WO2023273780A1 - 车辆定位方法、装置、电子设备和存储介质 - Google Patents

车辆定位方法、装置、电子设备和存储介质 Download PDF

Info

Publication number
WO2023273780A1
WO2023273780A1 PCT/CN2022/096647 CN2022096647W WO2023273780A1 WO 2023273780 A1 WO2023273780 A1 WO 2023273780A1 CN 2022096647 W CN2022096647 W CN 2022096647W WO 2023273780 A1 WO2023273780 A1 WO 2023273780A1
Authority
WO
WIPO (PCT)
Prior art keywords
lane
vehicle
information
perceived
guardrail
Prior art date
Application number
PCT/CN2022/096647
Other languages
English (en)
French (fr)
Inventor
韩佐悦
王子涵
Original Assignee
驭势（上海）汽车科技有限公司
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 驭势（上海）汽车科技有限公司 filed Critical 驭势（上海）汽车科技有限公司
Priority to KR1020237045521A priority Critical patent/KR102662425B1/ko
Priority to EP22831601.4A priority patent/EP4365048A1/en
Publication of WO2023273780A1 publication Critical patent/WO2023273780A1/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
    • 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
    • B60W40/02—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 ambient conditions
    • B60W40/04—Traffic conditions
    • 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
    • B60W40/02—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 ambient conditions
    • B60W40/06—Road conditions
    • 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
    • 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
    • B60W2050/0001—Details of the control system
    • B60W2050/0002—Automatic control, details of type of controller or control system architecture
    • B60W2050/0004—In digital systems, e.g. discrete-time systems involving sampling
    • B60W2050/0005—Processor details or data handling, e.g. memory registers or chip architecture
    • 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
    • B60W2520/14—Yaw
    • 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
    • B60W2540/00—Input parameters relating to occupants
    • B60W2540/18—Steering angle
    • 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
    • B60W2552/00—Input parameters relating to infrastructure
    • B60W2552/50—Barriers
    • 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
    • B60W2552/00—Input parameters relating to infrastructure
    • B60W2552/53—Road markings, e.g. lane marker or crosswalk

