶模式；当车内人员发现无人驾驶车辆的前方有障碍物或者当前为红灯而车辆仍未减速时，车内人员可以立刻踩刹车以控 制车辆速度，当车辆行驶情况正常时，再切换到无人驾驶模式。
在本实施例中，当上述电子设备为云服务器时，上述电子设备可以预先建立驾驶模式识别模型，驾驶模式识别模型可以用于表征车辆数据与驾驶模式的对应关系，其中，上述驾驶模型可以包括无人驾驶模式和人工驾驶模式。具体的，上述电子设备可以首先获取人工驾驶时所生成的车辆数据，例如，车辆行驶路线、最高车速、制动力矩等等；之后，可以获取无人驾驶时所生成的车辆数据；最后，上述电子设备可以利用机器学习方法，将上述人工驾驶时所生成的车辆数据和上述无人驾驶时所生成的车辆数据分别作为输入，将上述人工驾驶模式和上述无人驾驶模式分别作为输出，训练得到驾驶模式识别模型。
在本实施例中，上述电子设备可以将获取到的车辆数据输入到上述驾驶模式识别模型中得到上述无人驾驶车辆的驾驶模式，从而判断上述无人驾驶车辆是否从无人驾驶模式切换到人工驾驶模式。当上述电子设备为无人驾驶车辆大脑时，上述电子设备可以从存储驾驶模式识别模型的云服务器中获取驾驶模式识别模型。
在本实施例中，上述电子设备可以首先获取上述无人驾驶车辆的车内温度，当上述车内温度与方向盘上的温度传感器所采集的温度数据的差值大于预设的温度差值阈值时，则可以判断上述无人驾驶车辆从无人驾驶模式切换到人工驾驶模式。在无人驾驶模式下，方向盘上的温度传感器所采集的温度数据基本上会与车内温度保持一致，当对方向盘进行人工控制时，方向盘上的温度会发生变化，直到与控制方向盘的人员的手部温度保持一致，当温度传感器所采集的温度数据与车内温度相差过大时，则可以确定上述无人驾驶车辆切换到人工驾驶模式。作为示例，当温度差值阈值为6、温度传感器所采集到的温度数据为36度、当前的车内温度为27度时，则可以确定上述无人驾驶车辆切换到人工驾驶模式。
步骤203，确定切换到人工驾驶模式的切换时刻。
在本实施例中，当确定上述无人驾驶车辆切换到人工驾驶模式时，上述电子设备可以确定上述无人驾驶车辆切换到人工驾驶模式的切换时刻，上述切换时刻可以为上述无人驾驶车辆被人工接管的时刻。
在本实施例中，上述电子设备可以首先将车辆数据输入上述驾驶模式识别模型得到上述无人驾驶车辆所处的驾驶模式；之后，上述电子设备可以获取上述无人驾驶车辆处于人工驾驶模式时的各个人工驾驶时刻；最后，对于每个人工驾驶时刻，上述电子设备可以判断在该人工驾驶时刻的前一时刻，上述无人驾驶车辆是否处于无人驾驶模式，若是，则可以将该时刻确定为切换到人工驾驶模式的切换时刻。
在本实施例中，上述电子设备还可以将车内温度与方向盘上的温度传感器所采集的温度数据的差值等于上述温度差值阈值时的时刻确定为切换到人工驾驶模式的切换时刻。
步骤204，将切换时刻之前预设时段内获取的车辆数据标记为负样本。
在本实施例中，上述电子设备可以将在上述切换时刻之前的预设时段内获取的车辆数据标记为负样本，即将车辆出现异常情况或危险情况时的车辆数据标记为负样本，基于多次试验结果，上述预设时段例如可以为2秒或3秒。作为示例，当确定出切换时刻为1点55分48秒，则可以将1点55分46秒到1点55分48秒之间的车辆数据标记为负样本。当上述电子设备为无人驾驶车辆大脑时，上述电子设备可以将标记出的负样本发送给云服务器。
在本实施例的一些可选的实现方式中，当上述电子设备为云服务器时，上述电子设备可以利用上述负样本训练预设的无人驾驶车辆大脑模型，上述无人驾驶车辆大脑模型可以用于基于车辆数据预测车辆控制指令。具体地，上述电子设备可以获取与上述负样本对应的车辆控制指令，当获取到当前的车辆数据包括上述负样本中的车辆数据时，无人驾驶车辆大脑模型可以不向无人驾驶车辆发出上述负样本所对应的车辆控制指令。
