WO2022088722A1 - 导航方法、装置、智能驾驶设备及存储介质 - Google Patents

导航方法、装置、智能驾驶设备及存储介质 Download PDF

Info

Publication number
WO2022088722A1
WO2022088722A1 PCT/CN2021/102864 CN2021102864W WO2022088722A1 WO 2022088722 A1 WO2022088722 A1 WO 2022088722A1 CN 2021102864 W CN2021102864 W CN 2021102864W WO 2022088722 A1 WO2022088722 A1 WO 2022088722A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
lane
route
map
lanes
Prior art date
Application number
PCT/CN2021/102864
Other languages
English (en)
French (fr)
Inventor
李文强
陈龙泉
Original Assignee
上海商汤临港智能科技有限公司
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 上海商汤临港智能科技有限公司 filed Critical 上海商汤临港智能科技有限公司
Publication of WO2022088722A1 publication Critical patent/WO2022088722A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34Route searching; Route guidance
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02Control of position or course in two dimensions
    • G05D1/021Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0268Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means
    • G05D1/0274Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means using mapping information stored in a memory device

Definitions

  • the present disclosure relates to the technical field of automatic driving, and in particular, to a navigation method, an apparatus, an intelligent driving device and a storage medium.
  • the navigation module can provide the vehicle with the driving route and specific lane information, and the vehicle needs to rely on this information for decision-making and planning.
  • Embodiments of the present disclosure provide at least a navigation method, an apparatus, an intelligent driving device, and a computer-readable storage medium.
  • an embodiment of the present disclosure provides a navigation method, including:
  • the destination position of the vehicle determines the connection route of the lane between the current position and the destination position; the map is stored with the lane as the basic element;
  • the vehicle is controlled to travel along the determined connecting route of the lanes.
  • map is stored with the lane as the basic element, during the navigation process, route planning can be performed directly based on the specific lane, without the need to solve according to the road, thereby improving the planning efficiency and accuracy of the navigation.
  • a plurality of adjacent lanes in the same direction form a road; each lane is displayed with two lane lines for indicating the boundaries on both sides of the lane;
  • a connection route of the lanes between the current position and the destination position is determined according to the current position of the vehicle, each of the one or more road change positions, and the lanes in the map.
  • the road change position is determined according to the navigation route, and then the current position and the road change position are determined according to the current position of the vehicle, each road change position and the lane in the map
  • the connection route of the lanes between the destination locations so that the route planning of the lanes is carried out with the road change position as the node, which can reduce the amount of calculation in the process of lane route planning, thereby improving the efficiency of navigation planning.
  • the map further includes other elements connected to the lane;
  • the determining of the connection route map of the lane between the current position and the destination position according to the current position of the vehicle, the destination position of the vehicle and the stored map includes:
  • connection route of the lanes between the current position and the destination position is determined based on the attribute information of each lane in the map and other connected elements; the attribute information includes: lane identification code, driving direction, and steering.
  • the attribute information of the lane further includes: lane width, lane line parameters, lane speed limit, lane height limit, and types of vehicles allowed to pass through the lane.
  • the other elements include a drivable area; the drivable area is connected with at least one lane; the drivable area is shown in the form of an envelope; the envelope Network lines are used to indicate the boundaries of the drivable area.
  • the vehicle in the case that there are multiple lane connection routes between the current position and the destination position, the vehicle is controlled to follow the determined lane connection routes Before driving, the navigation method further includes:
  • the controlling the vehicle to travel according to the determined connection route of the lanes includes:
  • the determining, according to the prediction result, whether to control the vehicle to travel according to the alternative route includes:
  • the vehicle When there is a danger signal in the road conditions around the vehicle, the vehicle is controlled to travel according to the alternative route.
  • the vehicle when there is a danger signal in the road conditions around the vehicle, the vehicle can be controlled to travel according to the alternative route, and then the vehicle can be controlled to temporarily enter the drivable area when danger occurs to avoid the occurrence of safety accidents.
  • the drivable area includes at least one of the following:
  • the other elements further include an indicative object; the indicative object is displayed in the form of an envelope, and the envelope is used to indicate the size of the indicative object. contour.
  • controlling the vehicle to travel according to the determined connection route of the lanes includes:
  • the vehicle is controlled to travel along the determined connecting route of the lanes.
  • the additional indication of the indicative object can be detected in a targeted manner in the real scene. Attribute information, thereby avoiding the occurrence of security incidents caused by faulty detection by other devices, and improving the safety of autonomous vehicles.
  • the indicative object includes at least one of the following:
  • Traffic lights, stop lines, road signs, railings, zebra crossings are Traffic lights, stop lines, road signs, railings, zebra crossings.
  • the other elements further include obstructing objects; the obstructing objects are displayed in the form of envelopes, and the envelopes are used to indicate the size of the obstructing objects. contour.
  • controlling the vehicle to travel according to the determined connection route of the lanes includes:
  • the vehicle When it is determined according to the map that there is the obstructive object in the connecting route of the lane, the vehicle is controlled to travel along the connecting route to avoid the obstructing object.
  • the obstructive objects are also stored in the map, when it is determined that there are obstructive objects in the currently planned route, the obstructive objects can be detected in a targeted manner in the real scene, and the obstructive objects can be detected in advance. Good evasion preparation further improves the safety of autonomous vehicles.
  • the obstructive object includes at least one of the following:
  • Isolation guardrails flower beds, light poles.
  • an embodiment of the present disclosure provides a navigation device, including:
  • the positioning module is used to determine the current position of the vehicle
  • the planning module determines the connection route of the lane between the current position and the destination position; the map is stored with the lane as the basic element;
  • the control module is configured to control the vehicle to travel according to the determined connection route of the lanes.
  • embodiments of the present disclosure provide an intelligent driving device, including: a processor, a memory, and a bus, where the memory stores machine-readable instructions executable by the processor, and when the intelligent driving device runs, all The processor and the memory communicate through a bus, and the machine-readable instructions execute the steps of the navigation method according to the first aspect when the machine-readable instructions are executed by the processor.
  • an embodiment of the present disclosure provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is run by a processor, the steps of the navigation method according to the first aspect are executed .
  • FIG. 1 shows a flowchart of a navigation method provided by an embodiment of the present disclosure.
  • FIG. 2 shows a schematic diagram of a first driving road provided by an embodiment of the present disclosure.
  • FIG. 3 shows a flowchart of a method for determining a connection route of a lane provided by an embodiment of the present disclosure.
  • FIG. 4 shows a schematic diagram of a second driving road provided by an embodiment of the present disclosure.
  • FIG. 5 shows a schematic diagram of a third driving road provided by an embodiment of the present disclosure.
  • FIG. 6 shows a flowchart of a method for controlling a vehicle to travel according to a determined connection route of a lane provided by an embodiment of the present disclosure.
  • FIG. 7 shows a flowchart of another method for controlling a vehicle to travel along a determined connecting route of lanes provided by an embodiment of the present disclosure.
  • FIG. 8 shows a flowchart of a method for generating a map provided by an embodiment of the present disclosure.
  • FIG. 9 shows a schematic structural diagram of a navigation device provided by an embodiment of the present disclosure.
  • FIG. 10 shows a schematic diagram of a vehicle provided by an embodiment of the present disclosure.
  • autonomous driving technology can reduce the burden of people driving vehicles, improve traffic safety and improve traffic efficiency, so it is a hot research topic in recent years.
  • L0 level means no automation, that is, there is no automatic driving function, and all functions of the vehicle are completely controlled by the driver
  • L1 level means Driving support, that is, providing basic technical assistance to the driver, such as adaptive cruise control system, etc.
  • L2 level means partial automation, which realizes automatic control of various functions, such as automatic cruise control, lane keeping function, etc.
  • L3 level means conditional Automation, that is, under certain conditions, the system can be fully responsible for the control of the entire vehicle
  • Level L4 means full automation, that is, the vehicle can drive from the point of departure to the destination without the intervention or assistance of the driver.
  • High-precision map (hereinafter referred to as map) technology is an important part of autonomous driving technology.
  • map high-resolution maps have information with higher accuracy (eg, about 10-30 cm or higher accuracy levels), which can be lane shape, grade, curvature, slope, ground Signs, traffic signs, etc., are often the data base required for autonomous driving.
  • high-precision maps can provide a wider range of road information and are not affected by external factors such as weather and light. Therefore, high-precision maps can be used as redundancy and supplements for solutions such as vehicle vision and radar sensors for automatic driving systems to perform data fusion to achieve automatic vehicle control.
  • the existing map storage structure uses road and intersection elements as the basic units, and can only implement various map services at the road level.