Definitions

  • Embodiments of the present disclosure relate to the technical field of trailers, and in particular, relate to a vehicle positioning method, device, electronic equipment, and storage medium.
  • Self-driving cars can reduce traffic congestion, improve traffic efficiency, release hands and improve social productivity, so its related technologies have received widespread attention.
  • Sensors such as cameras, lidars, and millimeter-wave radars equipped on cars can perceive the surrounding road environment and quickly and accurately obtain information such as their own position and the position, size, and direction of movement of surrounding targets, which can ensure the safety and stability of unmanned vehicles. driving on the road.
  • the automatic driving system needs to accurately locate the position of the vehicle during operation to plan the driving route.
  • Using traditional civilian GPS to locate vehicles its accuracy can only determine the road where it is located, and cannot accurately obtain the lane where it is located. This will affect the misjudgment of the driving route and lane change needs of the self-driving vehicle.
  • the use of RTK (Real Time Kinematic, real-time dynamic) and other high-precision positioning equipment to obtain accurate positions requires the accuracy of high-precision maps, which is costly and limited in scope of use.
  • the traditional lane positioning method is difficult to cope with complex environments, such as road conditions such as blurred road edges, target occlusion, and lighting changes, and its stability and anti-interference ability are poor.
  • At least one embodiment of the present disclosure provides a vehicle positioning method, device, electronic device and storage medium.
  • the embodiment of the present disclosure proposes a vehicle positioning method, including:
  • the embodiment of the present disclosure further proposes a vehicle positioning device, including: an initialization module, configured to determine the current positioning lane based on the current position information of the vehicle, the road information perceived by the vehicle, and the map information;
  • the positioning monitoring module is used to compare the real-time acquired vehicle perception road information with the current positioning lane to determine the mismatch integral value
  • a judging module configured to determine whether the mismatch integral value is greater than or equal to a preset integral value, and if so, instruct the initialization module to perform the operation of determining the current positioning lane based on the vehicle's current position information, vehicle perceived road information, and map information again.
  • an embodiment of the present disclosure also provides an electronic device, including: a processor and a memory;
  • the processor is used to execute the steps of the method according to the first aspect by invoking the programs or instructions stored in the memory.
  • the embodiments of the present disclosure also provide a computer-readable storage medium for storing a program or an instruction, and the program or instruction causes the computer to execute the steps of the method described in the first aspect.
  • the current positioning lane is firstly determined based on the vehicle's current position information, the vehicle's perceived road information, and the map information line, that is, the initial vehicle lane positioning is performed first. Then compare the real-time vehicle perception road information with the current positioning lane to determine the mismatch integral value. This step is actually monitoring the lane positioning, analyzing discrepancies between the vehicle perception road information acquired in real time and the current positioning lane, and determining the mismatch integral value.
  • the embodiments of the present disclosure do not need RTK high-precision positioning, and the implementation cost is low.
  • the mismatch integral value is determined by comparing the real-time acquired vehicle perceived road information with the current positioning lane, Continuously monitor whether the positioning lane is correct, which improves the stability of lane positioning and anti-interference ability.
  • FIG. 1 is a schematic flowchart of a vehicle positioning method provided by an embodiment of the present disclosure
  • Fig. 2 is a kind of two-lane schematic diagram
  • Fig. 3 is a schematic diagram of three lanes
  • Fig. 4 is a schematic diagram of four lanes
  • Fig. 5 is a schematic diagram of the number of lanes being 2 and a moving vehicle on the left;
  • Fig. 6 is a schematic diagram showing that the number of lanes is 2 and there is a moving vehicle on the right side;
  • Fig. 7 is a schematic diagram showing that the number of lanes is 3 and there is a moving vehicle on the left;
  • Fig. 8 is a schematic diagram showing that the number of lanes is 3 and there is a moving vehicle on the right side;
  • Fig. 9 is a schematic diagram showing that the number of lanes is 3 and there are moving vehicles on the left and right sides;
  • FIG. 10 is a schematic flowchart of another vehicle positioning method provided by an embodiment of the present disclosure.
  • FIG. 11 is a schematic diagram of a vehicle changing lanes provided by an embodiment of the present disclosure.
  • Fig. 12 is a structural block diagram of a vehicle positioning device provided by an embodiment of the present disclosure.
  • Fig. 13 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.
  • Fig. 1 is a schematic flowchart of a vehicle positioning method provided by an embodiment of the present disclosure. As shown in Figure 1, the vehicle positioning method provided by the embodiment of the present disclosure includes S110 to S130:
  • the vehicle may be provided with a positioning device, such as a Global Positioning System (Global Positioning System, GPS) positioning device, an inertial measurement unit (Inertial Measurement Unit, IMU) and the like.
  • the global positioning system positioning device can obtain satellite signals, calculate the latitude and longitude information in real time, and determine the current position information of the vehicle according to the latitude and longitude information.
  • the current location information of the vehicle may include, for example, the road where the vehicle is located and the driving direction. After determining the road where the vehicle is located and the direction of travel, etc., the information on the total number of lanes corresponding to the current road, whether there is an emergency lane, etc. can be read according to the map information (for convenience of description, the subsequent collectively referred to as the lane model).
  • the collecting device in this embodiment can collect road information perceived by the vehicle.
  • Vehicle perceived road information includes, but is not limited to, perceived lane line information, perceived guardrail information, and surrounding vehicle information.
  • Perceived guardrail information may include, for example, the lateral position, slope, curvature, confidence, etc. of the guardrail.
  • Perceived lane line information may include, for example, the lateral distance, slope, curvature, line type (solid line, dashed line), confidence level, etc. of the lane line.
  • the surrounding vehicle information may include, for example, the longitudinal position, lateral position, and longitudinal speed of the moving vehicle.
  • the road information perceived by the vehicle refers to the real road information near the location of the vehicle acquired by the acquisition device in real time.
  • the current location information of the vehicle is obtained first, the lane model corresponding to the map information is searched according to the current location information of the vehicle, and then which lane of the lane model the vehicle is currently in is preliminarily determined according to the road information sensed by the vehicle. For example, according to the current position information of the vehicle and the map information, it is determined that the lane model corresponding to the road where the vehicle is currently located is 3 lanes.
  • the perceived lane line information in the vehicle perceived road information is that the second left lane line is a solid line, the left one lane line is a dotted line, the right one lane line is a dotted line, and the right second lane line is a solid line.
  • the current positioning lane is the middle lane.
  • S110 determines the current positioning lane based on the vehicle's current location information, the vehicle's perceived road information, and map information, including:
  • the generated lane score table is a 3x1 array for storing the score value of each lane.
  • the lanes that meet the conditions are integrated according to the integration rules, and the integration results are saved in the lane integration table. If the integral value of a certain lane in the lane integral table exceeds the first preset value, it is judged that the current vehicle is in the lane, and the vehicle positioning is completed. If the integral value of each lane does not exceed the first preset value, the integral is continued.
  • the process of determining the current positioning lane based on the vehicle's current position information, the vehicle's perceived road information, and the map information also includes clearing the lane score table after determining that the number of current lanes changes.
  • the vehicle's perceived road information includes perceived lane line information and perceived guardrail information.
  • S112 determines the integral value of each lane in the lane integral table based on vehicle perception road information, including:
  • the lane information corresponding to the location is determined from the map information, such as the number of lanes, lane line information, guardrail information, etc., and a lane score table is established. Integral calculation is performed according to the preset first integral rule, the sensed lane line information and the sensed guardrail information, and the integral value of each lane in the lane integral table is determined.
  • the first scoring rule can be set according to the number of lanes, for example, based on the total number of lanes, it can be divided into single lane, two lanes, three lanes, four lanes or more.
  • the embodiment of the present disclosure integrates the sensed lane line information and guardrail information.
  • the first scoring rule corresponding to the number of lanes being 1 is: if the vehicle perceives road information as a solid line on one side of the lane and there is a guardrail on the left side, then the single lane on which it is located will be given extra points. For the case where the number of lanes is 1, that is, a single lane, the comprehensively perceived lane line information and guardrail information are integrated. When the vehicle perceives that the lane line on the right side is a solid line and there is a guardrail on the left side in the road information, it will add points to the single lane it is in.
  • the first scoring rule corresponding to the number of lanes being 2 is: if the perceived lane line information and perceived guardrail information are solid lines for the left nearest neighbor lane line and dashed line for the right nearest neighbor lane line, then the left lane will add points; the sensed lane line If there is a guardrail on the left and the nearest neighbor lane line on the right is a dotted line, then the left lane will add points; if the information on the perceived lane line and the perceived guardrail information is that the nearest neighbor lane line on the right is a solid line, and the If the nearest neighbor lane line is a dotted line, the right lane will gain points; if the perceived lane line information and perceived guardrail information indicate that there is a guardrail on the right side and the left nearest neighbor lane line is a dotted line, then the right lane will gain points.
  • FIG. 2 is a schematic diagram of a dual-lane, where the left lane of the dual-lane is set as lane 2 and the right lane is lane 1.
  • the perceived lane line information and the perceived guardrail information are that the left nearest neighbor lane line is a solid line and the right nearest neighbor lane line is a dashed line, then it means that the real lane where the current vehicle is located is more in line with the left lane, that is, lane 2, then for Extra points for the left lane.
  • the perceived lane line information and perceived guardrail information indicate that there is a guardrail on the left, and the nearest neighbor lane line on the right is a dotted line, it means that the real lane where the current vehicle is located is more suitable for the left lane, that is, lane 2, then add point.
  • the perceived lane line information and the perceived guardrail information are that the nearest neighbor lane line on the right is a solid line, and the nearest neighbor lane line on the left is a dotted line, it means that the real lane where the current vehicle is located is more in line with the right lane, that is, lane 1, then Bonus points for the right lane.
  • the perceived lane line information and perceived guardrail information show that there is a guardrail on the right side and the nearest neighbor lane line on the left side is a dotted line, then it means that the real lane where the current vehicle is located is more suitable for the right lane, that is, lane 1, then add points to the right lane .
  • the nearest adjacent lane line on the left side of the vehicle refers to the left one lane line
  • the nearest adjacent lane line on the right side of the vehicle refers to the right one lane line
  • the first scoring rule corresponding to the number of lanes is 3: the perceived lane line information and the perceived guardrail information are dashed lines on the left and right sides and there is no guardrail, then the middle lane will add points; the perceived lane line information and the perceived guardrail information are If the left nearest neighbor lane line is a solid line, the right nearest neighbor lane line is a dotted line and there is no right guardrail, then the left lane will add points; the perceived lane line information and perceived guardrail information indicate that there is a guardrail on the left and the right nearest neighbor lane If the line is a dotted line and there is no right guardrail, then the left lane will add points; if the perceived lane line information and perceived guardrail information is that the right nearest neighbor lane line is a solid line, and the left nearest neighbor lane line is a dotted line and there is no guardrail on the left, then Bonus points for the right lane.
  • Fig. 3 is a schematic diagram of three lanes, where the left lane of the three lanes is set as lane 3, the right lane is lane 1, and the middle lane is lane 2.
  • the perceived lane line information and perceived guardrail information show that the nearest neighbor lane lines on the left and right sides are all dotted lines and there is no guardrail, then it means that the real lane where the current vehicle is located is more suitable for being in the middle lane, that is, lane 2, and the middle lane will be given extra points.
  • the perceived lane line information and perceived guardrail information are that the left nearest neighbor lane line is a solid line, the right nearest neighbor lane line is a dotted line and there is no right guardrail, then it means that the real lane where the current vehicle is located is more in line with the left lane, that is Lane 3, then add points to the left lane.
  • the perceived lane line information and the perceived guardrail information indicate that there is a guardrail on the left, and the nearest neighbor lane line on the right is a dotted line and there is no right guardrail, then it means that the real lane where the current vehicle is located is more in line with the left lane, that is, lane 3. Extra points for the left lane.
  • the perceived lane line information and perceived guardrail information are that the nearest neighbor lane line on the right is a solid line, the nearest neighbor lane line on the left is a dotted line, and there is no guardrail on the left, then the real lane where the current vehicle is located is more in line with the right lane, that is Lane 1, add points to the right lane.
  • the first integral rule corresponding to the number of lanes greater than or equal to 4 is: the perception of lane line information and the perception of guardrail information is that the left nearest neighbor lane line is a solid line, the right nearest neighbor lane line is a dashed line and there is no right guardrail, then the leftmost lane Bonus points; perception of lane line information and perception guardrail information means that there is a guardrail on the left, and the nearest neighbor lane line on the right is a dotted line and there is no right guardrail, then the leftmost lane will add points; perception of lane line information and perception of guardrail information is the closest on the right If the adjacent lane line is a solid line, the nearest neighbor lane line on the left is a dotted line, and there is no guardrail on the left side, then the rightmost lane will add points; the perceived lane line information and perceived guardrail information are that the nearest neighbor lane lines on the left and right sides are all dotted lines and If there is no guardrail, compare the perceived lane line information and perceived guardrail information
  • FIG. 4 is a schematic diagram of four lanes.
  • An exemplary setting of four lanes is lane 1, lane 2, lane 3, and lane 4 from right to left.
  • the perceived lane line information and perceived guardrail information are that the left nearest neighbor lane line is a solid line, and the right nearest neighbor lane line is a dotted line without a right guardrail, it means that the real lane where the current vehicle is located is more in line with the leftmost lane, that is Lane 4, then add points to the left lane.
  • the perceived lane line information and perceived guardrail information show that there is a guardrail on the left, and the nearest neighbor lane line on the right is a dotted line without a right guardrail, it means that the real lane where the current vehicle is located is more in line with the leftmost lane, that is, lane 4. Extra points for the left lane.
  • the perceived lane line information and perceived guardrail information show that the nearest neighbor lane line on the right is a solid line, the nearest neighbor lane line on the left is a dashed line, and there is no guardrail on the left side, it means that the real lane where the current vehicle is located is more in line with the rightmost lane. That is, lane 1, then add points to the right lane.
  • the perceived lane line information and perceived guardrail information show that the nearest neighbor lane lines on the left and right sides are all dotted lines and there is no guardrail, it means that the real lane where the current vehicle is located is more in line with the lane in the middle, such as lane 2 or lane 3. Then compare the perceived lane line information and perceived guardrail information with the lane lines of the middle lanes, and add points to the middle lanes that are consistent.
  • comparing the perceived lane line information and the perceived guardrail information with the lane lines of the lanes in the middle can be done by traversing the middle lanes.