在本实施例的一些可选的实现方式中，上述车辆数据还可以包括距离传感器所采集的上述无人驾驶车辆与障碍物之间的距离。上述电子设备可以确定上述距离是否小于预设的距离阈值(例如0.2米)，当上述距离小于上述距离阈值时，则可以将上述距离开始小于上述距离阈值的时刻之前的预设时段内获取的车辆数据标记为负样本。
在本实施例的一些可选的实现方式中，上述车辆数据还可以包括路况信息，上述路况信息可以包括交通标志信息、交通信号灯信息、行驶车道信息等等，上述电子设备可以通过安装在无人驾驶车辆各个方向上的摄像头监控路况信息。上述电子设备可以首先基于上述路况信息，判断上述无人驾驶车辆是否偏离行驶车道。具体地，可以通过安装在无人驾驶车辆前方或下方的摄像头采集到行驶车道信息，当检测到无人驾驶车辆目前位于直行道路，而方向盘转向角度大于预设的角度阈值时，则可以判断上述无人驾驶车辆偏离行驶车道；当检测到无人驾驶车辆的车轮压过道路上的实线时，则可以判断上述无人驾驶车辆偏离行驶车道。若确定上述无人驾驶车辆偏离行驶车道，则可以将开始偏离行驶车道时刻之前的预设时段内获取的车辆数据标记为负样本。
继续参见图3，图3是根据本实施例的无人驾驶车辆的数据采集方法的应用场景的一个示意图。在图3的应用场景中，服务器301首先获取到无人驾驶车辆的车辆数据302为车内温度26度、方向盘上温度传感器所采集的温度35度；之后，服务器301判断车内温度26度与方向盘上温度传感器所采集的温度35度之间的温度差9度大于预设的温度差阈值6度，则确定无人驾驶车辆从无人驾驶模式303切换到人工驾驶模式304；然后，服务器301将车内温度与方向盘上温度传感器所采集的温度之间的温度差为6度时的时刻确定为无人驾驶车辆切换到人工驾驶模式304的切换时刻305，切换时刻305为2点24分23秒；最后，服务器301将切换时刻305之前的预设时段2点24分21秒到2点24分23秒内获取的车辆数据标记为负样本306。
本申请的上述实施例提供的方法通过利用车辆数据判断无人驾驶车辆是否从无人驾驶模式切换到人工驾驶模式，并将切换到人工驾驶模式的切换时刻之前的预设时段内的车辆数据标记为负样本，从而提高了负样本数据采集的准确性。
进一步参考图4，其示出了无人驾驶车辆的数据采集方法的又一 个实施例的流程400。该无人驾驶车辆的数据采集方法的流程400，包括以下步骤：
步骤401，获取无人驾驶车辆的车辆数据。
在本实施例中，步骤401的操作与步骤201的操作基本相同，在此不再赘述。
步骤402，判断无人驾驶车辆的方向盘上的压力传感器所采集的压力数据是否大于预设的压力阈值。
在本实施例中，上述车辆数据可以包括传感器数据。上述电子设备可以判断上述无人驾驶车辆的方向盘上的压力传感器所采集的压力数据是否大于预设的压力阈值，若大于上述压力阈值，则可以执行步骤405。当无人驾驶车辆处于无人驾驶模式时，无人驾驶车辆的方向盘上的压力传感器所采集的压力数据通常为预定数值，当存在人为地对方向盘进行控制时，压力传感器所采集的压力数据通常会大于某一数值，根据多次试验，可以得到压力阈值，当上述电子设备判断压力传感器所采集的压力数据大于上述压力阈值时，则确定上述无人驾驶车辆切换到人工驾驶模式，可以执行步骤405。
在本实施例中，上述电子设备也可以判断在预设时间段内上述方向盘上的压力传感器所采集的压力数据的变化量是否大于预设的压力变化量阈值。当无人驾驶车辆处于无人驾驶模式时，无人驾驶车辆的方向盘上的压力传感器所采集的压力数据通常为预定数值，当人为地对方向盘进行控制时，方向盘上的压力传感器所采集到的压力数据一般会快速增加，当判断出压力数据的变化量大于上述压力变化量阈值，则可以确定上述无人驾驶车辆切换到人工驾驶模式。
步骤403，判断无人驾驶车辆的方向盘上的温度传感器所采集的温度数据是否大于预设的温度阈值。