  • it is necessary to solve the road first, and then plan the route of the specific lane, and then As a result, the existing navigation methods are inefficient. Therefore, in view of the complex urban road conditions, how to enable the vehicle to drive to a specific lane efficiently, accurately and safely is a technical problem to be solved by the present disclosure.
  • the present disclosure provides a navigation method, including: determining the current position of the vehicle; determining the lane between the current position and the destination position according to the current position of the vehicle, the destination position of the vehicle and a stored map
  • the connecting route of the lane is stored in the map as the basic element; the vehicle is then controlled to travel according to the connecting route of the determined lane.
  • route planning can be performed directly based on the specific lane, without the need to solve according to the road, thereby improving the planning efficiency and accuracy of the navigation.
  • the execution subject of the navigation method provided by the embodiment of the present disclosure may be an intelligent driving device, wherein the intelligent driving device includes but does not Limited to vehicles (eg, autonomous vehicles), robots, etc. Of course, it can also be any suitable device or system for controlling the automatic driving of the intelligent device, for example, an advanced driver assistance system (Advanced Driver Assistance Systems, ADAS) and the like.
  • the navigation method may be implemented by a processor invoking computer-readable instructions stored in a memory.
  • the navigation method includes the following S101-S103.
  • the latitude and longitude data corresponding to the vehicle can be acquired through a global positioning system (Global Positioning System, GPS), so as to determine the current position of the vehicle.
  • GPS Global Positioning System
  • IMU Inertial Measurement Unit
  • LiDAR LiDAR
  • the current real scene image can also be acquired through an image acquisition device (such as a camera installed on the vehicle), and the actual geographic location can be positioned based on the real scene image, such as image recognition of the real scene image, to determine the The geographic location information in the real scene corresponding to the real scene image.
  • image recognition recognition can be performed based on a pre-trained position prediction model, or recognition can be performed by comparing the real scene image with a pre-stored sample image.
  • the map may also include other elements connected (or referred to as being related) to the lane, and the lane includes basic attribute information including: lane identification code, driving direction, and steering. Therefore, the connection route of the lanes between the current position and the destination position can be determined based on the attribute information of each lane in the map and other elements of the connection.
  • the connection route of the lanes between the current position and the destination position can be determined based on the attribute information of each lane in the map and other elements of the connection.
  • the legitimacy and safety of the planned connection routes of the lanes can be improved.
  • the lane attribute information may further include at least one of: lane width, lane line parameters, lane speed limit, lane height limit, and vehicle types allowed to pass through the lane.
  • a lane L0 is represented by two lane lines E1 and E2 used to indicate the boundaries on both sides of the lane, and multiple adjacent lanes in the same direction ( For example, lane L0 and lane L1) form road A.
  • a vehicle driving in a lane has a unique driving direction, each lane has a unique identification code (such as L0 or L1), and the steering is divided into straight, left, left turn, right turn and right turn.
  • the width is used to represent the vertical distance between the two lane lines E1 and E2 of the lane.
  • connection relationship there is a connection relationship between the lane and other elements related to it. It can be understood that the connection relationship may be a direct connection or an indirect connection, which is not limited herein. In addition, the connection relationship can also be understood as the binding relationship and relative position relationship between other elements and the lane. If the vehicle 100 is currently in the lane L0 on the road A, after determining the position of the vehicle 100, other elements and connection relationships related to the lane L0 can be obtained, for example, the lane R connected with the lane L0 and the lane with the lane L0 can be obtained. L0 related stop line T, zebra crossing S and traffic lights (not shown) and so on.
  • lane in this document refers to a path marked by lane markings that is usually only allowed to drive through each vehicle one by one (eg, multiple vehicles are not allowed to drive through it in parallel), while
  • road may include one or more lanes.
  • the road A represented by the straight line in FIG. 2 contains two lanes L0 and L1.
  • a three-dimensional scene map representing the real scene can be generated by pre-shooting the video or image data of the real scene. The specific generation method is described later.
  • the three-dimensional scene map is generated based on the video data corresponding to the real scene.
  • the three-dimensional scene map in which the real scene completely overlaps in the same coordinate system, so the three-dimensional scene map can be used as a high-precision map of the real scene.
  • the vehicle is controlled to travel according to the determined connection route of the lanes.
  • the vehicle after planning the connection route of the lanes, the vehicle can be controlled to travel according to the route, so as to realize the purpose of automatic driving.
  • the map since the map includes lanes, that is, the map is stored with lanes as the basic elements, so that in the process of navigation, route planning can be performed directly based on specific lanes, and there is no need to solve based on roads, thereby improving navigation. planning efficiency and accuracy.
  • the navigation route may be generated based on the current location of the vehicle and the destination input by the user.
  • the navigation route is a global navigation route including the origin (the current position of the vehicle) and the destination. It should be noted that the navigation route is formed based on a road.
  • the navigation route may be a navigation route planned based on the shortest path between the origin and the destination, or may be a navigation route planned based on the path with the least time between the origin and the destination. This is not limited.
  • S1022 Determine one or more road change positions according to the navigation route.
  • the road change position refers to the specific position of the next road that needs to be determined based on the navigation route and the current position of the vehicle.
  • the current position of the vehicle 100 is located on the lane L0 on the road A. According to the navigation route, the vehicle 100 needs to drive to the next road B, so the road B is the road change location to be determined.
  • FIG. 4 is a schematic diagram of road driving in another embodiment of the present disclosure.
  • the current position of the vehicle 100 is located on the lane R0 on the road C.
  • the road change position should be the road D.
  • the lane L0 and the lane L1 are preferentially selected, that is, after the vehicle 100 changes to these two lanes, there is no need to change lanes in the subsequent driving process, which improves the convenience of driving.
  • route S1 and route S2 are two connecting routes between the current position (lane R0) and the road change position (road D) of the vehicle 100, namely route S1 and route S2.
  • route S2 should be planned for the vehicle 100 to travel.
  • the road change position is determined according to the navigation route
  • the current position of the vehicle the change position of each road and the road change position are determined according to the navigation route.
  • Determine the connection route of the lane between the current position and the destination position that is, after planning the global navigation route, then use the road as a node to determine the connection route of the lane between the road and the road, which can reduce the navigation process.
  • the calculation amount of the data in the system further improves the navigation efficiency.
  • FIG. 5 a schematic diagram of a third driving road provided by an embodiment of the present disclosure is shown.
  • other elements include a drivable area that is connected to at least one lane (eg, LB2).
  • the drivable area is shown on the map as an envelope, where the envelope is used to indicate the boundaries of the drivable area.
  • the drivable area includes at least one of a ground parking area, a garage entrance, a community entrance, an emergency parking area, and a non-motorized vehicle lane.
  • the navigation method further includes: determining the connecting route including the lane connecting the drivable area among the connecting routes of the plurality of lanes as an alternative route.
  • the vehicle 100 needs to change from the road E to the road F, and the three lanes on the road F all meet the requirements, but the lane LB2 is connected with a drivable area. Considering this factor, the vehicle 100 needs to be determined. Is it necessary to plan this route.
  • the method for controlling the vehicle to travel along the determined connecting route of the lanes includes the following S1031 to S1033.
  • a device such as a camera or a lidar installed on the vehicle may be used to collect road conditions around the vehicle.
  • the road conditions around the vehicle can be predicted according to the results of image collection. For example, if there are many vehicles or pedestrians in a certain lane according to the image, it can be predicted that the road conditions in the lane are relatively congested.
  • the vehicle 100 when there is a danger signal in the road conditions around the vehicle 100, the vehicle 100 is controlled to drive according to the alternative route, that is, the vehicle 100 is controlled to drive into the lane LB2.
  • the vehicle 100 can also be controlled to temporarily drive into the drivable area, thereby improving driving safety.
  • the basic attributes included when the drivable area is stored in the map include identifiers and geometric parameters.
  • the identifier is used to distinguish different drivable areas.
  • the geometric parameters are all envelopes, that is, the drivable area is displayed in the form of envelopes.
  • the envelope line refers to the boundary line of the drivable area.
  • other elements also include indicative objects.
  • Indicative objects are shown in the map in the form of envelopes, which are used to indicate the outline of the indicative objects.
  • the indicative objects include at least one of traffic lights, stop lines, road signs, zebra crossings and railings.
  • the method for controlling the vehicle to travel along the determined connecting route of the lane includes the following S103a to S103b.
  • the indicative object carries additional attribute information
  • indication information can be provided for the vehicle to drive.
  • the additional attribute information of the signal light is the color change of the signal light to instruct the vehicle to stop or continue driving;
  • the additional attribute information of the stop line is to prompt the vehicle to decelerate in advance;
  • the additional attribute information of the road sign is to prompt the vehicle to pay attention to the speed of travel, etc.