  • the perceived lane line information and the perceived guardrail information can be compared with the lane lines on both sides of lane 2.
  • Lane line comparison if the comparison is consistent, add points to lane 2. If not, compare the perceived lane line information and perceived guardrail information with the lane lines on both sides of lane 3, and if the comparison is consistent, add points to lane 3. If not, no points will be added for the time being.
  • the vehicle's perceived road information may also include surrounding vehicle information, determine the number of lanes in the map information corresponding to the vehicle's current position information, and based on the first integral rule corresponding to the number of lanes, perceived lane line information, and perceived guardrails After the information determines the integral value of each lane in the lane integral table, it may also include:
  • the integral value of each lane in the lane integral table is updated based on the second integral rule corresponding to the number of lanes and the surrounding vehicle information.
  • the embodiments of the present disclosure may also correct the integral value of each lane in the lane integral table according to the sensed surrounding vehicle information.
  • the surrounding vehicle information can be obtained through cameras, lidar and other devices, and the lanes that meet the conditions can be integrated according to the second integral rule corresponding to the number of lanes, and the integral value of each lane in the lane integral table can be updated.
  • the second integral rule corresponding to the number of lanes is 2: if the surrounding vehicle information recognizes that there is a moving vehicle on the left and the lateral distance from the current vehicle is greater than the second preset value, then add points to the right lane; In order to recognize that there is a moving vehicle on the right and the lateral distance from the current vehicle is greater than a second preset value, points are added to the left lane.
  • the surrounding vehicle information indicates that there is a moving vehicle on the left side, it means that the moving vehicle is on the left side of the vehicle.
  • the recognized lateral distance h between the left moving vehicle and the current vehicle is greater than the second preset value, it means that the left moving vehicle is not in the same lane as the current vehicle.
  • the second preset value can be set according to an actual road scene. At this time, it means that the real lane where the current vehicle is located is more suitable for being located in the right lane, that is, lane 1, and the right lane will be given extra points.
  • the surrounding vehicle information indicates that there is a moving vehicle on the right side, it means that the moving vehicle is on the right side of the vehicle. If the recognized lateral distance h between the moving vehicle on the right and the current vehicle is greater than the second preset value, it means that the moving vehicle on the right is not in the same lane as the current vehicle. At this time, it shows that the real lane where the current vehicle is located is relatively in line with the left lane, that is, lane 2, and the left lane will be given extra points.
  • the second integral rule corresponding to the number of lanes greater than or equal to 3 is: if the surrounding vehicle information recognizes that there is a moving vehicle on the left and the lateral distance from the current vehicle is greater than the second preset value, then the score for the leftmost lane will be reduced; the surrounding vehicle information In order to recognize that there is a moving vehicle on the right side and the lateral distance from the current vehicle is greater than the second preset value, the score for the rightmost lane is reduced; if the number of lanes is equal to 3, the surrounding vehicle information is that moving vehicles are recognized on the left and right sides and If the lateral distance from the current vehicle is greater than the second preset value, points will be added to the middle lane.
  • the surrounding vehicle information indicates that there is a moving vehicle on the left, it means that the moving vehicle is on the left side of the vehicle.
  • the identified lateral distance h between the left moving vehicle and the current vehicle is greater than the second preset value, indicating that the left moving vehicle is not in the same lane as the current vehicle. Then it means that the current vehicle cannot be located in the leftmost lane, so the points for the leftmost lane (lane 3 in FIG. 7 ) are deducted.
  • the surrounding vehicle information indicates that there is a moving vehicle on the right side, it means that the moving vehicle is on the right side of the vehicle.
  • the recognized lateral distance h between the moving vehicle on the right and the current vehicle is greater than the second preset value, indicating that the moving vehicle on the right is not in the same lane as the current vehicle. Then it means that the current vehicle cannot be located in the rightmost lane, so the score for the rightmost lane (lane 1 in FIG. 8 ) is deducted.
  • the surrounding vehicle information is that moving vehicles are recognized on the left and right sides and the lateral distance from the current vehicle is greater than the second preset value, then it means that the current vehicle is in a lane in the middle, but it is not sure which middle lane it is , as shown in Figure 9, if the number of lanes is equal to 3, and there is only one middle lane, if the surrounding vehicle information is that moving vehicles are recognized on both sides of the left and right sides and the lateral distance from the current vehicle is greater than the second preset value, then the current vehicle is in In the middle lane, add points to the middle lane.
  • the lower limit of the integral value of each lane in the lane point table is controlled at zero, that is, after the integral value is zero, no point reduction operation will be performed.
  • the lateral distance between the moving vehicle and the current vehicle can be determined to be greater than the second preset After the duration of the value is greater than the first preset time, the operation of updating the integral value of each lane in the lane integral table based on the second integral rule corresponding to the number of lanes and the surrounding vehicle information is performed.
  • This setting can avoid misjudgment caused by short-term fluctuations in sensor detection data.
  • the vehicle After the vehicle completes the preliminary lane positioning, it continuously monitors the current positioning lane. In this step, the vehicle-perceived road information is obtained in real time, and the real-time obtained vehicle-perceived road information is compared with the current positioning lane determined at the previous moment, and the mismatch integral value is determined according to the comparison result. In this step, you can set the comparative integral rules according to actual needs. For example, different comparison integral rules may be specified for different current positioning lanes, and if the comparison integral rule is met, the mismatch integral value shall be increased by 1.
  • comparing the vehicle perceived road information acquired in real time with the current positioning lane, and determining the mismatch integral value includes: determining the mismatch based on the third integral rule corresponding to the current positioning lane and the vehicle perceived road information acquired in real time points value.
  • the type of the current positioning lane corresponds to different third integration rules, for example, the left lane, the right lane, and the middle lane correspond to different third integration rules.
  • the third integral rule corresponding to the current positioning lane being the leftmost lane is as follows: the vehicle perceived road information obtained in real time shows that the nearest neighbor lane line on the left is a dotted line and there is no guardrail on the left side, and the mismatch integral value is increased; the vehicle acquired in real time The perceived road information is that there is a guardrail on the right side and the total number of lanes is greater than 1, and the mismatch integral value is increased.
  • the third integral rule corresponding to the current positioning lane being the rightmost lane is: the real-time acquired vehicle perceived road information is that the nearest neighbor lane line on the right is a dotted line and there is no guardrail on the right side, and the mismatch integral value is increased; the real-time acquired vehicle Perceived road information is that there is a guardrail on the left and the total number of lanes is greater than 1, and the mismatch integral value is increased.
  • the third integral rule corresponding to the current positioning lane being the middle lane is: the real-time acquired vehicle perception road information is that the distance between the second lane line on the left and the current vehicle is less than the first threshold, and the second lane line on the left is real line, increase the mismatch integral value; the vehicle perceived road information obtained in real time is that the distance between the second lane line on the right and the current vehicle is less than the first threshold, and the second lane line on the right is a solid line, increase the mismatch integral value ;
  • the vehicle perceived road information obtained in real time is that there is a guardrail on the left side, and the distance between the guardrail and the current vehicle is less than the second threshold, and the mismatch integral value is increased;
  • the real-time acquired vehicle perceived road information is that there is a guardrail on the right side, and the distance between the guardrail and the current vehicle The current distance between the vehicles is smaller than the second threshold, and the mismatch integral value is increased.
  • the current positioning lane is the leftmost lane, and the real-time vehicle perception road information shows that the nearest neighbor lane line on the left is a dotted line and there is no guardrail on the left side, predict the actual lane where the current vehicle is based on the real-time vehicle perception road information If it is not in the leftmost lane, it means that the actual lane of the current vehicle does not match the current positioning lane, so the mismatch integral value of the current positioning lane is increased.
  • the current positioning lane is the leftmost lane, and the real-time vehicle perception road information shows that there is a guardrail on the right side and the total number of lanes is greater than 1, it is predicted that the actual lane of the current vehicle is not in the leftmost lane according to the real-time vehicle perception road information , indicating that the actual lane of the current vehicle does not match the current positioning lane, so the mismatch integral value of the current positioning lane is increased.
  • the current positioning lane is the rightmost lane, and the real-time vehicle perception road information is that the nearest neighbor lane line on the right is a dotted line and there is no guardrail on the right side, predict the actual lane where the current vehicle is based on the real-time vehicle perception road information If it is not in the rightmost lane, it means that the actual lane of the current vehicle does not match the current positioning lane, so the mismatch integral value of the current positioning lane is increased.
  • the current positioning lane is the rightmost lane, and the real-time vehicle perception road information shows that there is a guardrail on the left side and the total number of lanes is greater than 1, it is predicted that the actual lane of the current vehicle is not in the rightmost lane according to the real-time vehicle perception road information , indicating that the actual lane of the current vehicle does not match the current positioning lane, so the mismatch integral value of the current positioning lane is increased.
  • the vehicle-perceived road information obtained in real time is that the distance between the second left lane line and the current vehicle is less than the first threshold, and the second left lane line is a solid line, according to the real-time acquired
  • the vehicle perception road information predicts that the actual lane of the current vehicle is not in the middle lane, indicating that the actual lane of the current vehicle does not match the current positioning lane, so the mismatch integral value of the current positioning lane is increased.
  • the vehicle-perceived road information obtained in real time is that the distance between the second lane line on the right and the current vehicle is less than the first threshold, and the second lane line on the right is a solid line, according to the real-time acquisition
  • the vehicle perception road information predicts that the actual lane of the current vehicle is not in the middle lane, indicating that the actual lane of the current vehicle does not match the current positioning lane, so the mismatch integral value of the current positioning lane is increased.
  • the vehicle-perceived road information acquired in real time shows that there is a guardrail on the left, and the distance between the guardrail and the current vehicle is less than the second threshold, predict the actual vehicle location of the current vehicle based on the real-time acquired vehicle-perceived road information. If the lane is not in the middle lane, it means that the actual lane of the current vehicle does not match the current positioning lane, so the mismatch integral value of the current positioning lane is increased.
  • the vehicle-perceived road information obtained in real time shows that there is a guardrail on the right side, and the distance between the guardrail and the current vehicle is less than the second threshold, predict the actual location of the current vehicle according to the real-time acquired vehicle-perceived road information. If the lane is not in the middle lane, it means that the actual lane of the current vehicle does not match the current positioning lane, so the mismatch integral value of the current positioning lane is increased.
  • the mismatch integral value may be cleared to zero. Before comparing the real-time vehicle perception road information with the current positioning lane, the mismatch integral value is zero. However, short-term fluctuations in sensor detection data may lead to misjudgment. In order to prevent this situation, after determining that the real-time vehicle perception road information does not meet any of the third integral rules, the mismatch integral value is cleared. .
  • the initial lane positioning is firstly performed based on the vehicle's current position information, the vehicle's perceived road information, and the map information.
  • the current positioning lane is first determined, and then the lane positioning is monitored. Compare and determine the mismatch integral value. If the mismatch integral value is greater than or equal to the preset integral value, it means that the positioning lane positioning at this time has failed, and the positioning lane needs to be re-determined, then return to re-determining the positioning lane based on the vehicle's current position information, vehicle perception road information, and map information.
  • the embodiment of the present disclosure does not need RTK high-precision positioning, so the implementation cost is low.
  • the mismatch integral value is determined by comparing the road information acquired in real time with the road perception information of the vehicle and the current positioning lane. Monitor whether the positioning lane is correct. After the mismatch integral value is greater than or equal to the preset integral value, firstly determine the current positioning lane based on the vehicle's current position information, vehicle perception road information and map information. Therefore, compared with the prior art, which is only based on the matching of the lane line type perceived by the camera and the map information, the stability of lane positioning and the anti-interference ability can be improved.
  • the vehicle positioning method may further include: S140 to S160:
  • mismatch integral value is less than the preset integral value, it means that the current positioning lane is more consistent with the road information sensed by the vehicle. Therefore, the embodiments of the present disclosure continue to monitor the vehicle steering to determine whether the vehicle is in a steering state.
  • determining whether the vehicle is in a steering state may include determining whether the vehicle is in a steering state based on a steering wheel angle and/or a yaw rate signal.
  • the steering wheel angle and/or yaw rate signal of the vehicle may be read from the chassis system, and when one of the steering wheel angle and yaw rate signal exceeds a threshold value, the vehicle is determined to be in a steering state.
  • a lane change sign is generated after the vehicle is determined to have changed lanes. If the vehicle is in a turning state, and the vehicle perceives road information acquired by a camera and other acquisition devices, it is found that the vehicle has changed lanes, then a lane change sign is generated for subsequent update of the positioning lane.
  • the lane change sign includes, for example, a lane change to the left and a lane change to the right.
  • determining whether the vehicle has changed lanes according to the vehicle's perceived road information, and generating a lane change sign after determining that the vehicle has changed lanes includes:
  • FIG. 11 is a schematic diagram of a vehicle lane change provided by an embodiment of the present disclosure. As shown in FIG. 11 , taking 3 lanes as an example, lane lines are denoted as n1, n2, n3, and n4 from left to right. The vehicle was in lane 2 at the previous moment, the left lane line of the vehicle is n2, and the right lane line is n3. The vehicle gradually changes lanes from lane 2 to lane 1.
  • the first left lane of the vehicle is n2, the second left lane is n1, the right first lane is n3, and the second right lane is n4.
  • the following takes the distance between the lane line and the vehicle as the distance between the lane line and the central axis of the vehicle as an example for detailed introduction.
  • the vehicle changes lanes to lane 1, the vehicle gradually approaches lane line n2.
  • the distance d1 between the left lane line n2 and the central axis of the vehicle gradually decreases from 1.7m to 0.
  • the distance d2 between the right lane line n3 and the vehicle central axis gradually decreases from -1.7m to -3.4m.
  • n1 becomes the left lane line
  • n2 becomes the right lane line (the left lane line before the lane change).
  • the distance between at least one lane line and the current vehicle in the vehicle's perceived road information changes, it means that the vehicle has changed lanes.
  • the wire of the second car on the left becomes the line of the first lane on the left, indicating that the vehicle is changing lanes to the left, so a lane-changing sign to change lanes to the left is generated.