在本实施例中，上述电子设备可以判断上述无人驾驶车辆的方向盘上的温度传感器所采集的温度数据是否大于预设的温度阈值，若大于上述温度阈值，则可以执行步骤405。当无人驾驶车辆处于无人驾驶模式时，无人驾驶车辆的方向盘上的温度传感器所采集的温度数据通常为预定数值，当存在人为地对方向盘进行控制时，温度传感器所 采集的温度数据通常会大于某一数值，根据多次试验，可以得到温度阈值，当上述电子设备判断温度传感器所采集的温度数据大于上述温度阈值时，则确定上述无人驾驶车辆切换到人工驾驶模式，可以执行步骤405。
在本实施例中，上述电子设备还可以判断在预设时间段内上述无人驾驶车辆的方向盘上的温度传感器所采集的温度数据的变化量是否大于预设的温度变化量阈值，若大于上述温度变化量阈值，则可以执行步骤405。当无人驾驶车辆处于无人驾驶模式时，无人驾驶车辆的方向盘上的温度传感器所采集的温度数据的变化量通常小于预定数值，当人为地对方向盘进行控制时，方向盘上的温度传感器所采集到的温度数据一般会快速增加，当判断出温度数据的变化量大于上述温度变化量阈值，则可以确定上述无人驾驶车辆切换到人工驾驶模式。
步骤404，判断预期驾驶数据与实际驾驶数据之间的差值是否大于预设的阈值。
在本实施例中，上述车辆数据可以包括预期驾驶数据和实际驾驶数据，上述预期驾驶数据可以为预先规划的驾驶参数，如行驶路线、行驶方向、速度、与障碍物保持的最小距离等等，当无人驾驶车辆处于无人驾驶模式时，无人驾驶车辆会按照预期驾驶数据进行行驶，上述实际驾驶数据可以为实际得到的驾驶参数。上述电子设备可以判断预期驾驶数据与实际驾驶数据之间的差值是否大于预设的阈值，若大于上述阈值，则可以执行步骤405。作为示例，在某一时刻，无人驾驶车辆的预期转向角度为左转40度，而实际转向角度为左转20度，当转向角度阈值为5度时，则确定无人驾驶车辆切换到人工驾驶模式。
步骤405，确定切换到人工驾驶模式的切换时刻。
在本实施例中，当在步骤402中判断出无人驾驶车辆的方向盘上的压力传感器所采集的压力数据大于上述压力阈值时，上述电子设备可以将上述压力数据开始大于上述压力阈值的时刻确定为切换时刻；当在步骤403中判断出无人驾驶车辆的方向盘上的温度传感器所采集的温度数据大于上述温度阈值时，上述电子设备可以将上述温度数据开始大于上述温度阈值的时刻确定为切换时刻；当在步骤404中判断 出预期驾驶数据与实际驾驶数据之间的差值大于上述阈值时，上述电子设备可以将预期驾驶数据与实际驾驶数据之间的差值大于上述阈值的开始时刻确定为切换时刻。
步骤406，将切换时刻之前预设时段内获取的车辆数据标记为负样本。
在本实施例中，步骤406的操作与步骤204的操作基本相同，在此不再赘述。
从图4中可以看出，与图2对应的实施例相比，本实施例中的无人驾驶车辆的数据采集方法的流程400突出了驾驶模式切换的多种判断方式。由此，本实施例描述的方案可以实现更全面的数据采集。
进一步参考图5，作为对上述各图所示方法的实现，本申请提供了一种无人驾驶车辆的数据采集装置的一个实施例，该装置实施例与图2所示的方法实施例相对应，该装置具体可以应用于各种电子设备中。
如图5所示，本实施例的无人驾驶车辆的数据采集装置500包括：获取单元501、第一判断单元502、确定单元503和第一标记单元504。其中，获取单元501配置用于获取无人驾驶车辆的车辆数据；第一判断单元502配置用于基于车辆数据，判断无人驾驶车辆是否从无人驾驶模式切换到人工驾驶模式；确定单元503配置用于响应于确定无人驾驶车辆切换到人工驾驶模式，确定切换到人工驾驶模式的切换时刻；第一标记单元504配置用于将切换时刻之前预设时段内获取的车辆数据标记为负样本。
在本实施例中，无人驾驶车辆的数据采集装置500的获取单元501、第一判断单元502、确定单元503和第一标记单元504的具体处理可以参考图2对应实施例中的步骤201、步骤202、步骤203和步骤204。