  • the additional attribute information of the railing is that the vehicle needs to stop running; and the additional attribute information of the zebra crossing is to remind the vehicle to slow down and avoid pedestrians. Since the additional attribute information of some indicative objects will change with time, it is necessary to detect the current state of the additional attribute information of the corresponding indicative objects in the actual environment when there are indicative objects in the map, such as , whether the traffic light is currently red or green.
  • the current state information of the indicative object can be detected in the real scene in a targeted manner, thereby avoiding the occurrence of security incidents caused by the detection errors of other devices, Improves the safety of autonomous vehicles.
  • the basic attribute information of the indicative object includes identifiers, geometric parameters (absolute positions) and additional attribute information.
  • the geometric parameters are represented by envelopes.
  • the envelope refers to the outline of the object.
  • the geometric elements of the zebra crossing are stored in two levels, the first level stores its outermost envelope rectangle parameters, and the second level stores the parameters of each rectangle in it.
  • the other elements also include obstructing objects, which are shown in the form of envelopes for indicating the contours of the obstructing objects.
  • the obstructing object includes at least one of a barrier fence, a flower bed, and a light pole, which is not limited herein.
  • the vehicle when it is determined from the map that the obstructing object exists in the connecting route of the lane, the vehicle is controlled to travel along the connecting route and avoiding the obstructing object.
  • obstructive objects are also stored in the map, when it is determined that there are obstructive objects in the currently planned route, the obstructive objects can be detected in the real scene in a targeted manner, and the obstructive objects can be detected in advance. Good evasion preparation further improves the safety of autonomous vehicles.
  • the basic attribute information of obstructive objects may include identifiers and geometric parameters (absolute positions), which will not be repeated here.
  • the map when the map is constructed, it can also include roads, in which lanes in the same driving direction between intersections are geometrically abstracted into roads. Roads also have unique driving directions.
  • the basic attributes of a road are the road identifier and the set of all associated lane identifiers. In the embodiment of the present disclosure, since the construction is directly based on the lane, the concept of the road is weakened, and its geometric parameters and road layer relationships are not stored.
  • intersection in the embodiment of the present disclosure is the actual intersection, and the basic attributes of the intersection include the identifier and geometric parameters of the intersection.
  • the geometric parameter of the intersection is the actual envelope of the intersection (see Z in Figure 5).
  • the camera or radar of the vehicle should be combined to detect whether the obstructive object exists in the actual environment and the indication
  • the image acquisition or radar detection may be misjudged.
  • the data in the map should be used as the to control the driving of the vehicle.
  • the current situation should be reported to remind relevant personnel that there may be errors in the map data, so as to further confirm and modify the elements stored in the map, thereby improving the accuracy of the map.
  • a multi-angle aerial photography of the real scene can be performed in advance by a drone, and a large number of real scene sample images corresponding to the real scene can be obtained.
  • the method when generating an initial three-dimensional scene virtual model corresponding to the real scene based on a plurality of real scene sample images, the method may include:
  • the feature points extracted for each real scene sample image may be points that can represent the key information of the real scene sample image.
  • the feature points here may represent the outline of the building. feature points of information.
  • the pre-stored 3D sample image matching the real scene may include a pre-set 3D image capable of characterizing the appearance features of the reality scene and with dimension annotations, for example, it may be a 3D image that characterizes the appearance features of the reality scene.
  • Computer Aided Design (CAD) three-dimensional drawing.
  • the feature point cloud composed of the feature points can form a three-dimensional model representing the real scene.
  • the feature points in the feature point cloud here are unitless, and the feature point cloud is composed of The 3D model is also unitless. Then, after aligning the feature point cloud with a 3D map with scale annotations that can characterize the topographical features of the real scene, the initial 3D scene virtual model corresponding to the real scene is obtained.
  • the generated initial three-dimensional scene virtual model may be distorted, and then it can be adjusted through the two-dimensional map corresponding to the real scene, and a high-accuracy three-dimensional scene virtual model can be obtained.
  • some feature points representing the spatial location points of the edges and corners of buildings can be selected as the calibration feature points here, and then based on the real coordinate data corresponding to the calibration feature points and the calibration feature points in the initial three-dimensional scene virtual model.
  • Coordinate data determine the coordinate data adjustment amount, and then correct the coordinate data of each feature point in the initial three-dimensional scene virtual model based on the coordinate data adjustment amount, that is, a map with high accuracy can be obtained.
  • the writing order of each step does not mean a strict execution order but constitutes any limitation on the implementation process, and the specific execution order of each step should be based on its function and possible Internal logic is determined.
  • the embodiment of the present disclosure also provides a navigation device corresponding to the navigation method. Since the principle of solving the problem of the device in the embodiment of the present disclosure is similar to the above-mentioned navigation method in the embodiment of the present disclosure, the implementation of the device can refer to the method implementation, and the repetition will not be repeated.
  • the navigation device includes:
  • the positioning module 501 is used to determine the current position of the vehicle
  • the planning module 502 according to the current position of the vehicle, the destination position of the vehicle and the stored map, determines the connection route of the lane between the current position and the destination position; the map is stored with the lane as the basic element ;
  • the control module 503 is configured to control the vehicle to travel according to the determined connection route of the lanes.
  • a plurality of adjacent lanes in the same direction form a road; each lane is displayed with two lane lines used to indicate the boundaries on both sides of the lane; the planning module 502 is specifically used for:
  • a connection route of the lanes between the current position and the destination position is determined according to the current position of the vehicle, each road change position, and the lanes in the map.
  • the map also includes other elements connected with the lane; the planning module 502 is specifically used for:
  • connection route of the lanes between the current position and the destination position is determined based on the attribute information of each lane in the map and other connected elements; the attribute information includes: lane identification code, driving direction, and steering.
  • the attribute information of the lane further includes: lane width, lane line parameters, lane speed limit, lane height limit, and types of vehicles allowed to pass through the lane.
  • the other elements include a drivable area; the drivable area is connected with at least one lane; the drivable area is displayed in the form of an envelope; the envelope is used to indicate the boundary of the drivable area.
  • the planning module 502 is further configured to:
  • the control module 503 is specifically used for:
  • control module 503 is specifically used for:
  • the vehicle When there is a danger signal in the road conditions around the vehicle, the vehicle is controlled to travel according to the alternative route.
  • the drivable area includes at least one of the following:
  • the other elements further include an indicative object; the indicative object is displayed in the form of an envelope, and the envelope is used to indicate the outline of the indicative object.
  • control module 503 is specifically used for:
  • the vehicle is controlled to travel along the determined connecting route of the lanes.
  • the indicative object includes at least one of the following:
  • Traffic lights, stop lines, road signs, railings, zebra crossings are Traffic lights, stop lines, road signs, railings, zebra crossings.
  • the other elements further include obstructing objects; the obstructing objects are displayed in the form of envelopes, and the envelopes are used to indicate the outlines of the obstructing objects.
  • control module 503 is specifically used for:
  • the vehicle When it is determined according to the map that there is the obstructive object in the connecting route of the lane, the vehicle is controlled to travel along the connecting route to avoid the obstructing object.
  • the obstructing object includes at least one of the following:
  • Isolation guardrails flower beds, light poles.
  • a schematic structural diagram of a vehicle 700 includes a processor 701 , a memory 702 , and a bus 703 .
  • the memory 702 is used to store the execution instructions, including the memory 7021 and the external memory 7022; the memory 7021 here is also called the internal memory, which is used to temporarily store the operation data in the processor 701 and the data exchanged with the external memory 7022 such as the hard disk,
  • the processor 701 exchanges data with the external memory 7022 through the memory 7021 .
  • the memory 702 is specifically used to store the application program code for executing the solution of the present application, and the execution is controlled by the processor 701 . That is, when the vehicle 700 is running, the processor 701 communicates with the memory 702 through the bus 703 , so that the processor 701 executes the application code stored in the memory 702 .
  • the memory 702 may be, but not limited to, random access memory (Random Access Memory, RAM), read only memory (Read Only Memory, ROM), programmable read only memory (Programmable Read-Only Memory, PROM), or Erasable Programmable Read-Only Memory (EPROM), Electrical Erasable Programmable Read-Only Memory (EEPROM), etc.
  • RAM Random Access Memory
  • ROM read only memory
  • PROM programmable read only memory
  • EPROM Erasable Programmable Read-Only Memory
  • EEPROM Electrical Erasable Programmable Read-Only Memory
  • the processor 701 may be an integrated circuit chip with signal processing capability.