  • the vehicle when the distance between the left and right lane lines and the current vehicle jumps in the road information perceived by the vehicle, it can be determined that the vehicle is changing lanes. In other implementations, in order to prevent asynchronous signal transmission during the signal collection process, it is also possible to determine that the vehicle has changed lanes when the distance between at least one lane line and the current vehicle in the vehicle's perceived road information changes.
  • the current positioning lane is updated in real time based on map information and lane change signs.
  • the map information includes, for example, information such as the total number of lanes where the vehicle is located. Still taking Figure 11 as an example, the current positioning lane determined at the last moment is lane 2. During the lane change monitoring process, if the vehicle is found to change lanes to the left, then the current positioning lane is updated as lane 1.
  • the lane numbers it is also possible to set the lane numbers to increase sequentially from right to left. If the lane number is named as shown in Figure 3, if it is found that n lanes are added to the right side of the current positioning lane of the vehicle according to the map information, then the current positioning lane is added by n; If it is found from the map information that the total number of lanes remains unchanged, the current positioning lane remains unchanged. The increase or decrease of the left lane number of the vehicle's current positioning lane does not affect the result of the current positioning lane. In addition, this embodiment does not limit the naming order of the serial numbers of the lane lines.
  • the generation times of two adjacent lane change signs are separated by at least a second preset time.
  • the acquisition device Since it takes a certain amount of time for the vehicle to change lanes normally, for example, 5 seconds, if the distance between the lane line and the current vehicle is detected to jump frequently within 5 seconds, it may be that the acquisition device has a sensing error or a processing error. For example, in an ideal state, when the first left lane of the vehicle jumps to become the second left lane at the previous moment, the right one lane jumps to become the first left lane at the same time. When the camera collects and perceives the lane line information, it generally transmits the information of the left lane line and the right lane line through two messages. The two messages will be received in order. In some cases, one message may be received.
  • the generation time of two adjacent lane change signs is set at least a second preset time apart.
  • the acquisition device in the vehicle collects the road information perceived by the vehicle, including but not limited to the following solutions:
  • the front-view camera can identify the nearest lane line information on the left side and the right side of the vehicle, and the forward-facing millimeter-wave radar can obtain the position information of more than 10 reflection points on the guardrail within 5 meters in front of the vehicle.
  • the front-view camera can identify the lane line information closest to the left and right of the vehicle, and can obtain road boundary information within 5 meters from the left and right.
  • the front-view camera can identify the nearest lane line information on the left side and the nearest right side of the car, as well as the second lane line information on the left side and the second right side lane line information, and can obtain road boundary information within 7 meters from the left and right.
  • the front-view camera can identify the nearest lane line information on the left and right side of the car, as well as the second lane line information on the left side and the second lane line on the right side.
  • the forward-facing millimeter-wave radar can obtain the guardrail within 7 meters in front of the car. The location information of more than 10 reflection points.
  • Scheme 1 and Scheme 2 can support the initial positioning of any lane on a 3-lane road, the initial positioning of lanes on both sides of a road with more than 4 lanes, and the stable positioning and tracking of less than 5 lanes.
  • Scheme 3 and Scheme 4 can support the initial positioning of any lane on a 5-lane road, the initial positioning of the lanes on both sides of the road with more than 6 lanes, and the stable positioning and tracking of the number of lanes within 7 lanes.
  • suitable collection devices such as forward-looking cameras and forward-facing millimeter-wave radars can be selected according to actual conditions, so as to meet the positioning requirements of camping.
  • FIG. 12 is a structural block diagram of a vehicle positioning device provided by an embodiment of the present disclosure. See Figure 12, including:
  • Initialization module 10 is used to determine the current positioning lane based on the current position information of the vehicle, the vehicle's perceived road information and map information;
  • the positioning monitoring module 20 is used to compare the vehicle perceived road information acquired in real time with the current positioning lane, and determine the mismatch integral value;
  • the judging module 30 is used to determine whether the mismatch integral value is greater than or equal to the preset integral value, and if so, instruct the initialization module to perform the operation of determining the current positioning lane based on the vehicle's current position information, vehicle perceived road information and map information again.
  • Fig. 13 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure, including: a processor 40 and a memory 50; the processor 40 calls the program or instructions stored in the memory 50 to execute the vehicle as described in any of the above embodiments. The steps of the positioning method.
  • the electronic device may further include at least one communication interface 60 .
  • Various components in the electronic device are coupled together through the bus system 70 .
  • the communication interface 60 is used for information transmission with external devices. It can be understood that the bus system 70 is used to realize connection and communication between these components.
  • the bus system 70 also includes a power bus, a control bus and a status signal bus.
  • the vehicle positioning method provided by the embodiments of the present disclosure may be applied to the processor 40 or implemented by the processor 40 .
  • the processor 40 may be an integrated circuit chip and has a signal processing capability. In the implementation process, each step of the above method can be completed by the processor 40 calling the hardware integrated logic circuit in the program or instructions stored in the memory 50 or instructions in the form of software.
  • the above-mentioned processor 40 may be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a ready-made programmable gate array (Field Programmable Gate Array, FPGA) or other available Program logic devices, discrete gate or transistor logic devices, discrete hardware components.
  • a general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.
  • Embodiments of the present disclosure also propose a computer-readable storage medium, the computer-readable storage medium stores programs or instructions, and the programs or instructions enable the computer to execute the steps of each embodiment of the vehicle positioning method. In order to avoid repeated descriptions, This will not be repeated here.
  • the present application discloses a vehicle positioning method, including:
  • A1 Determine the current positioning lane based on the vehicle's current location information, vehicle perception road information and map information;
  • A2 According to the vehicle positioning method described in A1, it also includes:
  • the determination of the current positioning lane based on the current position information of the vehicle, the road information perceived by the vehicle and the map information includes:
  • a lane score table is generated
  • the vehicle perceived road information includes perceived lane line information and perceived guardrail information; the determination of the integral value of each lane in the lane score table based on the vehicle perceived road information includes:
  • the first integral rule corresponding to the number of lanes being 1 is: if the vehicle perceives road information as a solid line on one side of the lane and there is a guardrail on the left side, add Minute;
  • the first scoring rule corresponding to the number of lanes being 2 is: the perceived lane line information and the perceived guardrail information are solid lines for the left nearest neighbor lane line and dashed line for the right nearest neighbor lane line, then the left lane will add points ;
  • the perceived lane line information and the perceived guardrail information are guardrails on the left, and the nearest neighbor lane line on the right is a dotted line, then the left lane will add points;
  • the perceived lane line information and the perceived guardrail information are right If the side nearest neighbor lane line is a solid line and the left nearest neighbor lane line is a dotted line, then the right lane will add points;
  • the perceived lane line information and the perceived guardrail information are that there is a guardrail on the right side and the left nearest neighbor lane line If it is a dotted line, the right lane will add points;
  • the first integral rule corresponding to the number of lanes being 3 is: if the perceived lane line information and the perceived guardrail information are dashed lines on the left and right sides and there is no guardrail, the middle lane will add points; the perceived lane line information and the perceived guardrail information is that the left nearest neighbor lane line is a solid line, the right nearest neighbor lane line is a dotted line and there is no right guardrail, then the left lane will add points; the perceived lane line information and the perceived guardrail If the information is that there is a guardrail on the left, the nearest neighbor lane line on the right is a dotted line and there is no guardrail on the right, then the left lane will add points; the perceived lane line information and the perceived guardrail information are that the nearest neighbor lane line on the right is a solid line , the nearest neighbor lane line on the left is a dotted line and there is no guardrail on the left, the right lane will get extra points.
  • the first integral rule corresponding to the number of lanes greater than or equal to 4 is: the perceived lane line information and the perceived guardrail information are that the nearest neighbor lane line on the left is a solid line, and the nearest neighbor on the right is a solid line.
  • the leftmost lane will add points; if the perceived lane line information and the perceived guardrail information indicate that there is a guardrail on the left, and the nearest neighbor lane line on the right is a dotted line and there is no right guardrail, then Extra points for the leftmost lane; the perceived lane line information and the perceived guardrail information are that the right nearest neighbor lane line is a solid line, the left nearest neighbor lane line is a dashed line, and there is no guardrail on the left side, then the rightmost lane Extra points; the perceived lane line information and the perceived guardrail information are that the nearest neighbor lane lines on the left and right sides are all dotted lines and there is no guardrail, then the perceived lane line information and the perceived guardrail information are combined with the lanes of the middle lanes Line alignment, and bonus points for consistent middle lanes.
  • the vehicle perception road information also includes surrounding vehicle information, the number of lanes in the map information corresponding to the current position information of the determined vehicle, and based on the first integral rule corresponding to the number of lanes
  • the perceived lane line information and the perceived guardrail information also include:
  • the integral value of each lane in the lane integral table is updated based on the second integral rule corresponding to the number of lanes and the surrounding vehicle information.
  • the second integral rule corresponding to the number of lanes being 2 is: the surrounding vehicle information is that there is a moving vehicle on the left and the lateral distance from the current vehicle is greater than the second preset value, Then add points to the right lane; the surrounding vehicle information is to recognize that there is a moving vehicle on the right and the lateral distance from the current vehicle is greater than the second preset value, then add points to the left lane;
  • the second integral rule corresponding to the number of lanes greater than or equal to 3 is: if the surrounding vehicle information recognizes that there is a moving vehicle on the left and the lateral distance from the current vehicle is greater than the second preset value, then the leftmost lane will be deducted; The surrounding vehicle information is to recognize that there is a moving vehicle on the right side and the lateral distance from the current vehicle is greater than the second preset value, then the rightmost lane will be decremented; if the number of lanes is equal to 3, the surrounding vehicle information is left and right sides If a moving vehicle is identified and the lateral distance to the current vehicle is greater than a second preset value, points are added to the middle lane.
  • A9 According to the vehicle positioning method described in A7, after determining the surrounding vehicle information and determining that the lateral distance between the moving vehicle and the current vehicle is greater than the second preset value and the duration is longer than the first preset time, execute the corresponding lane number-based The operation of updating the integral value of each lane in the lane integral table with the second integral rule and the surrounding vehicle information.
  • A10 According to the vehicle positioning method described in A3, in the process of determining the current positioning lane based on the current position information of the vehicle, the road information perceived by the vehicle and the map information, it also includes:
  • the lane score table is cleared.
  • the comparison of the real-time acquired vehicle perception road information with the current positioning lane to determine the mismatch integral value includes:
  • the mismatch integral value is determined based on the third integral rule corresponding to the current positioning lane and the vehicle perceived road information acquired in real time.
  • A12 According to the vehicle positioning method described in A11,
  • the third integral rule corresponding to the current positioning lane being the leftmost lane is as follows: the vehicle perceived road information obtained in real time shows that the nearest neighbor lane line on the left is a dotted line and there is no guardrail on the left side, and the mismatch integral value is increased; the vehicle acquired in real time Perceived road information is that there is a guardrail on the right side and the total number of lanes is greater than 1, and the mismatch integral value is increased;
  • the third integral rule corresponding to the current positioning lane being the rightmost lane is: the real-time acquired vehicle perceived road information is that the nearest neighbor lane line on the right is a dotted line and there is no guardrail on the right side, and the mismatch integral value is increased; the real-time acquired vehicle Perceived road information is that there is a guardrail on the left and the total number of lanes is greater than 1, and the mismatch integral value is increased;
  • the third integral rule corresponding to the current positioning lane being the middle lane is: the real-time acquired vehicle perception road information is that the distance between the second lane line on the left and the current vehicle is less than the first threshold, and the second lane line on the left is real line, increase the mismatch integral value; the vehicle perceived road information obtained in real time is that the distance between the second lane line on the right and the current vehicle is less than the first threshold, and the second lane line on the right is a solid line, increase the mismatch integral value ;
  • the vehicle perceived road information obtained in real time is that there is a guardrail on the left side, and the distance between the guardrail and the current vehicle is less than the second threshold, and the mismatch integral value is increased;
  • the real-time acquired vehicle perceived road information is that there is a guardrail on the right side, and the distance between the guardrail and the current vehicle The current distance between the vehicles is smaller than the second threshold, and the mismatch integral value is increased.
  • A13 According to the vehicle positioning method described in A12, after it is determined that the vehicle perceived road information acquired in real time does not comply with any of the third integral rules, the mismatch integral value is cleared.
  • the determination of whether the vehicle is in a steering state includes:
  • Whether the vehicle is in a steering state is determined based on the steering wheel angle and/or the yaw rate signal.
  • determining whether the vehicle has changed lanes according to the vehicle’s perceived road information, and generating a lane change sign after determining that the vehicle has changed lanes includes:
  • a lane change flag is generated according to the lane change direction in the vehicle's perceived road information.
  • A16 According to the vehicle positioning method described in A2, the generation time of two adjacent lane change signs is separated by at least a second preset time.
  • a vehicle positioning device comprising:
  • the initialization module is used to determine the current positioning lane based on the current position information of the vehicle, the road information perceived by the vehicle and the map information;
  • the positioning monitoring module is used to compare the real-time acquired vehicle perception road information with the current positioning lane to determine the mismatch integral value
  • a judging module configured to determine whether the mismatch integral value is greater than or equal to a preset integral value, and if so, instruct the initialization module to perform the operation of determining the current positioning lane based on the vehicle's current position information, vehicle perceived road information, and map information again.
  • C1 An electronic device comprising: a processor and a memory
  • the processor is used to execute the steps of the method described in any one of A1 to A16 by invoking the programs or instructions stored in the memory.
  • D1 A computer-readable storage medium, the computer-readable storage medium stores a program or an instruction, and the program or instruction causes a computer to execute the steps of any one of the methods described in A1 to A16.
  • the positioning lane is continuously monitored by comparing the real-time acquired vehicle perception road information with the current positioning lane to determine the mismatch integral value. Whether it is correct or not, the stability of lane positioning and anti-interference ability are improved, and it has strong industrial applicability.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Mathematical Physics (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Traffic Control Systems (AREA)