在本实施例的一些可选的实现方式中，上述车辆数据可以包括传感器数据。上述第一判断单元502可以包括第一判断模块(图中未示出)、第二判断模块(图中未示出)和第一确定模块(图中未示出)。 上述第一判断模块可以判断上述无人驾驶车辆的方向盘上的压力传感器所采集的压力数据是否大于预设的压力阈值。当无人驾驶车辆处于无人驾驶模式时，无人驾驶车辆的方向盘上的压力传感器所采集的压力数据通常为预定数值，当存在人为地对方向盘进行控制时，压力传感器所采集的压力数据通常会大于某一数值，根据多次试验，可以得到压力阈值。上述第二判断模块可以判断上述无人驾驶车辆的方向盘上的温度传感器所采集的温度数据是否大于预设的温度阈值。当无人驾驶车辆处于无人驾驶模式时，无人驾驶车辆的方向盘上的温度传感器所采集的温度数据通常为预定数值，当存在人为地对方向盘进行控制时，温度传感器所采集的温度数据通常会大于某一数值，根据多次试验，可以得到温度阈值。当上述第一判断模块判断压力传感器所采集的压力数据大于上述压力阈值时，或者当上述第二判断模块判断出温度数据大于上述温度阈值，则上述第一确定模块可以确定上述无人驾驶车辆切换到人工驾驶模式。
在本实施例的一些可选的实现方式中，上述车辆数据可以包括预期驾驶数据和实际驾驶数据，上述预期驾驶数据可以为预先规划的驾驶参数，如行驶路线、行驶方向、速度、与障碍物保持的最小距离等等，当无人驾驶车辆处于无人驾驶模式时，无人驾驶车辆会按照预期驾驶数据进行行驶，上述实际驾驶数据可以为实际得到的驾驶参数。上述第一判断单元502可以包括第三判断模块(图中未示出)和第二确定模块(图中未示出)。上述第三判断模块可以判断预期驾驶数据与实际驾驶数据之间的差值是否大于预设的阈值，若大于上述阈值，则上述第二确定模块可以确定上述无人驾驶车辆切换到人工驾驶模式。
在本实施例的一些可选的实现方式中，上述无人驾驶车辆的数据采集装置500还可以包括训练单元(图中未示出)。当上述无人驾驶车辆的数据采集装置500设置于云服务器上时，上述训练单元可以利用上述负样本训练预设的无人驾驶车辆大脑模型，上述无人驾驶车辆大脑模型可以用于基于车辆数据预测车辆控制指令。具体地，上述训练单元可以获取与上述负样本对应的车辆控制指令，当获取到当前的车辆数据包括上述负样本中的车辆数据时，无人驾驶车辆大脑模型可以 不向无人驾驶车辆发出上述负样本所对应的车辆控制指令。
在本实施例的一些可选的实现方式中，上述车辆数据还可以包括距离传感器所采集的上述无人驾驶车辆与障碍物之间的距离。上述无人驾驶车辆的数据采集装置500还可以包括第二标记单元(图中未示出)。上述第二标记单元可以确定上述距离是否小于预设的距离阈值，当上述距离小于上述距离阈值时，则可以将上述距离开始小于上述距离阈值的时刻之前的预设时段内获取的车辆数据标记为负样本。
在本实施例的一些可选的实现方式中，上述车辆数据还可以包括路况信息，上述路况信息可以包括交通标志信息、交通信号灯信息、行驶车道信息，上述无人驾驶车辆的数据采集装置500可以通过安装在无人驾驶车辆各个方向上的摄像头监控路况信息。上述无人驾驶车辆的数据采集装置500还可以包括第二判断单元(图中未示出)和第三标记单元(图中未示出)。上述第二判断单元可以首先基于上述路况信息，判断上述无人驾驶车辆是否偏离行驶车道。具体地，可以通过安装在无人驾驶车辆前方或下方的摄像头采集到行驶车道信息，当检测到无人驾驶车辆目前位于直行道路，而方向盘转向角度大于预设的角度阈值时，则可以判断上述无人驾驶车辆偏离行驶车道；当检测到无人驾驶车辆的车轮压过道路上的实线时，则可以判断上述无人驾驶车辆偏离行驶车道。若确定上述无人驾驶车辆偏离行驶车道，则上述第三标记单元可以将开始偏离行驶车道时刻之前的预设时段内获取的车辆数据标记为负样本。
下面参考图6，其示出了适于用来实现本发明实施例的服务器或车载终端设备的计算机系统600的结构示意图。图6示出的服务器或车载终端设备仅仅是一个示例，不应对本申请实施例的功能和使用范围带来任何限制。