  • the above-mentioned processor can be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC) , Field Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
  • DSP digital signal processor
  • ASIC application-specific integrated circuit
  • FPGA Field Programmable Gate Array
  • a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
  • the structures illustrated in the embodiments of the present application do not constitute a specific limitation on the vehicle 700 .
  • the vehicle 700 may include more or fewer components than shown, or some components may be combined, or some components may be split, or a different arrangement of components.
  • the illustrated components may be implemented in hardware, software, or a combination of software and hardware.
  • Embodiments of the present disclosure further provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is run by a processor, the steps of the navigation method in the above method embodiments are executed.
  • the storage medium may be a volatile or non-volatile computer-readable storage medium.
  • An embodiment of the present disclosure further provides a computer program product, the computer program product is loaded with program code, and the instructions included in the program code can be used to execute the steps of the navigation method in the foregoing method embodiment.
  • the computer program product is loaded with program code, and the instructions included in the program code can be used to execute the steps of the navigation method in the foregoing method embodiment.
  • the instructions included in the program code can be used to execute the steps of the navigation method in the foregoing method embodiment.
  • the above-mentioned computer program product can be specifically implemented by means of hardware, software or a combination thereof.
  • the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK), etc. Wait.
  • the units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
  • each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.
  • the functions, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a processor-executable non-volatile computer-readable storage medium.
  • the computer software products are stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present disclosure.
  • the aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program codes .

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Navigation (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种导航方法、装置、智能驾驶设备及存储介质,该导航方法包括:确定车辆的当前位置(S101);根据车辆的当前位置、车辆的目的位置以及存储的地图,确定当前位置和目的位置之间的车道的连接路线;地图以车道为基本元素存储(S102);控制车辆按照确定的车道的连接路线行驶(S103)。由于地图以车道为基本元素存储,使得在导航过程中,可以直接基于具体的车道进行路线规划,无需依据道路进行求解,进而提高了导航的规划效率及精准度。

Description

导航方法、装置、智能驾驶设备及存储介质
相关申请的交叉引用
本公开要求于2020年10月30日提交的、申请号为202011185601.6、发明名称为“导航方法、装置、智能行驶设备及存储介质”的中国专利申请的优先权,该中国专利申请公开的全部内容以引用的方式并入本文中。
技术领域
本公开涉及自动驾驶技术领域,具体而言,涉及一种导航方法、装置、智能驾驶设备和存储介质。
背景技术
自动驾驶中很重要的一个模块就是导航模块。导航模块可以为车辆提供行驶的路线以及具体的车道信息,车辆需要依靠这些信息进行决策规划。
然而,针对城市复杂的路况,如何使得车辆能够高效、精准且安全地行驶到具体车道上,为亟需解决的问题。
发明内容
本公开实施例至少提供一种导航方法、装置、智能驾驶设备及计算机可读存储介质。
第一方面,本公开实施例提供了一种导航方法,包括:
确定车辆的当前位置;
根据所述车辆的当前位置、所述车辆的目的位置以及存储的地图,确定所述当前位置和所述目的位置之间的车道的连接路线;所述地图以车道为基本元素存储;
控制所述车辆按照确定的车道的连接路线行驶。
本公开实施例中,由于该地图以车道为基本元素进行存储,使得在导航过程中,可以直接基于具体的车道进行路线规划,无需依据道路进行求解,进而提高了导航的规划效率及精准度。
根据第一方面,在一种可能的实施方式中,同一方向上的多个相邻车道组成道路;每个车道以两条用于指示车道两侧边界的车道线展示;
所述根据所述车辆的当前位置、所述车辆的目的位置以及存储的地图,确定所述当前位置和所述目的位置之间的车道的连接路线,包括:
根据所述车辆的当前位置、所述车辆的目的位置以及所述地图中的道路确定导航路线;
根据所述导航路线确定一个或多个道路变更位置;
根据所述车辆的当前位置、所述一个或多个道路变更位置中的各个道路变更位置及所述地图中的车道,确定所述当前位置和所述目的位置之间的车道的连接路线。
本公开实施例中,在规划了导航路线后,根据导航路线确定道路变更位置,再根据所述车辆的当前位置、各个道路变更位置及所述地图中的车道,确定所述当前位置和所 述目的位置之间的车道的连接路线,如此,以道路变更位置为节点进行车道的路线规划,可以减少在车道路线规划过程中的计算量,进而提高导航规划效率。
根据第一方面,在一种可能的实施方式中,所述地图中还包括与车道相连接的其他元素;
所述根据所述车辆的当前位置、所述车辆的目的位置以及存储的地图确定所述当前位置和所述目的位置之间的车道的连接路线地图,包括:
基于所述地图中的各个车道的属性信息以及连接的其他元素确定所述当前位置和所述目的位置之间的车道的连接路线;所述属性信息包括:车道标识码、行驶方向、转向。
本公开实施例中,由于在规划路线时考虑了车道基本属性信息(比如行驶方向、转向),以及车道与其他元素的连接关系,进而可以规划出合法且安全的路线。
根据第一方面,在一种可能的实施方式中,所述车道的属性信息还包括:车道宽度、车道线参数、车道限速、车道限高、车道允许通过的车辆类型。