Abstract

本公开实施例涉及一种车辆定位方法、装置、电子设备和存储介质，方法包括基于车辆当前位置信息、车辆感知道路信息以及地图信息确定当前定位车道；将实时获取的车辆感知道路信息与当前定位车道比对，确定失配积分值；确定所述失配积分值大于等于预设积分值后，返回执行所述基于车辆当前位置信息、车辆感知道路信息以及地图信息确定定位车道。本公开实施例提高了车道定位的稳定性以及抗干扰能力。

Description

车辆定位方法、装置、电子设备和存储介质
本公开要求于2021年6月28日提交中国专利局、申请号为202110720086.5、发明名称为“一种车辆定位方法、装置、电子设备和存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本公开中。
技术领域
本公开实施例涉及拖车技术领域，具体涉及车辆定位方法、装置、电子设备和存储介质。
背景技术
自动驾驶汽车能够减少交通拥堵提高交通效率、释放双手提高社会生产力，因而其相关技术受到广泛的关注。通过装备在汽车上的摄像头、激光雷达、毫米波雷达等传感器感知周围的道路环境并快速准确的获取自身位置和周围目标的位置、大小和运动方向等信息，可以保障无人驾驶车辆安全平稳的行驶在道路上。
自动驾驶系统在运行中需要对本车位置进行准确定位，用于规划行驶路线。采用传统民用GPS定位车辆的方式，其精度只能确定所在道路，无法精确获得所在车道。这会影响自动驾驶车辆对于行驶路线与变道需求的误判。而采用RTK(Real Time Kinematic，实时动态)等高精度定位设备来获取准确位置，需要依赖高精度地图的准确性，成本高且使用范围受限。此外，传统车道定位方式难以应对复杂环境，如道路边缘模糊、目标遮挡和光照变化等道路情况，稳定性与抗干扰能力较差。
发明内容
为了解决现有技术存在的至少一个问题，本公开的至少一个实施例提供了一种车辆定位方法、装置、电子设备和存储介质。
第一方面，本公开实施例提出一种车辆定位方法，包括：
基于车辆当前位置信息、车辆感知道路信息以及地图信息确定当前定位车道；
将实时获取的车辆感知道路信息与当前定位车道比对，确定失配积分值；
确定所述失配积分值大于等于预设积分值后，返回执行所述基于车辆当前位置信息、车辆感知道路信息以及地图信息确定定位车道。
第二方面，本公开实施例还提出一种车辆定位装置，包括：初始化模块，用于基于车辆当前位置信息、车辆感知道路信息以及地图信息确定当前定位车道；
定位监控模块，用于将实时获取的车辆感知道路信息与当前定位车道比对，确定失配积分值；
判断模块，用于确定所述失配积分值是否大于等于预设积分值，若是，指示所述初始化模块再次执行基于车辆当前位置信息、车辆感知道路信息以及地图信息确定当前定位车道的操作。
第三方面，本公开实施例还提出一种电子设备，包括：处理器和存储器；
所述处理器通过调用所述存储器存储的程序或指令，用于执行如第一方面所述方法的步骤。
第三方面，本公开实施例还提出计算机可读存储介质，用于存储程序或指令，所述程序或指令使计算机执行如第一方面所述方法的步骤。
可见，本公开实施例的至少一个实施例中，首先基于车辆当前位置信息、车辆感知道路信息以及地图信息线先确定当前定位车道，即，先进行初始的车辆的车道定位。然后将实时获取的车辆感知道路信息与当前定位车道比对，确定失配积分值。该步骤实际为进行车道定位的监控，基于实时获取的车辆感知道路信息分析与当前定位车道的不符之处，并确定失配积分值。若失配积分值大于等于预设积分值，说明此时的定位车道定位失败，需要重新确定定位车道，那么则返回执行基于车辆当前位置信息、车辆感知道路信息以及地图信息再次重新确定定位车道。本公开实施例相比于现有技术，不需要借助RTK高精度定位，实现成本低。此外，本公开实施例在根据车辆当前位置信息、车辆感知道路信息以及地图信息确定当前定位车道后，通过将实时获取的车辆感知道路信息与当前定位车道比对，确定失配积分值的方式，持续监控定位车道是否正确，提高了车道定位的稳定性以及抗干扰能力。
附图说明
为了更清楚地说明本公开实施例的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本公开的一些实施例，对于本领域普通技术人员来讲，还可以根据这些附图获得其他的附图。
图1为本公开实施例提供的一种车辆定位方法的流程示意图；
图2为一种双车道示意图；
图3为一种三车道示意图；
图4为一种四车道示意图；
图5为车道数量为2且左侧有运动车辆的示意图；
图6为车道数量为2且右侧有运动车辆的示意图；
图7为车道数量为3且左侧有运动车辆的示意图；
图8为车道数量为3且右侧有运动车辆的示意图；
图9为车道数量为3且左右两侧均有运动车辆的示意图；
图10为本公开实施例提供的又一种车辆定位方法的流程示意图；
图11为本公开实施例提供的一种车辆变道的示意图；
图12为本公开实施例提供的一种车辆定位装置的结构框图；
图13是本公开实施例提供的一种电子设备的结构示意图。
具体实施方式
为了能够更清楚地理解本公开的上述目的、特征和优点，下面结合附图和实施例对本公开作进一步的详细说明。可以理解的是，所描述的实施例是本公开的一部分实施例，而不是全部的实施例。此处所描述的具体实施例仅仅用于解释本公开，而非对本公开的限定。基于所描述的本公开的实施例，本领域普通技术人员所获得的所有其他实施例，都属于本公开保护的范围。
需要说明的是，在本文中，诸如“第一”和“第二”等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。
图1为本公开实施例提供的一种车辆定位方法的流程示意图。如图1所示，本公开实施例提供 的车辆定位方法包括S110至S130：
S110、基于车辆当前位置信息、车辆感知道路信息以及地图信息确定当前定位车道。
车辆可以设置有定位装置，例如：全球定位系统(Global Positioning System，GPS)定位装置、惯性测量单元(Inertial Measurement Unit，IMU)等。全球定位系统定位装置可以获得卫星信号，实时计算出经纬度信息，并根据经纬度信息确定车辆当前的位置信息。车辆当前的位置信息例如可以包括车辆所在道路以及行驶方向等。确定车辆所在道路以及行驶方向等后，可以根据地图信息读取当前所在道路对应的车道总数信息、有无应急车道的信息等(为方便描述，后续统称为车道模型)。
车辆中还可以设置有采集装置，包括但不限于摄像头、激光雷达等。本实施例中的采集装置可以采集车辆感知道路信息。车辆感知道路信息包括但不限于感知车道线信息、感知护栏信息以及周边车辆信息等。感知护栏信息例如可以包括护栏的侧向位置、斜率、曲率、置信度等。感知车道线信息例如可以包括车道线的横向距离、斜率、曲率、线型(实线、虚线)、置信度等。周边车辆信息例如可以包括运动车辆的纵向位置、横向位置、纵向车速等。车辆感知道路信息是指采集装置实时获取的车辆所处位置附近的真实的道路信息。
本公开实施例先获取车辆当前位置信息，根据车辆当前位置信息查找地图信息所对应的车道模型，然后再根据车辆感知道路信息初步确定车辆当前处于车道模型的哪个车道。例如，根据车辆当前位置信息以及地图信息，确定车辆当前所在道路对应的车道模型为3车道。车辆感知道路信息中的感知车道线信息依次为左二车道线为实线、左一车道线为虚线、右一车道线为虚线、右二车道线为实线。根据上述感知车道线信息以及车道模型，初步确定车辆当前处于车道模型的中间车道，即当前定位车道为中间车道。
在一些实施例中，S110基于车辆当前位置信息、车辆感知道路信息以及地图信息确定当前定位车道，包括：
S111、基于车辆当前位置信息以及地图信息，生成车道积分表；
S112、基于车辆感知道路信息确定车道积分表中各车道的积分值；
S113、将车道积分表中积分值大于第一预设值的车道确定为定位车道。
例如基于车辆当前位置信息以及地图信息确定当前车道总数为3时，则生成的车道积分表为一个3x1的数组，用于存放每个车道的积分数值。基于车辆感知道路信息根据积分规则对满足条件的车道进行积分，并将积分结果保存在车道积分表中。若车道积分表中某一车道积分值超过第一预设值，则判断当前车辆处于该车道中，完成车辆定位。各车道积分值均未超过第一预设值，则继续进行积分。
在一些实施例中，在基于车辆当前位置信息、车辆感知道路信息以及地图信息确定当前定位车道过程中，还包括确定当前车道数量发生变化后，将车道积分表清零。
若在基于车辆当前位置信息、车辆感知道路信息以及地图信息确定当前定位车道过程中，当前车道数量发生了而变化，那么再根据原有车道积分表中的积分值确定当前定位车道将会出现判断错误，因此本实施例在确定当前车道数量发生变化后，将车道积分表清零。
在一些实施例中，车辆感知道路信息包括感知车道线信息以及感知护栏信息。S112基于车辆感 知道路信息确定车道积分表中各车道的积分值，包括：
确定车辆当前位置信息对应的地图信息中的车道数量，并基于车道数量对应的第一积分规则、感知车道线信息以及感知护栏信息确定所述车道积分表中各车道的积分值。
例如根据GPS定位的车辆当前位置信息，从地图信息中确定该位置对应的车道信息，比如车道数量、车道线信息、护栏信息等，并建立车道积分表。根据预设的第一积分规则，以及感测车道线信息以及感知护栏信息进行积分计算，确定车道积分表中各车道的积分值。
第一积分规则可以根据车道数量分别设置，例如基于车道总数分为单车道、两车道、三车道、四车道及以上等情况。
因为护栏检测的可靠性不如车道线的可靠性，有时不一定能检测到护栏。因此本公开实施例综合感知的车道线信息以及护栏信息进行积分。
车道数量为1对应的第一积分规则为：车辆感知道路信息为有一侧车道线为实线，且左侧有护栏，则对所在单车道加分。对于车道数量为1，即单车道的情况，综合感知的车道线信息以及护栏信息进行积分。当车辆感知道路信息中右侧车道线为实线，且左侧有护栏，则对所在单车道加分。
车道数量为2对应的第一积分规则为：感知车道线信息以及感知护栏信息为左侧最近邻车道线为实线且右侧最近邻车道线为虚线，则左侧车道加分；感知车道线信息以及感知护栏信息为左侧有护栏，且右侧最近邻车道线为虚线，则左侧车道加分；感知车道线信息以及感知护栏信息为右侧最近邻车道线为实线，且左侧最近邻车道线为虚线，则右侧车道加分；感知车道线信息以及感知护栏信息为右侧有护栏且左侧最近邻车道线为虚线，则右侧车道加分。
图2为一种双车道示意图，示例性的设置双车道的左侧车道为车道2，右侧车道为车道1。
若感知车道线信息以及感知护栏信息为左侧最近邻车道线为实线且右侧最近邻车道线为虚线，那么说明当前车辆所在的真实车道比较符合位于左侧车道，即车道2，那么对左侧车道加分。
若感知车道线信息以及感知护栏信息为左侧有护栏，且右侧最近邻车道线为虚线，那么说明当前车辆所在的真实车道比较符合位于左侧车道，即车道2，那么对左侧车道加分。
若感知车道线信息以及感知护栏信息为右侧最近邻车道线为实线，且左侧最近邻车道线为虚线，那么说明当前车辆所在的真实车道比较符合位于右侧车道，即车道1，那么对右侧车道加分。
若感知车道线信息以及感知护栏信息为右侧有护栏且左侧最近邻车道线为虚线，那么说明当前车辆所在的真实车道比较符合位于右侧车道，即车道1，那么对右侧车道加分。
其中，上述描述过程中，车辆左侧最近邻车道线是指左一车道线，车辆右侧最近邻车道线是指右一车道线。
车道数量为3对应的第一积分规则为：感知车道线信息以及感知护栏信息为左右两侧最近邻车道线均为虚线且没有护栏，则中间车道加分；感知车道线信息以及感知护栏信息为左侧最近邻车道线为实线，右侧最近邻车道线为虚线且没有右侧护栏，则左侧车道加分；感知车道线信息以及感知护栏信息为左侧有护栏，右侧最近邻车道线为虚线且没有右侧护栏，则左侧车道加分；感知车道线信息以及感知护栏信息为右侧最近邻车道线为实线，左侧最近邻车道线为虚线且左侧没有护栏，则右侧车道加分。
图3为一种三车道示意图，示例性的设置三车道的左侧车道为车道3，右侧车道为车道1，中间车道为车道2。
若感知车道线信息以及感知护栏信息为左右两侧最近邻车道线均为虚线且没有护栏，那么说明当前车辆所在的真实车道比较符合位于中间车道，即车道2，则对中间车道加分。
若感知车道线信息以及感知护栏信息为左侧最近邻车道线为实线，右侧最近邻车道线为虚线且没有右侧护栏，那么说明当前车辆所在的真实车道比较符合位于左侧车道，即车道3，则对左侧车道加分。
若感知车道线信息以及感知护栏信息为左侧有护栏，右侧最近邻车道线为虚线且没有右侧护栏，那么说明当前车辆所在的真实车道比较符合位于左侧车道，即车道3，则对左侧车道加分。
若感知车道线信息以及感知护栏信息为右侧最近邻车道线为实线，左侧最近邻车道线为虚线且左侧没有护栏，那么说明当前车辆所在的真实车道比较符合位于右侧车道，即车道1，则对右侧车道加分。
车道数量大于等于4对应的第一积分规则为：感知车道线信息以及感知护栏信息为左侧最近邻车道线为实线，右侧最近邻车道线为虚线且没有右侧护栏则最左侧车道加分；感知车道线信息以及感知护栏信息为左侧有护栏，右侧最近邻车道线为虚线且没有右侧护栏则最左侧车道加分；感知车道线信息以及感知护栏信息为右侧最近邻车道线为实线，左侧最近邻车道线为虚线，且左侧没有护栏，则最右侧车道加分；感知车道线信息以及感知护栏信息为左右两侧最近邻车道线均为虚线且没有护栏，则将感知车道线信息以及感知护栏信息与中间各车道的车道线比对，并对比对一致的中间车道加分。
图4为一种四车道示意图，示例性的设置四车道从右向左依次为车道1、车道2、车道3、车道4。
若感知车道线信息以及感知护栏信息为左侧最近邻车道线为实线，右侧最近邻车道线为虚线且没有右侧护栏，说明当前车辆所在的真实车道比较符合位于最左侧车道，即车道4，则对左侧车道加分。
若感知车道线信息以及感知护栏信息为左侧有护栏，右侧最近邻车道线为虚线且没有右侧护栏，说明当前车辆所在的真实车道比较符合位于最左侧车道，即车道4，则对左侧车道加分。