如图6所示，计算机系统600包括中央处理单元(CPU)601，其可以根据存储在只读存储器(ROM)602中的程序或者从存储部分608加载到随机访问存储器(RAM)603中的程序而执行各种适当的动作和处理。在RAM 603中，还存储有系统600操作所需的各种程序和数 据。CPU 601、ROM 602以及RAM 603通过总线604彼此相连。输入/输出(I/O)接口605也连接至总线604。
以下部件连接至I/O接口605：包括键盘、鼠标等的输入部分606；包括诸如液晶显示器(LCD)以及扬声器等的输出部分607；包括硬盘等的存储部分608；以及包括诸如LAN卡、调制解调器等的网络接口卡的通信部分609。通信部分609经由诸如因特网的网络执行通信处理。驱动器610也根据需要连接至I/O接口605。可拆卸介质611，诸如磁盘、光盘、磁光盘、半导体存储器等等，根据需要安装在驱动器610上，以便于从其上读出的计算机程序根据需要被安装入存储部分608。
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信部分609从网络上被下载和安装，和/或从可拆卸介质611被安装。在该计算机程序被中央处理单元(CPU)601执行时，执行本申请的方法中限定的上述功能。需要说明的是，本申请上述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本申请中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本申请中，计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电 磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：无线、电线、光缆、RF等等，或者上述的任意合适的组合。
附图中的流程图和框图，图示了按照本发明各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本发明实施例中所涉及到的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。所描述的单元也可以设置在处理器中，例如，可以描述为：一种处理器包括获取单元、第一判断单元、确定单元和第一标记单元。其中，这些单元的名称在某种情况下并不构成对该单元本身的限定。例如，获取单元还可以被描述为“获取无人驾驶车辆的车辆数据的单元”。
作为另一方面，本申请还提供了一种计算机可读介质，该计算机可读介质可以是上述实施例中描述的装置中所包含的；也可以是单独存在，而未装配入该装置中。上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该装置执行时，使得该装置：获取无人驾驶车辆的车辆数据；基于车辆数据，判断无人驾驶车辆是否从无人驾驶模式切换到人工驾驶模式；响应于确定无人驾驶车辆切换到人工驾驶模式，确定切换到人工驾驶模式的切换时刻；将切换时刻 之前预设时段内获取的车辆数据标记为负样本。
以上描述仅为本发明的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本发明中所涉及的发明范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述发明构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本发明中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。