根据第一方面,在一种可能的实施方式中,所述其他元素包括可行驶区域;所述可行驶区域与至少一个车道相连接;所述可行驶区域以包络线形式展示;所述包络线用于指示所述可行驶区域的边界。
根据第一方面,在一种可能的实施方式中,在所述当前位置和所述目的位置之间存在多条车道的连接路线的情况下,所述控制所述车辆按照确定的车道的连接路线行驶之前,所述导航方法还包括:
确定所述多条车道的连接路线中包含连接所述可行驶区域的车道的连接路线为备选路线;
所述控制所述车辆按照确定的车道的连接路线行驶,包括:
对所述车辆周围的路况进行图像采集;
根据采集的图像对所述车辆周围的路况进行预测;
根据预测的结果,确定是否控制所述车辆依据所述备选路线行驶。
本公开实施例中,当所规划的路线中存在可行驶区域时,需要根据当前的路况来确定具体行驶哪条路线,提高了自动驾驶的灵活性。
根据第一方面,在一种可能的实施方式中,所述根据预测的结果,确定是否控制所述车辆依据所述备选路线行驶,包括:
在所述车辆周围的路况存在危险信号时,控制所述车辆依据所述备选路线行驶。
本公开实施例中,当车辆周围的路况存在危险信号时,可以控制所述车辆依据所述备选路线行驶,进而可以在出现危险时控制车辆临时驶入可行驶区域以避免安全事故的发生。
根据第一方面,在一种可能的实施方式中,所述可行驶区域包括以下至少一种:
地面停车区、车库入口、小区入口、紧急停车区、非机动车道。
根据第一方面,在一种可能的实施方式中,所述其他元素还包括指示性物体;所述指示性物体以包络线形式展示,所述包络线用于指示所述指示性物体的轮廓。
根据第一方面,在一种可能的实施方式中,所述控制所述车辆按照确定的车道的连接路线行驶,包括:
在根据所述地图确定所述车道的连接路线中存在所述指示性物体时,检测实际环境中相应的指示性物体的当前状态;
根据所述相应的指示性物体的当前状态,控制所述车辆按照确定的车道的连接路线行驶。
本公开实施例中,由于地图中存储了与车道相对应的指示性物体,因此当确定当前规划的路线中存在指示性物体时,可以在现实场景中有针对性的检测该指示性物体的附加属性信息,进而可以避免因其他装置检测错误而导致的安全事件发生,提高了自动驾驶车辆的安全性。
根据第一方面,在一种可能的实施方式中,所述指示性物体包括以下至少一种:
交通信号灯、停止线、道路标志牌、栏杆、斑马线。
根据第一方面,在一种可能的实施方式中,所述其他元素还包括阻碍性物体;所述阻碍性物体以包络线形式展示,所述包络线用于指示所述阻碍性物体的轮廓。
根据第一方面,在一种可能的实施方式中,所述控制所述车辆按照确定的车道的连接路线行驶,包括:
在根据所述地图确定车道的连接路线中存在所述阻碍性物体时,控制所述车辆按照所述连接路线避开所述阻碍性物体行驶。
本公开实施例中,由于地图中还存储了阻碍性物体,如此,当确定当前规划的路线中存在阻碍性物体时,可以在现实场景中有针对性的对阻碍性物体进行检测,并提前做好避让准备,进一步提高了自动驾驶车辆的安全性。
根据第一方面,在一种可能的实施方式中,所述阻碍性物体包括以下至少一种:
隔离护栏、花坛、灯杆。
第二方面,本公开实施例提供了一种导航装置,包括:
定位模块,用于确定车辆的当前位置;
规划模块,根据所述车辆的当前位置、所述车辆的目的位置以及存储的地图,确定所述当前位置和所述目的位置之间的车道的连接路线;所述地图以车道为基本元素存储;
控制模块,用于控制所述车辆按照确定的车道的连接路线行驶。
第三方面,本公开实施例提供了一种智能驾驶设备,包括:处理器、存储器和总线,所述存储器存储有所述处理器可执行的机器可读指令,当智能驾驶设备运行时,所述处理器与所述存储器之间通过总线通信,所述机器可读指令被所述处理器执行时执行如第一方面所述的导航方法的步骤。
第四方面,本公开实施例提供了一种计算机可读存储介质,该计算机可读存储介质上存储有计算机程序,该计算机程序被处理器运行时执行如第一方面所述的导航方法的步骤。
为使本公开的上述目的、特征和优点能更明显易懂,下文特举较佳实施例,并配合所附附图,作详细说明如下。
附图说明
为了更清楚地说明本公开实施例的技术方案,下面将对实施例中所需要使用的附图作简单地介绍,此处的附图被并入说明书中并构成本说明书中的一部分,这些附图示出了符合本公开的实施例,并与说明书一起用于说明本公开的技术方案。应当理解,以下 附图仅示出了本公开的某些实施例,因此不应被看作是对范围的限定,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他相关的附图。
图1示出了本公开实施例所提供的一种导航方法的流程图。
图2示出了本公开实施例所提供的第一种行驶道路示意图。
图3示出了本公开实施例所提供的一种确定车道的连接路线的方法流程图。
图4示出了本公开实施例所提供的第二种行驶道路示意图。
图5示出了本公开实施例所提供的第三种行驶道路示意图。
图6示出了本公开实施例所提供的一种控制车辆按照确定的车道的连接路线行驶的方法流程图。
图7示出了本公开实施例所提供的另一种控制车辆按照确定的车道的连接路线行驶的方法流程图。
图8示出了本公开实施例所提供的一种生成地图的方法流程图。
图9示出了本公开实施例所提供的一种导航装置的结构示意图。
图10示出了本公开实施例所提供的一种车辆的示意图。
具体实施方式
为使本公开实施例的目的、技术方案和优点更加清楚,下面将结合本公开实施例中附图,对本公开实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本公开一部分实施例,而不是全部的实施例。通常在此处附图中描述和示出的本公开实施例的组件可以以各种不同的配置来布置和设计。因此,以下对在附图中提供的本公开的实施例的详细描述并非旨在限制要求保护的本公开的范围,而是仅仅表示本公开的选定实施例。基于本公开的实施例,本领域技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例,都属于本公开保护的范围。
应注意到:相似的标号和字母在下面的附图中表示类似项,因此,一旦某一项在一个附图中被定义,则在随后的附图中不需要对其进行进一步定义和解释。
本文中术语“和/或”,仅仅是描述一种关联关系,表示可以存在三种关系,例如,A和/或B,可以表示:单独存在A,同时存在A和B,单独存在B这三种情况。另外,本文中术语“至少一种”表示多种中的任意一种或多种中的至少两种的任意组合,例如,包括A、B、C中的至少一种,可以表示包括从A、B和C构成的集合中选择的任意一个或多个元素。
自动驾驶技术可以减轻人们驾驶车辆的负担,改善交通安全并提高交通效率,因此是近年来研发的热点。通常,根据自动化的程度不同,可将自动驾驶技术划分为L0-L4的级别,其中,L0级表示无自动化,即没有任何自动驾驶功能,完全由司机对车辆的所有功能进行控制;L1级表示驾驶支援,即向司机提供基本的技术性帮助,例如自适应巡航控制系统等;L2级表示部分自动化,其实现多种功能的自动控制,例如自动巡航控制、车道保持功能等;L3级表示有条件自动化,即在某些条件下,系统可以完全负责整个车辆的控制;L4级表示完全自动化,即车辆可以在无需司机的干预或协助的情况下由出发地驶向目的地。
高精度地图(下文称地图)技术是自动驾驶技术的重要组成部分。与一般供导航系统使用的传统地图相比,高精度地图具有更高精度(例如10-30厘米左右或更高的精度 级别)的信息,这些信息可以是车道形状、等级、曲率、坡度、地面标识、交通标志等等,其通常是实现自动驾驶所需的数据基础。与车辆视觉、雷达传感器等来收集数据的方案相比,高精度地图可以提供的道路信息范围更大,并且不受天气、光线等外界因素影响。因此,高精度地图可作为车辆视觉、雷达传感器等方案的冗余和补充,以供自动驾驶系统进行数据融合,实现车辆的自动控制。
然而,现有的地图的存储结构以道路和路口元素作为基本单元,仅能够实现道路级别的各种地图服务,在进行导航时需要先对道路进行求解,才能规划出具体的车道的路线,进而导致现有的导航方法的效率较低。因此,针对城市复杂的路况,如何使得车辆能够高效、精准且安全地行驶到具体车道上,为本公开要解决的技术问题。
基于上述研究,本公开提供了一种导航方法,包括:确定车辆的当前位置;根据车辆的当前位置、所述车辆的目的位置以及存储的地图,确定当前位置和所述目的位置之间的车道的连接路线;其中,地图以车道为基本元素存储;再控制车辆按照确定的车道的连接路线行驶。本公开实施例中,由于该地图以车道为基本元素进行存储,使得在导航过程中,可以直接基于具体的车道进行路线规划,无需依据道路进行求解,进而提高了导航的规划效率及精准度。
为便于对本实施例进行理解,首先对本公开实施例所公开的一种导航方法进行详细介绍,本公开实施例所提供的导航方法的执行主体可以是智能驾驶设备,其中,智能驾驶设备包括但不限于车辆(例如,自动驾驶车辆)、机器人等。当然,还可以是任何适当的用于操控智能设备自动行驶的装置或系统,例如,高级辅助驾驶系统(Advanced Driver Assistance Systems,ADAS)等。在一些可能的实现方式中,该导航方法可以通过处理器调用存储器中存储的计算机可读指令的方式来实现。
参见图1所示,为本公开实施例提供的导航方法的流程图,该导航方法包括以下S101~S103。
S101,确定车辆的当前位置。