若感知车道线信息以及感知护栏信息为右侧最近邻车道线为实线，左侧最近邻车道线为虚线，且左侧没有护栏，说明当前车辆所在的真实车道比较符合位于最右侧车道，即车道1，则对右侧车道加分。
若感知车道线信息以及感知护栏信息为左右两侧最近邻车道线均为虚线且没有护栏，说明当前车辆所在的真实车道比较符合位于中间的车道例如车道2或车道3。则将感知车道线信息以及感知护栏信息与中间各车道的车道线比对，并对比对一致的中间车道加分。
其中，将感知车道线信息以及感知护栏信息与中间各车道的车道线比对，可以通过遍历各中间车道的方式，以图4为例，将感知车道线信息以及感知护栏信息与车道2两边的车道线比对，若比对一致那么对车道2加分。若不一致，则将感知车道线信息以及感知护栏信息与车道3两边的车道线比对，若比对一致那么对车道3加分。若不一致，则暂不加分。
需要说明的是，以上积分过程中满足的条件越大，则积分越多。
在一些实施例中，车辆感知道路信息还可以包括周边车辆信息，在确定车辆当前位置信息对应的地图信息中的车道数量，并基于车道数量对应的第一积分规则、感知车道线信息以及感知护栏信 息确定车道积分表中各车道的积分值之后，还可以包括：
基于车道数量对应的第二积分规则以及周边车辆信息更新车道积分表中各车道的积分值。
本公开实施例还可以根据感测的周边车辆信息来修正车道积分表中各车道的积分值。可以通过摄像头、激光雷达等装置获取周边车辆信息，根据车道数量对应的第二积分规则对满足条件的车道进行相应积分，更新车道积分表中各车道的积分值。
例如，车道数量为2对应的第二积分规则为：周边车辆信息为识别出左侧有运动车辆且与当前车辆的横向距离大于第二预设值，则对右侧车道加分；周边车辆信息为识别出右侧有运动车辆且与当前车辆的横向距离大于第二预设值，则对左侧车道加分。
如图5所示，若周边车辆信息为识别出左侧有运动车辆，说明运动车辆在本车的左侧。若识别出的左侧运动车辆与当前车辆的横向距离h大于第二预设值，说明左侧运动车辆与当前车辆不在同一车道。第二预设值可以根据实际道路场景进行设置。此时说明当前车辆所在的真实车道比较符合位于右侧车道，即车道1，则对右侧车道加分。
如图6所示，若周边车辆信息为识别出右侧有运动车辆，说明运动车辆在本车的右侧。若识别出的右侧运动车辆与当前车辆的横向距离h大于第二预设值，说明右侧运动车辆与当前车辆不在同一车道。此时说明当前车辆所在的真实车道比较符合位于左侧车道，即车道2，则对左侧车道加分。
车道数量大于等于3对应的第二积分规则为：周边车辆信息为识别出左侧有运动车辆且与当前车辆的横向距离大于第二预设值，则对最左侧车道减分；周边车辆信息为识别出右侧有运动车辆且与当前车辆的横向距离大于第二预设值，则对最右侧车道减分；若车道数量等于3，周边车辆信息为左右两侧均识别出运动车辆且与当前车辆的横向距离大于第二预设值，则对中间车道加分。
如图7所示，以3车道为例，若周边车辆信息为识别出左侧有运动车辆，说明运动车辆在本车的左侧。识别出的左侧运动车辆与当前车辆的横向距离h大于第二预设值，说明左侧运动车辆与当前车辆不在同一车道。那么说明当前车辆不可能位于最左侧车道，那么对最左侧车道(图7中的车道3)减分。
如图8所示，若周边车辆信息为识别出右侧有运动车辆，说明运动车辆在本车的右侧。识别出的右侧运动车辆与当前车辆的横向距离h大于第二预设值，说明右侧运动车辆与当前车辆不在同一车道。那么说明当前车辆不可能位于最右侧车道，那么对最右侧车道(图8中的车道1)减分。
若车道数量大于3，周边车辆信息为左右两侧均识别出运动车辆且与当前车辆的横向距离大于第二预设值，那么说明当前车辆位于中间的某一车道，但不确定是哪个中间车道，如图9所示，若车道数量等于3，只有一个中间车道，若周边车辆信息为左右两侧均识别出运动车辆且与当前车辆的横向距离大于第二预设值，那么说明当前车辆位于中间车道，则对中间车道加分。
需要说明的时，在减分过程中，将车道积分表中各车道的积分值下限控制在零，即积分值为零后，不再进行减分操作。
在一些实施例中，为例防止在确定周边车辆信息时，传感器(例如摄像头、激光雷达等)等的误判，可以在确定周边车辆信息确定运动车辆与当前车辆的横向距离大于第二预设值的持续时间大于第一预设时间后，再执行基于车道数量对应的第二积分规则以及周边车辆信息更新车道积分表中各车道的积分值的操作。这样设置可以避免传感器检测数据的短时间波动导致的误判。
S120、将实时获取的车辆感知道路信息与当前定位车道比对，确定失配积分值。
车辆完成初步的车道定位后，对当前定位车道进行持续监控。该步骤中实时获取车辆感知道路信息，并将实时获取的车辆感知道路信息与上一时刻确定的当前定位车道进行比对，根据比对结果确定失配积分值。该步骤中，可以根据实际需求设置对比积分规则。例如可以针对当前定位车道的不同指定不同的对比积分规则，符合对比积分规则，失配积分值加1。
在一些实施例中，将实时获取的车辆感知道路信息与当前定位车道比对，确定失配积分值，包括：基于当前定位车道对应的第三积分规则以及实时获取的车辆感知道路信息确定失配积分值。
针对当前定位车道的类型对应不同的第三积分规则，例如左车道、右车道、中间车道对应不同的第三积分规则。
当前的定位车道为最左侧车道对应的第三积分规则为：实时获取的车辆感知道路信息为左侧最近邻车道线为虚线且左侧不存在护栏，增加失配积分值；实时获取的车辆感知道路信息为右侧存在护栏且车道总数大于1，增加失配积分值。
当前的定位车道为最右侧车道对应的第三积分规则为：实时获取的车辆感知道路信息为右侧最近邻车道线为虚线且右侧不存在护栏，增加失配积分值；实时获取的车辆感知道路信息为左侧存在护栏且车道总数大于1，增加失配积分值。
当前的定位车道为中间车道对应的第三积分规则为：实时获取的车辆感知道路信息为左侧第二车道线与当前车辆之间的距离小于第一阈值，且左侧第二车道线为实线，增加失配积分值；实时获取的车辆感知道路信息为右侧第二车道线与当前车辆之间的距离小于第一阈值，且右侧第二车道线为实线，增加失配积分值；实时获取的车辆感知道路信息为左侧存在护栏，且护栏与当前车辆之间的距离小于第二阈值，增加失配积分值；实时获取的车辆感知道路信息为右侧存在护栏，且护栏与当前车辆之间的距离小于第二阈值，增加失配积分值。
若当前的定位车道为最左侧车道，而实时获取的车辆感知道路信息为左侧最近邻车道线为虚线且左侧不存在护栏，根据实时获取的车辆感知道路信息预测当前车辆实际所处车道不在最左侧车道，说明当前车辆实际所处车道与当前的定位车道不符，因此增加当前的定位车道的失配积分值。若当前的定位车道为最左侧车道，而实时获取的车辆感知道路信息为右侧存在护栏且车道总数大于1，根据实时获取的车辆感知道路信息预测当前车辆实际所处车道不在最左侧车道，说明当前车辆实际所处车道与当前的定位车道不符，因此增加当前的定位车道的失配积分值。
若当前的定位车道为最右侧车道，而实时获取的车辆感知道路信息为右侧最近邻车道线为虚线且右侧不存在护栏，根据实时获取的车辆感知道路信息预测当前车辆实际所处车道不在最右侧车道，说明当前车辆实际所处车道与当前的定位车道不符，因此增加当前的定位车道的失配积分值。若当前的定位车道为最右侧车道，而实时获取的车辆感知道路信息为左侧存在护栏且车道总数大于1，根据实时获取的车辆感知道路信息预测当前车辆实际所处车道不在最右侧车道，说明当前车辆实际所处车道与当前的定位车道不符，因此增加当前的定位车道的失配积分值。
若当前的定位车道为中间车道，而实时获取的车辆感知道路信息为左侧第二车道线与当前车辆之间的距离小于第一阈值，且左侧第二车道线为实线，根据实时获取的车辆感知道路信息预测当前车辆实际所处车道不在中间车道，说明当前车辆实际所处车道与当前的定位车道不符，因此增加当前的定位车道的失配积分值。若当前的定位车道为中间车道，而实时获取的车辆感知道路信息为右侧第二车道线与当前车辆之间的距离小于第一阈值，且右侧第二车道线为实线，根据实时获取的车辆感知道路信息预测当前车辆实际所处车道不在中间车道，说明当前车辆实际所处车道与当前的定位车道不符，因此增加当前的定位车道的失配积分值。若当前的定位车道为中间车道，而实时获取的车辆感知道路信息为左侧存在护栏，且护栏与当前车辆之间的距离小于第二阈值，根据实时获取的车辆感知道路信息预测当前车辆实际所处车道不在中间车道，说明当前车辆实际所处车道与当前的定位车道不符，因此增加当前的定位车道的失配积分值。若当前的定位车道为中间车道，而实时获取的车辆感知道路信息为右侧存在护栏，且护栏与当前车辆之间的距离小于第二阈值，根据实时获取的车辆感知道路信息预测当前车辆实际所处车道不在中间车道，说明当前车辆实际所处车道与当前的定位车道不符，因此增加当前的定位车道的失配积分值。
以上加分过程，同时满足的条件越多，则加分越多。
在一些实施例中，还可以在确定实时获取的车辆感知道路信息不符合任一第三积分规则后，则将失配积分值清零。在将实时获取的车辆感知道路信息与当前定位车道比对之前，失配积分值为零。但有可能出现传感器检测数据的短时间波动导致误判的情况，为防止这种情况，在确定实时获取的车辆感知道路信息不符合任一第三积分规则后，则将失配积分值清零。
S130、确定失配积分值大于等于预设积分值后，返回执行基于车辆当前位置信息、车辆感知道路信息以及地图信息确定定位车道。
在确定失配积分值过程中，符合对比积分规则的条件越大，失配积分值加分越多，若失配积分值大于等于预设积分值，说明当前定位车道与当前感知的车辆感知道路信息严重不符，当前定位车道错误，需要重新确定定位车道。因此本公开实施例在确定失配积分值大于等于预设积分值后，返回执行S110基于车辆当前位置信息、车辆感知道路信息以及地图信息确定定位车道的操作。
本公开实施例首先基于车辆当前位置信息、车辆感知道路信息以及地图信息先进行初始的车道定位，先确定当前定位车道，然后进行车道定位的监控，将实时获取的车辆感知道路信息与当前定位车道比对，确定失配积分值。若失配积分值大于等于预设积分值，说明此时的定位车道定位失败，需要重新确定定位车道，那么则返回执行基于车辆当前位置信息、车辆感知道路信息以及地图信息再次重新确定定位车道。本公开实施例相比于现有技术，不需要借助RTK高精度定位，因此实现成本低。此外，本公开实施例在根据车辆当前位置信息、车辆感知道路信息以及地图信息确定当前定位车道后，还通过将实时获取的车辆感知道路信息与当前定位车道比对，确定失配积分值，持续监控定位车道是否正确，在失配积分值大于等于预设积分值后，重新首先基于车辆当前位置信息、车辆感知道路信息以及地图信息确定当前定位车道。因此相比于现有技术中仅基于摄像头感知的车道线类型与地图信息匹配的方式，可以提高车道定位的稳定性以及抗干扰能力。
在一些实施例中，参见图10，车辆定位方法还可以包括：S140至S160：
S140、确定失配积分值小于预设积分值后，确定车辆是否处于转向状态。
若失配积分值小于预设积分值，说明当前定位车道与车辆感知道路信息较符合，因此本公开实施例继续进行车辆转向的监控，判断车辆是否处于转向状态。
在一些实施例中，确定车辆是否处于转向状态，可以包括基于方向盘转角和/或横摆角速度信号确定车辆是否处于转向状态。例如可以从底盘系统中读取车辆的方向盘转角和/或横摆角速度信号，当向盘转角以及横摆角速度信号中二者其一超过门限值，认定车辆处于转向状态。
S150、在确定车辆处于转向状态后，根据车辆感知道路信息确定车辆是否变道，并在确定车辆发生变道后生成变道标识。
若车辆处于转向状态，则根据车辆感知道路信息确定车辆是否变道，进行变道监控，并在确定车辆发生变道后生成变道标识。若车辆处于转向状态，并且根据摄像头等采集装置获取的车辆感知道路信息发现车辆发生了变道，那么生成变道标识，以进行后续定位车道的更新。变道标识例如包括向左变道和向右变道。
在一些实施例中，S150中根据车辆感知道路信息确定车辆是否变道，并在确定车辆发生变道后生成变道标识包括：
在车辆感知道路信息中至少一侧车道线与当前车辆之间的距离发生跳变时，确定车辆变道；
根据车辆感知道路信息中的车道线变化方向生成变道标志。
图11为本公开实施例提供的一种车辆变道的示意图，如图11所示，以3车道为例，车道线从左向右依次表示为n1、n2、n3、n4。前一时刻车辆处于车道2，车辆的左一车道线为n2，右一车道线为n3。车辆从车道2逐渐向车道1变道。
变道前，车辆的左一车道线为n2，左二车道线为n1，右一车道线为n3，右二车道线为n4。下面以车道线与车辆之间的距离为车道线与车辆中轴线之间的距离为例进行详细介绍。车辆向车道1变道过程中，车辆逐渐靠车道线n2。例如左一车道线n2与车辆中轴线距离d1从1.7m逐渐减小到0。而同时右一车道线n3与车辆中轴线距离d2从-1.7m逐渐减小到-3.4m。车辆中轴线跨过车道线n2的瞬间，n1变为左一车道线，n2变为右一车道线(变道前的左一车道线)。变道瞬间，左一车道线与车辆中轴线距离由原来的d1＝0m跳变为d3＝3.4m，右一车道线与车辆中轴线距离由原来的d2＝-3.4m跳变为d4＝0m。若车辆感知道路信息中至少一侧车道线与当前车辆之间的距离发生跳变，说明车辆发生了变道。如图11中，左二车导线变为左一车道线，说明车辆向左变道，因此生成向左变道的变道标志。
本实施例可以在车辆感知道路信息中左右两侧车道线与当前车辆之间的距离均发生跳变时，确定车辆变道。在其他实施方式中，为了防止信号采集过程中的信号传递不同步问题，还可以在车辆感知道路信息中至少一侧车道线与当前车辆之间的距离发生跳变时，就确定车辆变道。
S160、基于地图信息以及变道标识更新当前定位车道。
在进行变道监控中，实时基于地图信息以及变道标识更新当前定位车道。地图信息例如包括车辆所处位置处的车道总数等信息。仍然以图11为例，上一时刻确定的当前定位车道为车道2，在进行变道监控过程中，发现车辆向左变道，那么更新当前定位车道为车道1。
若发现车辆向右变道，那么更新当前定位车道为车道2。若车辆没有发生变道，那么保持当前定位车道不变。