Claims (14)

  1. 一种无人驾驶车辆的数据采集方法，其特征在于，所述方法包括：
    获取无人驾驶车辆的车辆数据；
    基于所述车辆数据，判断所述无人驾驶车辆是否从无人驾驶模式切换到人工驾驶模式；
    响应于确定所述无人驾驶车辆切换到人工驾驶模式，确定切换到人工驾驶模式的切换时刻；
    将所述切换时刻之前预设时段内获取的车辆数据标记为负样本。
  2. 根据权利要求1所述的方法，其特征在于，所述车辆数据包括传感器数据；以及
    所述判断所述无人驾驶车辆是否从无人驾驶模式切换到人工驾驶模式，包括：
    判断所述无人驾驶车辆的方向盘上的压力传感器所采集的压力数据是否大于预设的压力阈值；和/或
    判断所述无人驾驶车辆的方向盘上的温度传感器所采集的温度数据是否大于预设的温度阈值；
    若是，则确定所述无人驾驶车辆从无人驾驶模式切换到人工驾驶模式。
  3. 根据权利要求1所述的方法，其特征在于，所述车辆数据包括预期驾驶数据和实际驾驶数据；以及
    所述判断所述无人驾驶车辆是否从无人驾驶模式切换到人工驾驶模式，包括：
    判断所述预期驾驶数据与所述实际驾驶数据之间的差值是否大于预设的阈值；
    若是，则确定所述无人驾驶车辆从无人驾驶模式切换到人工驾驶模式。
  4. 根据权利要求1-3之一所述的方法，其特征在于，在所述将所述切换时刻之前预设时段内获取的车辆数据标记为负样本之后，所述方法还包括：
    利用所述负样本训练预设的无人驾驶车辆大脑模型，其中，所述无人驾驶车辆大脑模型用于基于车辆数据预测车辆控制指令。
  5. 根据权利要求1所述的方法，其特征在于，所述车辆数据包括距离传感器所采集的所述无人驾驶车辆与障碍物之间的距离；以及
    所述方法还包括：
    当所述距离小于预设的距离阈值时，将所述距离小于所述距离阈值的开始时刻之前的预设时段内获取的车辆数据标记为负样本。
  6. 根据权利要求1所述的方法，其特征在于，所述车辆数据包括路况信息；以及
    所述方法还包括：
    基于所述路况信息，判断所述无人驾驶车辆是否偏离行驶车道；
    若是，则将开始偏离行驶车道时刻之前的预设时段内获取的车辆数据标记为负样本。
  7. 一种无人驾驶车辆的数据采集装置，其特征在于，所述装置包括：
    获取单元，配置用于获取无人驾驶车辆的车辆数据；
    第一判断单元，配置用于基于所述车辆数据，判断所述无人驾驶车辆是否从无人驾驶模式切换到人工驾驶模式；
    确定单元，配置用于响应于确定所述无人驾驶车辆切换到人工驾驶模式，确定切换到人工驾驶模式的切换时刻；
    第一标记单元，配置用于将所述切换时刻之前预设时段内获取的车辆数据标记为负样本。
  8. 根据权利要求7所述的装置，其特征在于，所述车辆数据包括传感器数据；以及
    所述第一判断单元，包括：
    第一判断模块，配置用于判断所述无人驾驶车辆的方向盘上的压力传感器所采集的压力数据是否大于预设的压力阈值；和/或
    第二判断模块，配置用于判断所述无人驾驶车辆的方向盘上的温度传感器所采集的温度数据是否大于预设的温度阈值；
    第一确定模块，配置用于若所述压力数据大于预设的压力阈值和/或所述温度数据大于预设的温度阈值，则确定所述无人驾驶车辆从无人驾驶模式切换到人工驾驶模式。
  9. 根据权利要求7所述的装置，其特征在于，所述车辆数据包括预期驾驶数据和实际驾驶数据；以及
    所述第一判断单元，包括：
    第三判断模块，配置用于判断所述预期驾驶数据与所述实际驾驶数据之间的差值是否大于预设的阈值；
    第二确定模块，配置用于若所述差值大于预设的阈值，则确定所述无人驾驶车辆从无人驾驶模式切换到人工驾驶模式。
  10. 根据权利要求7-9之一所述的装置，其特征在于，所述装置还包括：
    训练单元，配置用于利用所述负样本训练预设的无人驾驶车辆大脑模型，其中，所述无人驾驶车辆大脑模型用于基于车辆数据预测车辆控制指令。
  11. 根据权利要求7所述的装置，其特征在于，所述车辆数据包括距离传感器所采集的所述无人驾驶车辆与障碍物之间的距离；以及
    所述装置还包括：
    第二标记单元，配置用于当所述距离小于预设的距离阈值时，将所述距离小于所述距离阈值的开始时刻之前的预设时段内获取的车辆 数据标记为负样本。
  12. 根据权利要求7所述的装置，其特征在于，所述车辆数据包括路况信息；以及
    所述装置还包括：
    第二判断单元，配置用于基于所述路况信息，判断所述无人驾驶车辆是否偏离行驶车道；
    第三标记单元，配置用于若所述无人驾驶车辆偏离行驶车道，则将开始偏离行驶车道时刻之前的预设时段内获取的车辆数据标记为负样本。
  13. 一种服务器或终端，包括：
    一个或多个处理器；
    存储装置，用于存储一个或多个程序，
    当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如权利要求1-6中任一所述的方法。
  14. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于，该程序被处理器执行时实现如权利要求1-6中任一所述的方法。
PCT/CN2018/098983 2017-09-05 2018-08-06 无人驾驶车辆的数据采集方法和装置 WO2019047650A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710790002.9A CN107571864B (zh) 2017-09-05 2017-09-05 无人驾驶车辆的数据采集方法和装置
CN201710790002.9 2017-09-05