示例性地,可以通过全球定位系统(Global Positioning System,GPS)来获取车辆所对应的经纬度数据,进而确定车辆的当前位置。另外,还可以结合GPS、惯性测量单元(Inertial Measurement Unit,IMU)及激光雷达进行融合定位,以提高对车辆定位的精准度。
示例性地,还可以通过图像采集设备(比如安装于车辆上的摄像头)获取当前的现实场景图像,基于该现实场景图像进行实际地理位置的定位,比如对该现实场景图像进行图像识别,确定该现实场景图像所对应的现实场景中的地理位置信息。进行图像识别时,可以基于预先训练好的位置预测模型进行识别,也可以通过将该现实场景图像与预存的样本图像进行比对的方式进行识别。
S102,根据车辆的当前位置、车辆的目的位置以及存储的地图,确定当前位置和所述目的位置之间的车道的连接路线;其中,地图以车道为基本元素存储。
示例性地,地图还可以包括与车道相连接(或被称为相关)的其他元素,车道包括基本属性信息,该基本属性信息包括:车道标识码、行驶方向、转向。因此,可以基于地图中的各个车道的属性信息以及连接的其他元素确定当前位置和目的位置之间的车道的连接路线。本公开实施例中,由于在路线规划的过程中考虑与车道相关的其他元素,以及各个车道的属性信息,进而可以提高所规划的车道的连接路线的合法性及安全性。
示例性地,车道属性信息还可以包括:车道宽度、车道线参数、车道限速、车道限高、车道允许通过的车辆类型中的至少一种。
参见图2所示,为本公开实施例提供的一种行驶道路的示意图,车道L0以两条用 于指示车道两侧边界的车道线E1和E2表示,同一方向上的多个相邻车道(如车道L0和车道L1)组成道路A。行驶在一个车道上的车辆具有唯一行驶方向,每个车道具有唯一标识码(如L0或L1),转向分为直行、左转、左转掉头、右转及右转掉头。宽度用来表示车道的两条车道线E1和E2之间的垂直距离。
示例性地,车道和与其相关的其他元素之间存在连接关系,可以理解,该连接关系可以是直接连接也可以是间接连接,在此不做限定。此外,连接关系还可以理解为其他元素与车道之间的绑定关系以及相对位置关系。若车辆100当前处于道路A上的车道L0,则在确定该车辆100的位置后,即可获得与该车道L0相关的其他元素以及连接关系,比如,与车道L0相连接的车道R以及与车道L0相关的停止线T、斑马线S及红绿灯(图未示)等。
需要说明的是,本文中的词语“车道”是指由车道线标识出的通常仅允许各辆车辆在其上逐一行驶通过(例如不允许多辆车辆在其上并行行驶通过)的路径,而词语“道路”可包含一个或多个车道。例如,图2中的直线表示的道路A包含两个车道L0和L1。
示例性地,可以通过预先拍摄现实场景得到的视频或者图像数据,生成表征现实场景的三维场景地图,具体生成方式详见后文,该三维场景地图基于现实场景对应的视频数据生成,可以构建与现实场景在相同坐标系下完全重合的三维场景地图,因此可以将该三维场景地图作为现实场景的高精度地图使用。
S103,控制所述车辆按照确定的车道的连接路线行驶。
示例地,当规划出车道的连接路线后,即可控制车辆按照路线行驶,进而实现自动驾驶的目的。
本公开实施例中,由于该地图包括车道,也即该地图以车道为基本元素进行存储,使得在导航过程中,可以直接基于具体的车道进行路线规划,无需依据道路进行求解,进而提高了导航的规划效率及精准度。
针对上述S102,在根据车辆的当前位置、车辆的目的位置以及存储的地图,确定当前位置和所述目的位置之间的车道的连接路线时,如图3所示,包括以下S1021~S1023:
S1021,根据车辆的当前位置、车辆的目的位置以及地图中的道路确定导航路线。
示例地,导航路线可以根据车辆当前的位置及用户输入目的地而生成。本申请实施例中,导航路线为包含有起始地(车辆的当前位置)和目的地的全局导航路线。需要说明的是,该导航路线是基于道路而形成的。此外,该导航路线可以是基于该起始地和目的地之间的最短路径而规划的导航路线,也可以是基于该起始地和目的地之间用时最少的路径而规划的导航路线,在此不做限定。
S1022,根据导航路线确定一个或多个道路变更位置。
示例性地,该道路变更位置是指基于导航路线和车辆的当前位置而需要确定的下一道路的具体位置。请再次参阅图2,车辆100当前的位置位于道路A上的车道L0上,根据导航路线,该车辆100需要行驶至下一道路B,因此该道路B即为需要确定的道路变更位置。
S1023,根据车辆的当前位置、各个道路变更位置及地图中的车道,确定当前位置和目的位置之间的车道的连接路线。
请参阅图4,为本公开另一实施方式中的道路行驶示意图。本实施方式中,车辆100的当前位置位于道路C上的车道R0上,根据导航路线,道路变更位置应为道路D,根据地图中的车道及连接关系,当确定了车辆100当前所处的车道R0时,根据车道R0的连接关系,道路D上的车道L0、车道L1及车道L2均会被索引到,但是根据导航路 线由于车辆100在道路D上需要直行,因此根据每个车道的基本属性信息(转向信息),优先选择车道L0、车道L1,也即当车辆100变更至这两个车道上之后,在后续行驶过程中不需要变道,提高了行驶的便捷性。
但是由于车道L0及车道L1均可以直行,使得车辆100在当前位置(车道R0)与道路变更位置(道路D)之间会存在两条连接路线,分别为路线S1和路线S2,此时,会考量变道因素以及转弯的舒适度(比如转弯半径的大小)来确定具体行驶哪条路线。例如,若根据变道次数少的原则,则应规划路线S2以供车辆100行驶。
本公开实施例中,由于先根据车辆的当前位置、车辆的目的位置以及地图中的道路确定导航路线,再根据导航路线确定道路变更位置,最后根据车辆的当前位置、各个道路变更位置及地图中的车道,确定当前位置和目的位置之间的车道的连接路线,也即在规划出全局导航路线后,再以道路为节点来确定道路与道路之间的车道的连接路线,如此可以减少导航过程中的数据的计算量,进一步提高了导航效率。
参见图5所示,为本公开实施例提供的第三种行驶道路示意图。本公开实施例中,其他元素包括可行驶区域,该可行驶区域与至少一个车道(如LB2)连接。可行驶区域在地图中以包络线形式展示,其中包络线用于指示可行驶区域的边界。一些实施方式中,可行驶区域包括地面停车区、车库入口、小区入口、紧急停车区、非机动车道中的至少一种。
在当前位置和目的位置之间存在多条车道的连接路线的情况下,为了提高自动驾驶的灵活性,应根据车辆周围的路况信息确定具体规划哪条路线行驶,因此,在控制车辆按照确定的车道的连接路线行驶之前,导航方法还包括:确定多条车道的连接路线中包含连接可行驶区域的车道的连接路线为备选路线。
示例地,根据导航路线,车辆100需要从道路E变更到道路F,而道路F上的三个车道均满足要求,但其中车道LB2连接有可行驶区域,考虑到该因素,则需要确定车辆100是否有必要规划该条路线。
可以理解,可行驶区域(比如小区入口)附近由于人流量比较大,经常有行人出没,因此,正常情况下,道路F的路况良好的情况下,应尽量避免驶入车道LB2,进而保证行车的安全性。因此,正常情况下,在规划路线时,应将包含连接可行驶区域的车道的连接路线规划为备选路线。
在该情况下,参见图6所示,该控制车辆按照确定的车道的连接路线行驶的方法包括以下S1031~S1033。
S1031,对车辆周围的路况进行图像采集。
示例地,可以采用安装于车辆上的摄像头或者激光雷达等设备来对车辆周围的路况进行采集。
S1032,根据采集的图像对车辆周围的路况进行预测。
示例地,可以根据图像采集的结果预测车辆周围的路况,比如,若根据图像显示某一车道上的车辆或行人较多,则可以预测该车道的路况较为拥堵。
S1033,根据预测的结果,确定是否控制车辆依据备选路线行驶。
示例性地,请再次参阅图5,在车辆100周围路况存在危险信号时,比如当车道LB0上因交通肇事存在故障车辆时,此时若驶入该车道LB0以及与该车道LB0相邻的车道LB1,则存在很大概率发生堵塞或者碰撞事件。
因此,在一些实施方式中,在所述车辆100周围的路况存在危险信号时,控制所述车辆100依据所述备选路线行驶,也即控制车辆100驶入车道LB2。此外,若在突发事 件发生时,比如车道LB2或者车道LB1突然蹿出其他车辆时,还可以控制车辆100临时驶入该可行驶区域内,进而提高了行驶的安全性。
需要说明的是,可行驶区域在地图中存储时包括的基本属性有标识符和几何参数。其中,标识符用于将不同的可行驶区域进行区分。几何参数均为包络线,也即可行驶区域以包络线形式展示。其中,包络线是指可行驶区域的边界线。
示例性地,在构建地图时,只将从该车道变更至下一车道所需要的相关其他元素与相应的车道进行绑定以使得其存在连接关系即可。车辆100从车道LA1驶入道路F时,只需要关注斑马线X1和斑马线X3上的路况即可,而斑马线X2和X4对本次行驶并没有影响,因此,只需将斑马线X1和斑马线X3与车道LA1进行绑定即可,如此在导航时可以提高地图索引的效率,进一步提高导航路线规划的路线。
示例性地,其他元素还包括指示性物体。指示性物体在地图中以包络线形式展示,该包络线用于指示所述指示性物体的轮廓。其中,指示性物体包括交通信号灯、停止线、道路标志牌、斑马线及栏杆中的至少一种。
因此,本实施方式中,在确定连接路线中存在所述指示性物体时,参见图7所示,该控制车辆按照确定的车道的连接路线行驶的方法包括以下S103a~S103b。
S103a,在根据所述地图确定所述车道的连接路线中存在指示性物体时,检测实际环境中相应的指示性物体的当前状态。