以图11为例，在该过程中，若根据地图信息发现车辆当前定位车道的左侧增加n车道，则当 前定位车道加n；若左侧减少n车道，则当前定位车道减n。若根据地图信息发现，车道总数不变，则当前定位车道不变。车辆当前定位车道的右侧车道数增加或减少不影响当前定位车道的结果。需要说明的是，图11示例性的设置车道序号从左到右依次增加，并非对本发明实施例的限定。在其它实施方式中，还可以如图3所示，设置车道序号从右到左依次增加。若如图3所示的车道序号命名，那么若根据地图信息发现车辆当前定位车道的右侧增加n车道，则当前定位车道加n；若右侧减少n车道，则当前定位车道减n。若根据地图信息发现，车道总数不变，则当前定位车道不变。车辆当前定位车道的左侧车道数增加或减少不影响当前定位车道的结果。此外，本实施例对车道线的序号命名顺序也不做限定。
在一些实施例中，相邻两次变道标识的生成时间至少间隔第二预设时间。
由于车辆正常换道需要一定的时间，例如5s，若5s内检测出车道线与当前车辆之间的距离频繁跳变，就有可能是采集装置感测出错亦或者处理过程出错。例如，理想状态下，车辆的左一车道线跳变成上一时刻左二车道线的同时，右一车道线跳变成左一车道线。摄像头在采集感知车道线信息时，一般通过两条报文分别传送左一车道线和右一车道线信息，两条报文接收会存在先后顺序，在个别有时可能会出现一条报文接收了，而另一条报文还没有更新，这样就有可能出现左侧车道线跳变与右侧车道线跳变之间具有较小的时间间隔。这时候就有可能被认定为是发生两次变道。因此，本实施例为避免误判，设置邻两次变道标识的生成时间至少间隔第二预设时间。
需要说明的是，车辆中的采集装置采集车辆感知道路信息包括但不限于如下几种方案：
1、前视摄像头可以识别本车左侧最近以及右侧最近的车道线信息，前向毫米波雷达可以获取本车前方左右5米内护栏的10个以上的反射点位置信息。
2、前视摄像头可以识别本车左侧最近以及右侧最近的车道线信息，且能够获取左右5米内道路边界信息。
3、前视摄像头可以识别本车左侧最近以及右侧最近的车道线信息以及左侧第二条、右侧第二条车道线信息，且能够获得左右7米内的道路边界信息。
4、前视摄像头可以识别本车左侧最近以及右侧最近的车道线信息以及左侧第二条、右侧第二条车道线信息，前向毫米波雷达可以获取本车前方左右7米内护栏的10个以上的反射点位置信息。
方案1、方案2可以支持3车道道路任意车道的初始定位、4条以上车道道路两侧车道初始定位、5条以内车道的稳定定位跟踪。
方案3、方案4可以支持5车道道路任意车道的初始定位、6条以上车道道路两侧车道初始定位、7条以内车道数的稳定定位跟踪。
本公开实施例可以根据实际情况选择合适的前视摄像头、前向毫米波雷达等采集装置，以适应行营的定位需求。
基于同一发明构思，本公开实施例还提供一种车辆定位装置，图12为本公开实施例提供的一种车辆定位装置的结构框图。参见图12，包括：
初始化模块10，用于基于车辆当前位置信息、车辆感知道路信息以及地图信息确定当前定位车 道；
定位监控模块20，用于将实时获取的车辆感知道路信息与当前定位车道比对，确定失配积分值；
判断模块30，用于确定失配积分值是否大于等于预设积分值，若是，指示初始化模块再次执行基于车辆当前位置信息、车辆感知道路信息以及地图信息确定当前定位车道的操作。
图13是本公开实施例提供的一种电子设备的结构示意图，包括：处理器40和存储器50；处理器40通过调用存储器50存储的程序或指令，用于执行如上述任意实施例所述车辆定位方法的步骤。此外，电子设备还可以包括至少一个通信接口60。电子设备中的各个组件通过总线系统70耦合在一起。通信接口60，用于与外部设备之间的信息传输。可理解，总线系统70用于实现这些组件之间的连接通信。总线系统70除包括数据总线之外，还包括电源总线、控制总线和状态信号总线。
本公开实施例提供的车辆定位方法可以应用于处理器40中，或者由处理器40实现。处理器40可以是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述方法的各步骤可以通过处理器40调用存储器50存储的程序或指令中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器40可以是通用处理器、数字信号处理器(Digital SignalProcessor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
本公开实施例还提出一种计算机可读存储介质，所述计算机可读存储介质存储程序或指令，所述程序或指令使计算机执行如车辆定位方法各实施例的步骤，为避免重复描述，在此不再赘述。
本申请公开了一种车辆定位方法，包括：
A1：基于车辆当前位置信息、车辆感知道路信息以及地图信息确定当前定位车道；
将实时获取的车辆感知道路信息与当前定位车道比对，确定失配积分值；
确定所述失配积分值大于等于预设积分值后，返回执行所述基于车辆当前位置信息、车辆感知道路信息以及地图信息确定定位车道。
A2：根据A1所述的车辆定位方法，还包括：
确定失配积分值小于预设积分值后，确定车辆是否处于转向状态；
在确定车辆处于转向状态后，根据车辆感知道路信息确定车辆是否变道，并在确定车辆发生变道后生成变道标识；
基于所述地图信息以及所述变道标识更新当前定位车道。
A3：根据A1所述的车辆定位方法，所述基于车辆当前位置信息、车辆感知道路信息以及地图信息确定当前定位车道，包括：
基于车辆当前位置信息以及地图信息，生成车道积分表；
基于车辆感知道路信息确定所述车道积分表中各车道的积分值；
将所述车道积分表中积分值大于第一预设值的车道确定为定位车道。
A4：根据A3所述的车辆定位方法，所述车辆感知道路信息包括感知车道线信息以及感知护栏信息；所述基于车辆感知道路信息确定所述车道积分表中各车道的积分值，包括：
确定车辆当前位置信息对应的地图信息中的车道数量，并基于车道数量对应的第一积分规则、 感知车道线信息以及感知护栏信息确定所述车道积分表中各车道的积分值。
A5：根据A4所述的车辆定位方法，车道数量为1对应的第一积分规则为：所述车辆感知道路信息为有一侧车道线为实线，且左侧有护栏，则对所在单车道加分；
车道数量为2对应的第一积分规则为：所述感知车道线信息以及所述感知护栏信息为左侧最近邻车道线为实线且右侧最近邻车道线为虚线，则左侧车道加分；所述感知车道线信息以及所述感知护栏信息为左侧有护栏，且右侧最近邻车道线为虚线，则左侧车道加分；所述感知车道线信息以及所述感知护栏信息为右侧最近邻车道线为实线，且左侧最近邻车道线为虚线，则右侧车道加分；所述感知车道线信息以及所述感知护栏信息为右侧有护栏且左侧最近邻车道线为虚线，则右侧车道加分；
车道数量为3对应的第一积分规则为：所述感知车道线信息以及所述感知护栏信息为左右两侧最近邻车道线均为虚线且没有护栏，则中间车道加分；所述感知车道线信息以及所述感知护栏信息为左侧最近邻车道线为实线，右侧最近邻车道线为虚线且没有右侧护栏，则左侧车道加分；所述感知车道线信息以及所述感知护栏信息为左侧有护栏，右侧最近邻车道线为虚线且没有右侧护栏，则左侧车道加分；所述感知车道线信息以及所述感知护栏信息为右侧最近邻车道线为实线，左侧最近邻车道线为虚线且左侧没有护栏，则右侧车道加分。
A6：根据A4所述的车辆定位方法，车道数量大于等于4对应的第一积分规则为：所述感知车道线信息以及所述感知护栏信息为左侧最近邻车道线为实线，右侧最近邻车道线为虚线且没有右侧护栏则最左侧车道加分；所述感知车道线信息以及所述感知护栏信息为左侧有护栏，右侧最近邻车道线为虚线且没有右侧护栏则最左侧车道加分；所述感知车道线信息以及所述感知护栏信息为右侧最近邻车道线为实线，左侧最近邻车道线为虚线，且左侧没有护栏，则最右侧车道加分；所述感知车道线信息以及所述感知护栏信息为左右两侧最近邻车道线均为虚线且没有护栏，则将所述感知车道线信息以及所述感知护栏信息与中间各车道的车道线比对，并对比对一致的中间车道加分。
A7：根据A4所述的车辆定位方法，所述车辆感知道路信息还包括周边车辆信息，在所述确定车辆当前位置信息对应的地图信息中的车道数量，并基于车道数量对应的第一积分规则、感知车道线信息以及感知护栏信息确定所述车道积分表中各车道的积分值之后，还包括：
基于车道数量对应的第二积分规则以及所述周边车辆信息更新所述车道积分表中各车道的积分值。
A8：根据A7所述的车辆定位方法，车道数量为2对应的第二积分规则为：所述周边车辆信息为识别出左侧有运动车辆且与当前车辆的横向距离大于第二预设值，则对右侧车道加分；所述周边车辆信息为识别出右侧有运动车辆且与当前车辆的横向距离大于第二预设值，则对左侧车道加分；
车道数量大于等于3对应的第二积分规则为：所述周边车辆信息为识别出左侧有运动车辆且与当前车辆的横向距离大于第二预设值，则对最左侧车道减分；所述周边车辆信息为识别出右侧有运动车辆且与当前车辆的横向距离大于第二预设值，则对最右侧车道减分；若车道数量等于3，所述周边车辆信息为左右两侧均识别出运动车辆且与当前车辆的横向距离大于第二预设值，则对中间车道加分。
A9：根据A7所述的车辆定位方法，在确定所述周边车辆信息确定运动车辆与当前车辆的横向距离大于第二预设值的持续时间大于第一预设时间后，执行基于车道数量对应的第二积分规则以及 所述周边车辆信息更新所述车道积分表中各车道的积分值的操作。
A10：根据A3所述的车辆定位方法，在所述基于车辆当前位置信息、车辆感知道路信息以及地图信息确定当前定位车道过程中，还包括：
确定当前车道数量发生变化后，将所述车道积分表清零。
A11：根据A1所述的车辆定位方法，所述将实时获取的车辆感知道路信息与当前定位车道比对，确定失配积分值，包括：
基于当前定位车道对应的第三积分规则以及实时获取的车辆感知道路信息确定失配积分值。
A12：根据A11所述的车辆定位方法，
当前的定位车道为最左侧车道对应的第三积分规则为：实时获取的车辆感知道路信息为左侧最近邻车道线为虚线且左侧不存在护栏，增加失配积分值；实时获取的车辆感知道路信息为右侧存在护栏且车道总数大于1，增加失配积分值；
当前的定位车道为最右侧车道对应的第三积分规则为：实时获取的车辆感知道路信息为右侧最近邻车道线为虚线且右侧不存在护栏，增加失配积分值；实时获取的车辆感知道路信息为左侧存在护栏且车道总数大于1，增加失配积分值；
当前的定位车道为中间车道对应的第三积分规则为：实时获取的车辆感知道路信息为左侧第二车道线与当前车辆之间的距离小于第一阈值，且左侧第二车道线为实线，增加失配积分值；实时获取的车辆感知道路信息为右侧第二车道线与当前车辆之间的距离小于第一阈值，且右侧第二车道线为实线，增加失配积分值；实时获取的车辆感知道路信息为左侧存在护栏，且护栏与当前车辆之间的距离小于第二阈值，增加失配积分值；实时获取的车辆感知道路信息为右侧存在护栏，且护栏与当前车辆之间的距离小于第二阈值，增加失配积分值。
A13：根据A12所述的车辆定位方法，确定实时获取的车辆感知道路信息不符合任一所述第三积分规则后，则将失配积分值清零。
A14：根据A2所述的车辆定位方法，所述确定车辆是否处于转向状态，包括：
基于方向盘转角和/或横摆角速度信号确定车辆是否处于转向状态。
A15：根据A2所述的车辆定位方法，根据车辆感知道路信息确定车辆是否变道，并在确定车辆发生变道后生成变道标识包括：
在所述车辆感知道路信息中至少一侧车道线与当前车辆之间的距离发生跳变时，确定车辆变道；
根据所述车辆感知道路信息中的车道线变化方向生成变道标志位。
A16：根据A2所述的车辆定位方法，相邻两次变道标识的生成时间至少间隔第二预设时间。
B1：一种车辆定位装置，包括：
初始化模块，用于基于车辆当前位置信息、车辆感知道路信息以及地图信息确定当前定位车道；
定位监控模块，用于将实时获取的车辆感知道路信息与当前定位车道比对，确定失配积分值；
判断模块，用于确定所述失配积分值是否大于等于预设积分值，若是，指示所述初始化模块再次执行基于车辆当前位置信息、车辆感知道路信息以及地图信息确定当前定位车道的操作。
C1：一种电子设备，包括：处理器和存储器；
所述处理器通过调用所述存储器存储的程序或指令，用于执行如A1至A16任一项所述方法的步骤。
D1：一种计算机可读存储介质，所述计算机可读存储介质存储程序或指令，所述程序或指令使计算机执行如A1至A16任一项所述方法的步骤。
需要说明的是，对于前述的各方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员能够理解，本公开实施例并不受所描述的动作顺序的限制，因为依据本公开实施例，某些步骤可以采用其他顺序或者同时进行。另外，本领域技术人员能够理解，说明书中所描述的实施例均属于可选实施例。
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下，由语句“包括……”限定的要素，并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。
本领域的技术人员能够理解，尽管在此所述的一些实施例包括其它实施例中所包括的某些特征而不是其它特征，但是不同实施例的特征的组合意味着处于本公开的范围之内并且形成不同的实施例。
本领域的技术人员能够理解，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。
虽然结合附图描述了本公开的实施方式，但是本领域技术人员可以在不脱离本公开的精神和范围的情况下做出各种修改和变型，这样的修改和变型均落入由所附权利要求所限定的范围之内。
工业实用性
本公开在根据车辆当前位置信息、车辆感知道路信息以及地图信息确定当前定位车道后，通过将实时获取的车辆感知道路信息与当前定位车道比对，确定失配积分值的方式，持续监控定位车道是否正确，提高了车道定位的稳定性以及抗干扰能力，具有很强的工业实用性。