Publications (1)

Publication Number Publication Date
WO2019047650A1 true WO2019047650A1 (zh) 2019-03-14

Family

ID=61030764

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/098983 WO2019047650A1 (zh) 2017-09-05 2018-08-06 无人驾驶车辆的数据采集方法和装置

Country Status (2)

Country Link
CN (1) CN107571864B (zh)
WO (1) WO2019047650A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113665590A (zh) * 2021-09-24 2021-11-19 阿波罗智联(北京)科技有限公司 控制车辆的方法、装置、设备、介质和车辆

Families Citing this family (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107571864B (zh) * 2017-09-05 2019-11-05 百度在线网络技术（北京）有限公司 无人驾驶车辆的数据采集方法和装置
CN108909714A (zh) * 2018-07-26 2018-11-30 南京威尔瑞智能科技有限公司 一种基于无人驾驶汽车驾驶模式快速切换的系统
CN109255341B (zh) * 2018-10-30 2021-08-10 百度在线网络技术（北京）有限公司 障碍物感知错误数据的提取方法、装置、设备及介质
CN109318906B (zh) * 2018-10-30 2021-04-27 奇瑞汽车股份有限公司 智能汽车的接管检测方法、装置及存储介质
CN109334673B (zh) * 2018-10-30 2021-03-02 奇瑞汽车股份有限公司 智能汽车的接管提醒方法、装置及存储介质
CN109298719B (zh) * 2018-12-04 2021-11-02 奇瑞汽车股份有限公司 智能汽车的接管方法、装置及存储介质
CN111325230B (zh) * 2018-12-17 2023-09-12 上海汽车集团股份有限公司 车辆换道决策模型的在线学习方法和在线学习装置
CN110221605A (zh) * 2019-05-16 2019-09-10 厦门理工学院 无人驾驶汽车的会车方法、装置、设备及存储介质
CN110481630B (zh) * 2019-08-21 2021-07-20 同济大学 一种基于电子皮肤技术的方向盘及交互方法
CN110708504A (zh) * 2019-09-06 2020-01-17 北京智行者科技有限公司 基于平行驾驶的数据处理方法及系统
CN110745143B (zh) * 2019-10-29 2021-08-24 广州文远知行科技有限公司 一种车辆的控制方法、装置、设备和存储介质
CN111026111A (zh) * 2019-11-29 2020-04-17 上海电机学院 一种基于5g网络的汽车智能驾驶控制系统
MX2023000973A (es) * 2020-07-23 2023-03-01 Huawei Tech Co Ltd Metodo y aparato para controlar el cambio de modo de conduccion de vehiculo.

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006044395A (ja) * 2004-08-02 2006-02-16 Yamaha Motor Co Ltd 有人無人運転切替走行車両
CN105711591A (zh) * 2016-04-26 2016-06-29 百度在线网络技术（北京）有限公司 无人驾驶车辆、无人驾驶车辆的控制方法和装置
CN106809216A (zh) * 2015-11-27 2017-06-09 鸿富锦精密工业（深圳）有限公司 车辆驾驶模式切换系统和方法
CN106985907A (zh) * 2015-11-06 2017-07-28 本田技研工业株式会社 接触判定处理装置
CN107491073A (zh) * 2017-09-05 2017-12-19 百度在线网络技术（北京）有限公司 无人驾驶车辆的数据训练方法和装置
CN107571864A (zh) * 2017-09-05 2018-01-12 百度在线网络技术（北京）有限公司 无人驾驶车辆的数据采集方法和装置