可以理解,指示性物体带有附加属性信息,根据该附加属性信息可以为车辆行驶提供指示信息。具体地,信号灯的附加属性信息为信号灯的颜色变化以指示车辆停止或者继续行驶;停止线的附加属性信息为提示车辆需要提前减速;道路标志牌的附加属性信息为提示车辆需要注意的行驶速度等信息;栏杆的附加属性信息为需要车辆停止行驶;而斑马线的附加属性信息为提醒车辆注意减速以及避让行人。由于一些指示性物体的附加属性信息会随着时间的不同而发生变化,因此,需要在地图中存在指示性物体的情况下检测实际环境中相应的指示性物体的附加属性信息的当前状态,比如,交通信号灯当前为红色还是绿色。
S103b,根据所述相应的指示性物体的当前状态,控制所述车辆按照确定的车道的连接路线行驶。
示例地,当确定当前规划的路线中存在指示性物体时,可以在现实场景中有针对性地检测该指示性物体的当前状态信息,进而可以避免因其他装置检测错误而导致的安全事件发生,提高了自动驾驶车辆的安全性。
示例性地,在构建地图时,指示性物体的基本属性信息包括标识符、几何参数(绝对位置)和附加属性信息。其中,几何参数用包络线表示。该包络线是指物体的轮廓线。另外,需要说明的是,斑马线的几何元素采用二级存储,第一级存储其最外层包络矩形参数,第二层存储其里面的每一个矩形的参数。
示例性地,其他元素还包括阻碍性物体,所述阻碍性物体以包络线形式展示,所述包络线用于指示所述阻碍性物体的轮廓。该阻碍性物体包括隔离护栏、花坛、灯杆中的至少一种,在此不做限定。本实施方式中,在根据所述地图确定车道的连接路线中存在所述阻碍性物体时,控制所述车辆按照所述连接路线避开所述阻碍性物体行驶。
本公开实施例中,由于地图中还存储了阻碍性物体,如此,当确定当前规划的路线中存在阻碍性物体时,可以在现实场景中有针对性地对阻碍性物体进行检测,并提前做好避让准备,进一步提高了自动驾驶车辆的安全性。
另外,在地图构建时,与指示性物体类似,阻碍性物体的基本属性信息可以包括标识符和几何参数(绝对位置),在此不再赘述。
另外,在地图构建时,也可包括道路,其中将十字路口之间,同一个行驶方向的车道几何抽象成道路。道路也具有唯一行驶方向。道路的基本属性为道路的标识符和所有关联的车道标识符集合。在本公开实施例中由于直接以车道为基础进行构建,所以道路的概念被弱化,没有存储其几何参数和道路层关系。
本公开实施例中的路口即实际上的十字路口,十字路口的基本属性包含路口的标识符和几何参数。路口的几何参数为该路口的实际包络线(参图5中的Z)。
需要说明的是,在根据所述地图确定车道的连接路线中存在所述阻碍性物体或者指示性物体的情况下,应结合车辆的摄像头或者雷达去检测实际环境中是否存在该阻碍性物体以及指示性物体的当前状态,在检测结果与地图中的数据存在误差时,由于受外界环境(比如天气)的影响,图像采集或者雷达检测可能出现误判的情况,此时应以地图中的数据为准来控制车辆行驶。但是,为了确保后续行驶的安全性,应将当前的情况进行上报,以提示相关人员或许地图数据出现了错误,以进一步对地图中存储的元素进行确认和修改,进而提高地图的准确性。
针对上述多次提到的地图,如图8所示,具体可以按照以下方式预先构建,包括S601~S603。
S601,获取多张现实场景样本图像。
示例性地,可以预先通过无人机对该现实场景,比如某个城市进行多角度航拍,得到该现实场景对应的大量现实场景样本图像。
S602,基于多张现实场景样本图像,构建表征现实场景的初始三维场景虚拟模型。
针对S602,在基于多张现实场景样本图像,生成现实场景对应的初始三维场景虚拟模型时,可以包括:
(1)从获取的每张现实场景样本图像中提取多个特征点;
(2)基于提取的多个特征点,以及预存的与现实场景匹配的三维样本图,生成初始三维场景虚拟模型;其中,三维样本图为预存储的表征现实场景形貌特征的三维图。
具体地,针对每张现实场景样本图像提取的特征点可以为能够表征该张现实场景样本图像关键信息的点,比如针对包含建筑物的现实场景样本图像,这里的特征点可以表示该建筑物轮廓信息的特征点。
示例性地,这里预存的与现实场景匹配的三维样本图可以包括提前设置好的能够表征该现实场景形貌特征、且带有尺寸标注的三维图,比如可以是表征该现实场景形貌特征的计算机辅助设计(Computer Aided Design,CAD)三维图。
针对该现实场景,当提取的特征点足够多时,特征点构成的特征点云,可以构成表征该现实场景的三维模型,这里的特征点云中的特征点是没有单位的,特征点云构成的三维模型也是没有单位的,然后将该特征点云与带有尺度标注的且能够表征该现实场景形貌特征的三维图对齐后,即得到该现实场景对应的初始三维场景虚拟模型。
S603,将构建的初始三维场景虚拟模型上的标定特征点与现实场景对应的标定特征点进行对齐,生成地图。
生成的初始三维场景虚拟模型可能会存在失真现象,然后可以通过现实场景对应的二维地图对其进行调整,可以得到准确度较高的三维场景虚拟模型。
针对S603,在将构建的初始三维场景虚拟模型上的标定特征点与现实场景对应的标定特征点进行对齐,生成地图时,包括:
(1)在现实场景对应的初始三维场景虚拟模型中提取用于表征现实场景多个空间位置点的标定特征点;
(2)确定标定特征点在现实场景对应的真实二维地图中的真实坐标数据,并基于每个标定特征点对应的真实坐标数据,调整初始三维场景虚拟模型中各个特征点的坐标数据。
示例性地,可以选择一些表征建筑物边缘、角落的空间位置点的特征点作为这里的标定特征点,然后基于标定特征点对应的真实坐标数据以及该标定特征点在初始三维场景虚拟模型中的坐标数据,确定坐标数据调整量,然后基于该坐标数据调整量对初始三维场景虚拟模型中各个特征点的坐标数据进行修正,即可以得到准确度较高的地图。
本领域技术人员可以理解,在具体实施方式的上述方法中,各步骤的撰写顺序并不意味着严格的执行顺序而对实施过程构成任何限定,各步骤的具体执行顺序应当以其功能和可能的内在逻辑确定。
基于同一技术构思,本公开实施例中还提供了与导航方法对应的导航装置,由于本公开实施例中的装置解决问题的原理与本公开实施例上述导航方法相似,因此装置的实施可以参见方法的实施,重复之处不再赘述。
参照图9所示,为本公开实施例提供的一种导航装置500的示意图,该导航装置包括:
定位模块501,用于确定车辆的当前位置;
规划模块502,根据所述车辆的当前位置、所述车辆的目的位置以及存储的地图,确定所述当前位置和所述目的位置之间的车道的连接路线;所述地图以车道为基本元素存储;
控制模块503,用于控制所述车辆按照确定的车道的连接路线行驶。
在一种可能的实施方式中,同一方向上的多个相邻的车道组成道路;每个车道以两条用于指示车道两侧边界的车道线展示;所述规划模块502具体用于:
根据所述车辆的当前位置、所述车辆的目的位置以及所述地图中的道路确定导航路线;
根据所述导航路线确定一个或多个道路变更位置;
根据所述车辆的当前位置、各个道路变更位置及所述地图中的车道,确定所述当前位置和所述目的位置之间的车道的连接路线。
在一种可能的实施方式中,所述地图中还包括与车道相连接的其他元素;所述规划模块502具体用于:
基于所述地图中的各个车道的属性信息以及连接的其他元素确定所述当前位置和所述目的位置之间的车道的连接路线;所述属性信息包括:车道标识码、行驶方向、转向。
在一种可能的实施方式中,所述车道的属性信息还包括:车道宽度、车道线参数、车道限速、车道限高、车道允许通过的车辆类型。
在一种可能的实施方式中,所述其他元素包括可行驶区域;所述可行驶区域与至少一个车道相连接;所述可行驶区域以包络线形式展示;所述包络线用于指示所述可行驶区域的边界。
在一种可能的实施方式中,在所述当前位置和所述目的位置之间存在多条车道的连接路线的情况下,所述规划模块502还用于:
确定所述多条车道的连接路线中包含连接所述可行驶区域的车道的连接路线为备选路线;
所述控制模块503具体用于:
对所述车辆周围的路况进行图像采集;
根据采集的图像对所述车辆周围的路况进行预测;
根据预测的结果,确定是否控制所述车辆依据所述备选路线行驶。
在一种可能的实施方式中,所述控制模块503具体用于:
在所述车辆周围的路况存在危险信号时,控制所述车辆依据所述备选路线行驶。
在一种可能的实施方式中,所述可行驶区域包括以下至少一种:
地面停车区、车库入口、小区入口、紧急停车区、非机动车道。
在一种可能的实施方式中,所述其他元素还包括指示性物体;所述指示性物体以包络线形式展示,所述包络线用于指示所述指示性物体的轮廓。
在一种可能的实施方式中,所述控制模块503具体用于:
在根据所述地图确定所述车道的连接路线中存在指示性物体时,检测实际环境中相应的指示性物体的当前状态;
根据所述相应的指示性物体的当前状态,控制所述车辆按照确定的车道的连接路线行驶。
在一种可能的实施方式中,所述指示性物体包括以下至少一种:
交通信号灯、停止线、道路标志牌、栏杆、斑马线。
在一种可能的实施方式中,所述其他元素还包括阻碍性物体;所述阻碍性物体以包络线形式展示,所述包络线用于指示所述阻碍性物体的轮廓。
在一种可能的实施方式中,所述控制模块503具体用于:
在根据所述地图确定车道的连接路线中存在所述阻碍性物体时,控制所述车辆按照所述连接路线避开所述阻碍性物体行驶。
在一种可能的实施方式中,所述阻碍性物体包括以下至少一种:
隔离护栏、花坛、灯杆。
关于装置中的各模块的处理流程、以及各模块之间的交互流程的描述可以参照上述方法实施例中的相关说明,这里不再详述。