Claims (18)

  1. 一种车辆定位方法，其特征在于，包括：
    基于车辆当前位置信息、车辆感知道路信息以及地图信息确定当前定位车道；
    将实时获取的车辆感知道路信息与当前定位车道比对，确定失配积分值；所述将实时获取的车辆感知道路信息与当前定位车道比对，确定失配积分值包括：实时获取车辆感知道路信息，并将实时获取的车辆感知道路信息与上一时刻确定的当前定位车道进行比对，根据比对结果确定失配积分值，针对当前定位车道的不同指定不同的对比积分规则，符合对比积分规则，增加失配积分值；
    确定所述失配积分值大于等于预设积分值后，返回执行所述基于车辆当前位置信息、车辆感知道路信息以及地图信息确定定位车道。
  2. 根据权利要求1所述的车辆定位方法，其特征在于，还包括：
    确定失配积分值小于预设积分值后，确定车辆是否处于转向状态；
    在确定车辆处于转向状态后，根据车辆感知道路信息确定车辆是否变道，并在确定车辆发生变道后生成变道标识；
    基于所述地图信息以及所述变道标识更新当前定位车道。
  3. 根据权利要求1所述的车辆定位方法，其特征在于，所述基于车辆当前位置信息、车辆感知道路信息以及地图信息确定当前定位车道，包括：
    基于车辆当前位置信息以及地图信息，生成车道积分表；
    基于车辆感知道路信息确定所述车道积分表中各车道的积分值；
    将所述车道积分表中积分值大于第一预设值的车道确定为定位车道。
  4. 根据权利要求3所述的车辆定位方法，其特征在于，所述车辆感知道路信息包括感知车道线信息以及感知护栏信息；所述基于车辆感知道路信息确定所述车道积分表中各车道的积分值，包括：
    确定车辆当前位置信息对应的地图信息中的车道数量，并基于车道数量对应的第一积分规则、感知车道线信息以及感知护栏信息确定所述车道积分表中各车道的积分值。
  5. 根据权利要求4所述的车辆定位方法，其特征在于，车道数量为1对应的第一积分规则为：所述车辆感知道路信息为有一侧车道线为实线，且左侧有护栏，则对所在单车道加分；
    车道数量为2对应的第一积分规则为：所述感知车道线信息以及所述感知护栏信息为左侧最近邻车道线为实线且右侧最近邻车道线为虚线，则左侧车道加分；所述感知车道线信息以及所述感知护栏信息为左侧有护栏，且右侧最近邻车道线为虚线，则左侧车道加分；所述感知车道线信息以及所述感知护栏信息为右侧最近邻车道线为实线，且左侧最近邻车道线为虚线，则右侧车道加分；所 述感知车道线信息以及所述感知护栏信息为右侧有护栏且左侧最近邻车道线为虚线，则右侧车道加分；
    车道数量为3对应的第一积分规则为：所述感知车道线信息以及所述感知护栏信息为左右两侧最近邻车道线均为虚线且没有护栏，则中间车道加分；所述感知车道线信息以及所述感知护栏信息为左侧最近邻车道线为实线，右侧最近邻车道线为虚线且没有右侧护栏，则左侧车道加分；所述感知车道线信息以及所述感知护栏信息为左侧有护栏，右侧最近邻车道线为虚线且没有右侧护栏，则左侧车道加分；所述感知车道线信息以及所述感知护栏信息为右侧最近邻车道线为实线，左侧最近邻车道线为虚线且左侧没有护栏，则右侧车道加分。
  6. 根据权利要求4所述的车辆定位方法，其特征在于，车道数量大于等于4对应的第一积分规则为：所述感知车道线信息以及所述感知护栏信息为左侧最近邻车道线为实线，右侧最近邻车道线为虚线且没有右侧护栏则最左侧车道加分；所述感知车道线信息以及所述感知护栏信息为左侧有护栏，右侧最近邻车道线为虚线且没有右侧护栏则最左侧车道加分；所述感知车道线信息以及所述感知护栏信息为右侧最近邻车道线为实线，左侧最近邻车道线为虚线，且左侧没有护栏，则最右侧车道加分；所述感知车道线信息以及所述感知护栏信息为左右两侧最近邻车道线均为虚线且没有护栏，则将所述感知车道线信息以及所述感知护栏信息与中间各车道的车道线比对，并对比对一致的中间车道加分。
  7. 根据权利要求4所述的车辆定位方法，其特征在于，所述车辆感知道路信息还包括周边车辆信息，在所述确定车辆当前位置信息对应的地图信息中的车道数量，并基于车道数量对应的第一积分规则、感知车道线信息以及感知护栏信息确定所述车道积分表中各车道的积分值之后，还包括：
    基于车道数量对应的第二积分规则以及所述周边车辆信息更新所述车道积分表中各车道的积分值。
  8. 根据权利要求7所述的车辆定位方法，其特征在于，车道数量为2对应的第二积分规则为：所述周边车辆信息为识别出左侧有运动车辆且与当前车辆的横向距离大于第二预设值，则对右侧车道加分；所述周边车辆信息为识别出右侧有运动车辆且与当前车辆的横向距离大于第二预设值，则对左侧车道加分；
    车道数量大于等于3对应的第二积分规则为：所述周边车辆信息为识别出左侧有运动车辆且与当前车辆的横向距离大于第二预设值，则对最左侧车道减分；所述周边车辆信息为识别出右侧有运动车辆且与当前车辆的横向距离大于第二预设值，则对最右侧车道减分；若车道数量等于3，所述周边车辆信息为左右两侧均识别出运动车辆且与当前车辆的横向距离大于第二预设值，则对中间车道加分。
  9. 根据权利要求7所述的车辆定位方法，其特征在于，在确定所述周边车辆信息确定运动车辆与当前车辆的横向距离大于第二预设值的持续时间大于第一预设时间后，执行基于车道数量对应的第二积分规则以及所述周边车辆信息更新所述车道积分表中各车道的积分值的操作。
  10. 根据权利要求3所述的车辆定位方法，其特征在于，在所述基于车辆当前位置信息、车辆 感知道路信息以及地图信息确定当前定位车道过程中，还包括：
    确定当前车道数量发生变化后，将所述车道积分表清零。
  11. 根据权利要求1所述的车辆定位方法，其特征在于，所述将实时获取的车辆感知道路信息与当前定位车道比对，确定失配积分值，包括：
    基于当前定位车道对应的第三积分规则以及实时获取的车辆感知道路信息确定失配积分值；
    当前的定位车道为最左侧车道对应的第三积分规则为：实时获取的车辆感知道路信息为左侧最近邻车道线为虚线且左侧不存在护栏，增加失配积分值；实时获取的车辆感知道路信息为右侧存在护栏且车道总数大于1，增加失配积分值；
    当前的定位车道为最右侧车道对应的第三积分规则为：实时获取的车辆感知道路信息为右侧最近邻车道线为虚线且右侧未不存在护栏，增加失配积分值；实时获取的车辆感知道路信息为左侧存在护栏且车道总数大于1，增加失配积分值；
    当前的定位车道为中间车道对应的第三积分规则为：实时获取的车辆感知道路信息为左侧第二车道线与当前车辆之间的距离小于第一阈值，且左侧第二车道线为实线，增加失配积分值；实时获取的车辆感知道路信息为右侧第二车道线与当前车辆之间的距离小于第一阈值，且右侧第二车道线为实线，增加失配积分值；实时获取的车辆感知道路信息为左侧存在护栏，且护栏与当前车辆之间的距离小于第二阈值，增加失配积分值；实时获取的车辆感知道路信息为右侧存在护栏，且护栏与当前车辆之间的距离小于第二阈值，增加失配积分值。
  12. 根据权利要求11所述的车辆定位方法，其特征在于，确定实时获取的车辆感知道路信息不符合任一所述第三积分规则后，则将失配积分值清零。
  13. 根据权利要求2所述的车辆定位方法，其特征在于，所述确定车辆是否处于转向状态，包括：
    基于方向盘转角和/或横摆角速度信号确定车辆是否处于转向状态。
  14. 根据权利要求2所述的车辆定位方法，其特征在于，
    根据车辆感知道路信息确定车辆是否变道，并在确定车辆发生变道后生成变道标识包括：
    在所述车辆感知道路信息中至少一侧车道线与当前车辆之间的距离发生跳变时，确定车辆变道；
    根据所述车辆感知道路信息中的车道线变化方向生成变道标志位。
  15. 根据权利要求2所述的车辆定位方法，其特征在于，相邻两次变道标识的生成时间至少间隔第二预设时间。
  16. 一种车辆定位装置，其特征在于，包括：
    初始化模块，用于基于车辆当前位置信息、车辆感知道路信息以及地图信息确定当前定位车道；
    定位监控模块，用于将实时获取的车辆感知道路信息与当前定位车道比对，确定失配积分值；所述将实时获取的车辆感知道路信息与当前定位车道比对，确定失配积分值包括：实时获取车辆感知道路信息，并将实时获取的车辆感知道路信息与上一时刻确定的当前定位车道进行比对，根据比对结果确定失配积分值，针对当前定位车道的不同指定不同的对比积分规则，符合对比积分规则，增加失配积分值；
    判断模块，用于确定所述失配积分值是否大于等于预设积分值，若是，指示所述初始化模块再次执行基于车辆当前位置信息、车辆感知道路信息以及地图信息确定当前定位车道的操作。
  17. 一种电子设备，其特征在于，包括：处理器和存储器；
    所述处理器通过调用所述存储器存储的程序或指令，用于执行如权利要求1至15任一项所述方法的步骤。
  18. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储程序或指令，所述程序或指令使计算机执行如权利要求1至15任一项所述方法的步骤。
PCT/CN2022/096647 2021-06-28 2022-06-01 车辆定位方法、装置、电子设备和存储介质 WO2023273780A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
KR1020237045521A KR102662425B1 (ko) 2021-06-28 2022-06-01 차량 측위 방법, 장치, 전자기기 및 저장 매체
EP22831601.4A EP4365048A1 (en) 2021-06-28 2022-06-01 Vehicle positioning method and apparatus, electronic device, and storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110720086.5 2021-06-28
CN202110720086.5A CN113232658B (zh) 2021-06-28 2021-06-28 一种车辆定位方法、装置、电子设备和存储介质

Publications (1)

Publication Number Publication Date
WO2023273780A1 true WO2023273780A1 (zh) 2023-01-05

Family

ID=77141015

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/096647 WO2023273780A1 (zh) 2021-06-28 2022-06-01 车辆定位方法、装置、电子设备和存储介质

Country Status (3)

Country Link
EP (1) EP4365048A1 (zh)
CN (1) CN113232658B (zh)
WO (1) WO2023273780A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116380107A (zh) * 2023-05-29 2023-07-04 速度科技股份有限公司 一种基于高精地图对车辆进行定位的系统

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113232658B (zh) * 2021-06-28 2022-06-28 驭势（上海）汽车科技有限公司 一种车辆定位方法、装置、电子设备和存储介质
CN114954527A (zh) * 2022-06-01 2022-08-30 驭势（上海）汽车科技有限公司 一种车道级导航规划方法、装置、设备、介质及车辆

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20120081771A (ko) * 2011-01-12 2012-07-20 현대모비스 주식회사 차선 유지 제어 시스템 및 방법
US20180345960A1 (en) * 2017-06-06 2018-12-06 Toyota Jidosha Kabushiki Kaisha Lane change assist device
KR20190061137A (ko) * 2017-11-27 2019-06-05 현대모비스 주식회사 가상차선 유지 장치 및 그 방법
CN110688920A (zh) * 2019-09-17 2020-01-14 宁波吉利汽车研究开发有限公司 一种无人驾驶控制方法、装置及服务器
CN110979346A (zh) * 2019-11-29 2020-04-10 北京百度网讯科技有限公司 确定车辆所处车道的方法、装置及设备
CN111380539A (zh) * 2018-12-28 2020-07-07 沈阳美行科技有限公司 车辆定位、导航方法和装置及相关系统
US20200361489A1 (en) * 2019-05-15 2020-11-19 Rideflux Inc. Method and apparatus for controlling a vehicle's driving operation using advance information
CN112415552A (zh) * 2020-11-17 2021-02-26 北京百度网讯科技有限公司 车辆位置的确定方法、装置及电子设备
CN113232658A (zh) * 2021-06-28 2021-08-10 驭势（上海）汽车科技有限公司 一种车辆定位方法、装置、电子设备和存储介质

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE10334620B4 (de) * 2003-07-30 2023-07-06 Robert Bosch Gmbh Generierung von Verkehrshinweisen durch die Interpretation von Verkehrszeichenszenarien und Navigationsinformation in einem Fahrzeug
KR102058001B1 (ko) * 2012-09-03 2020-01-22 엘지이노텍 주식회사 차선 보정 시스템, 차선 보정 장치 및 이의 차선 보정 방법
CN105374212B (zh) * 2015-12-14 2017-07-18 上海交通大学 基于智能终端传感的高速公路车辆车道识别方法及系统
KR102541561B1 (ko) * 2018-02-12 2023-06-08 삼성전자주식회사 차량의 주행을 위한 정보를 제공하는 방법 및 그 장치들
CN111507129B (zh) * 2019-01-31 2023-08-22 广州汽车集团股份有限公司 车道级定位方法及系统、计算机设备、车辆、存储介质
FR3094318B1 (fr) * 2019-03-28 2021-02-26 Renault Sas Procédé de commande du positionnement d’un véhicule automobile sur une voie de circulation
CN112639907B (zh) * 2020-10-14 2024-04-02 驭势（上海）汽车科技有限公司 一种交通拥堵感知方法、装置、电子设备及存储介质
CN112622903B (zh) * 2020-10-29 2022-03-08 东北大学秦皇岛分校 一种车辆跟随驾驶环境下自主车辆的纵向和横向控制方法

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20120081771A (ko) * 2011-01-12 2012-07-20 현대모비스 주식회사 차선 유지 제어 시스템 및 방법
US20180345960A1 (en) * 2017-06-06 2018-12-06 Toyota Jidosha Kabushiki Kaisha Lane change assist device
KR20190061137A (ko) * 2017-11-27 2019-06-05 현대모비스 주식회사 가상차선 유지 장치 및 그 방법
CN111380539A (zh) * 2018-12-28 2020-07-07 沈阳美行科技有限公司 车辆定位、导航方法和装置及相关系统
US20200361489A1 (en) * 2019-05-15 2020-11-19 Rideflux Inc. Method and apparatus for controlling a vehicle's driving operation using advance information
CN110688920A (zh) * 2019-09-17 2020-01-14 宁波吉利汽车研究开发有限公司 一种无人驾驶控制方法、装置及服务器
CN110979346A (zh) * 2019-11-29 2020-04-10 北京百度网讯科技有限公司 确定车辆所处车道的方法、装置及设备
CN112415552A (zh) * 2020-11-17 2021-02-26 北京百度网讯科技有限公司 车辆位置的确定方法、装置及电子设备
CN113232658A (zh) * 2021-06-28 2021-08-10 驭势（上海）汽车科技有限公司 一种车辆定位方法、装置、电子设备和存储介质

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116380107A (zh) * 2023-05-29 2023-07-04 速度科技股份有限公司 一种基于高精地图对车辆进行定位的系统
CN116380107B (zh) * 2023-05-29 2023-08-22 速度科技股份有限公司 一种基于高精地图对车辆进行定位的系统

Also Published As

Publication number Publication date
KR20240011201A (ko) 2024-01-25
EP4365048A1 (en) 2024-05-08
CN113232658A (zh) 2021-08-10
CN113232658B (zh) 2022-06-28

Similar Documents

Publication Publication Date Title
WO2023273780A1 (zh) 车辆定位方法、装置、电子设备和存储介质
EP3470789A1 (en) Autonomous driving support apparatus and method
US20200174470A1 (en) System and method for supporting autonomous vehicle
JP7314213B2 (ja) 車両測位方法、装置、電子デバイス、記憶媒体及びプログラム
CN115214661A (zh) 基于目标车辆的驾驶样式的协同自适应巡航控制系统
US11092442B2 (en) Host vehicle position estimation device
JP6451857B2 (ja) 走行制御装置の制御方法および走行制御装置
JP2018180735A (ja) 動作範囲決定装置
US11738747B2 (en) Server device and vehicle
JP7147442B2 (ja) 地図情報システム
US11585945B2 (en) Method for the satellite-supported determination of a position of a vehicle
US11780448B2 (en) Vehicle behavior estimation method, vehicle control method, and vehicle behavior estimation device
CN109345870B (zh) 预防车辆碰撞的预警方法及装置
JP2005182310A (ja) 車両運転支援装置
EP3912877A1 (en) Driving assistance method and driving assistance device
US11590971B2 (en) Apparatus and method for determining traveling position of vehicle
JPWO2019207639A1 (ja) 行動選択装置、行動選択プログラム及び行動選択方法
CN113015243A (zh) 车辆定位方法、装置及车辆
CN115950441A (zh) 自动驾驶车辆的融合定位方法、装置及电子设备
CN114252086B (zh) 提示信息的输出方法、装置、设备、介质和车辆
US11260884B2 (en) Vehicle control apparatus, vehicle, operation method of vehicle control apparatus, and non-transitory computer-readable storage medium
JP7198005B2 (ja) 自車位置検出装置
KR102662425B1 (ko) 차량 측위 방법, 장치, 전자기기 및 저장 매체
JP2020135091A (ja) 認識装置及び認識方法
US20240116509A1 (en) Traveling control apparatus

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: 22831601

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2023579429

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 20237045521

Country of ref document: KR

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 2022831601

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2022831601

Country of ref document: EP

Effective date: 20240129