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9815475B2 (en) * 2015-11-24 2017-11-14 Accenture Global Solutions Limited Analytics platform for identifying a roadway anomaly
CN106080606B (zh) * 2016-07-08 2019-01-01 百度在线网络技术（北京）有限公司 用于控制无人驾驶车辆的方法和装置
CN106218639B (zh) * 2016-07-20 2019-01-11 百度在线网络技术（北京）有限公司 无人驾驶车辆、用于控制无人驾驶车辆的方法和装置
CN107123175A (zh) * 2017-03-31 2017-09-01 百度在线网络技术（北京）有限公司 一种记录驾驶信息的方法、装置和系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006044395A (ja) * 2004-08-02 2006-02-16 Yamaha Motor Co Ltd 有人無人運転切替走行車両
CN106985907A (zh) * 2015-11-06 2017-07-28 本田技研工业株式会社 接触判定处理装置
CN106809216A (zh) * 2015-11-27 2017-06-09 鸿富锦精密工业（深圳）有限公司 车辆驾驶模式切换系统和方法
CN105711591A (zh) * 2016-04-26 2016-06-29 百度在线网络技术（北京）有限公司 无人驾驶车辆、无人驾驶车辆的控制方法和装置
CN107491073A (zh) * 2017-09-05 2017-12-19 百度在线网络技术（北京）有限公司 无人驾驶车辆的数据训练方法和装置
CN107571864A (zh) * 2017-09-05 2018-01-12 百度在线网络技术（北京）有限公司 无人驾驶车辆的数据采集方法和装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113665590A (zh) * 2021-09-24 2021-11-19 阿波罗智联(北京)科技有限公司 控制车辆的方法、装置、设备、介质和车辆
CN113665590B (zh) * 2021-09-24 2024-04-19 阿波罗智联(北京)科技有限公司 控制车辆的方法、装置、设备、介质和车辆

Also Published As

Publication number Publication date
CN107571864A (zh) 2018-01-12
CN107571864B (zh) 2019-11-05

Similar Documents

Publication Publication Date Title
WO2019047650A1 (zh) 无人驾驶车辆的数据采集方法和装置
US11130501B2 (en) System, method and apparatus for controlling autonomous driving vehicle
CN106218639B (zh) 无人驾驶车辆、用于控制无人驾驶车辆的方法和装置
CN107491073B (zh) 无人驾驶车辆的数据训练方法和装置
US11842638B2 (en) Parallel remote control driving system for intelligent network vehicle
US10642268B2 (en) Method and apparatus for generating automatic driving strategy
WO2019047656A1 (zh) 用于控制无人驾驶车辆的方法和装置
CN107491072B (zh) 车辆避障方法和装置
CN107063713B (zh) 应用于无人驾驶汽车的测试方法和装置
CN108919785B (zh) 一种测试系统及测试方法
CN106154834B (zh) 用于控制无人驾驶车辆的方法和装置
CN109709966B (zh) 用于无人车的控制方法和装置
WO2020259705A1 (en) Autonomous driving handoff systems and methods
CN109064763A (zh) 自动驾驶车辆的测试方法、装置、测试设备和存储介质
CN109255341A (zh) 障碍物感知错误数据的提取方法、装置、设备及介质
CN110696826B (zh) 用于控制车辆的方法和装置
WO2023226733A1 (zh) 车辆场景数据的采集方法、装置、存储介质及电子设备
CN112071066A (zh) 自动驾驶车辆测试方法、判断方法及装置
CN111882924A (zh) 车辆测试系统、驾驶行为判断控制方法及事故预警方法
CN110745143B (zh) 一种车辆的控制方法、装置、设备和存储介质
CN112415910A (zh) 用于评价SiL环境的软件组件的方法
CN117131589A (zh) 智能网联车辆协同算法的仿真测试方法及装置
CN110659696A (zh) 用于检测行车安全的方法及装置
US11454966B2 (en) Programmatic application of router flags for vehicle limitations
CN115346288A (zh) 仿真行车记录采集方法、系统、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: 18853947

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 11/08/2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18853947

Country of ref document: EP

Kind code of ref document: A1