基于同一技术构思,本公开实施例还提供了一种车辆。参照图10所示,为本公开实施例提供的车辆700的结构示意图,包括处理器701、存储器702、和总线703。其中,存储器702用于存储执行指令,包括内存7021和外部存储器7022;这里的内存7021也称内存储器,用于暂时存放处理器701中的运算数据,以及与硬盘等外部存储器7022交换的数据,处理器701通过内存7021与外部存储器7022进行数据交换。
本申请实施例中,存储器702具体用于存储执行本申请方案的应用程序代码,并由处理器701来控制执行。也即,当车辆700运行时,处理器701与存储器702之间通过总线703通信,使得处理器701执行存储器702中存储的应用程序代码。
其中,存储器702可以是,但不限于,随机存取存储器(Random Access Memory,RAM),只读存储器(Read Only Memory,ROM),可编程只读存储器(Programmable Read -Only Memory,PROM),可擦除只读存储器(Erasable Programmable Read-Only Memory,EPROM),电可擦除只读存储器(Electric Erasable Programmable Read-Only Memory,EEPROM)等。其中,存储器702用于存储程序,处理器701在接收到执行指令后,执行程序,后述本发明实施例任一实施例揭示的流程定义的车辆200所执行的方法可以应用于处理器701中,或者由处理器701实现。
处理器701可能是一种集成电路芯片,具有信号的处理能力。上述的处理器可以是通用处理器,包括中央处理器(Central Processing Unit,CPU)、网络处理器(Network Processor,NP)等;还可以是数字信号处理器(DSP)、专用集成电路(ASIC)、现场可编程门阵列(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。可以实现或者执行本发明实施例中的公开的各方法、步骤及逻辑框图。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。
可以理解的是,本申请实施例示意的结构并不构成对车辆700的具体限定。在本申请另一些实施例中,车辆700可以包括比图示更多或更少的部件,或者组合某些部件,或者拆分某些部件,或者不同的部件布置。图示的部件可以以硬件,软件或软件和硬件的组合实现。
本公开实施例还提供一种计算机可读存储介质,该计算机可读存储介质上存储有计算机程序,该计算机程序被处理器运行时执行上述方法实施例中的导航方法的步骤。其中,该存储介质可以是易失性或非易失的计算机可读取存储介质。
本公开实施例还提供一种计算机程序产品,该计算机程序产品载有程序代码,所述程序代码包括的指令可用于执行上述方法实施例中的导航方法的步骤,具体可参见上述方法实施例,在此不再赘述。
其中,上述计算机程序产品可以具体通过硬件、软件或其结合的方式实现。在一个可选实施例中,所述计算机程序产品具体体现为计算机存储介质,在另一个可选实施例中,计算机程序产品具体体现为软件产品,例如软件开发包(Software Development Kit,SDK)等等。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的系统和装置的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。在本公开所提供的几个实施例中,应该理解到,所揭露的系统、装置和方法,可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,又例如,多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些通信接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外,在本公开各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个处理器可执行的非易失的计算机可读取存储介质中。基于这样的理解,本公开的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行本公开 各个实施例所述方法的全部或部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是:以上所述实施例,仅为本公开的具体实施方式,用以说明本公开的技术方案,而非对其限制,本公开的保护范围并不局限于此,尽管参照前述实施例对本公开进行了详细的说明,本领域的普通技术人员应当理解:任何熟悉本技术领域的技术人员在本公开揭露的技术范围内,其依然可以对前述实施例所记载的技术方案进行修改或可轻易想到变化,或者对其中部分技术特征进行等同替换;而这些修改、变化或者替换,并不使相应技术方案的本质脱离本公开实施例技术方案的精神和范围,都应涵盖在本公开的保护范围之内。因此,本公开的保护范围应所述以权利要求的保护范围为准。

Claims (17)

  1. 一种导航方法,包括:
    确定车辆的当前位置;
    根据所述车辆的当前位置、所述车辆的目的位置以及存储的地图,确定所述当前位置和所述目的位置之间的车道的连接路线;所述地图以车道为基本元素存储;
    控制所述车辆按照确定的车道的连接路线行驶。
  2. 根据权利要求1所述的方法,其中,同一方向上的多个相邻的车道组成道路;每个车道以两条用于指示车道两侧边界的车道线展示;
    所述根据所述车辆的当前位置、所述车辆的目的位置以及存储的地图,确定所述当前位置和所述目的位置之间的车道的连接路线,包括:
    根据所述车辆的当前位置、所述车辆的目的位置以及所述地图中的道路确定导航路线;
    根据所述导航路线确定一个或多个道路变更位置;
    根据所述车辆的当前位置、所述一个或多个道路变更位置中的各个道路变更位置及所述地图中的车道,确定所述当前位置和所述目的位置之间的车道的连接路线。
  3. 根据权利要求1或2所述的方法,其中,所述地图中还包括与车道相连接的其他元素;
    所述根据所述车辆的当前位置、所述车辆的目的位置以及存储的地图确定所述当前位置和所述目的位置之间的车道的连接路线,包括:
    基于所述地图中的各个车道的属性信息以及连接的其他元素确定所述当前位置和所述目的位置之间的车道的连接路线;所述属性信息包括:车道标识码、行驶方向、转向。
  4. 根据权利要求3所述的方法,其中,所述车道的属性信息还包括:车道宽度、车道线参数、车道限速、车道限高、车道允许通过的车辆类型。
  5. 根据权利要求3或4所述的方法,其中,所述其他元素包括可行驶区域;所述可行驶区域与至少一个车道相连接;所述可行驶区域以包络线形式展示;所述包络线用于指示所述可行驶区域的边界。
  6. 根据权利要求5所述的方法,其中,在所述当前位置和所述目的位置之间存在多条车道的连接路线的情况下,所述控制所述车辆按照确定的车道的连接路线行驶之前,所述导航方法还包括:
    确定所述多条车道的连接路线中包含连接所述可行驶区域的车道的连接路线为备选路线;
    所述控制所述车辆按照确定的车道的连接路线行驶,包括:
    对所述车辆周围的路况进行图像采集;
    根据采集的图像对所述车辆周围的路况进行预测;
    根据预测的结果,确定是否控制所述车辆依据所述备选路线行驶。
  7. 根据权利要求6所述的方法,其中,所述根据预测的结果,确定是否控制所述车辆依据所述备选路线行驶,包括:
    在所述车辆周围的路况存在危险信号时,控制所述车辆依据所述备选路线行驶。
  8. 根据权利要求5-7任一所述的方法,其中,所述可行驶区域包括以下至少一种:
    地面停车区、车库入口、小区入口、紧急停车区、非机动车道。
  9. 根据权利要求3-8任一项所述的方法,其中,所述其他元素还包括指示性物体;所述指示性物体以包络线形式展示,所述包络线用于指示所述指示性物体的轮廓。
  10. 根据权利要求9所述的方法,其中,所述控制所述车辆按照确定的车道的连接路线行驶,包括:
    在根据所述地图确定所述车道的连接路线中存在所述指示性物体时,检测实际环境中相应的指示性物体的当前状态;
    根据所述相应的指示性物体的当前状态,控制所述车辆按照确定的车道的连接路线行驶。
  11. 根据权利要求9或10所述的方法,其中,所述指示性物体包括以下至少一种:
    交通信号灯、停止线、道路标志牌、栏杆、斑马线。
  12. 根据权利要求3-11任一项所述的方法,其中,所述其他元素还包括阻碍性物体;所述阻碍性物体以包络线形式展示,所述包络线用于指示所述阻碍性物体的轮廓。
  13. 根据权利要求12所述的方法,其中,所述控制所述车辆按照确定的车道的连接路线行驶,包括:
    在根据所述地图确定车道的连接路线中存在所述阻碍性物体时,控制所述车辆按照所述连接路线避开所述阻碍性物体行驶。
  14. 根据权利要求12或13所述的方法,其中,所述阻碍性物体包括以下至少一种:
    隔离护栏、花坛、灯杆。
  15. 一种导航装置,包括:
    定位模块,用于确定车辆的当前位置;
    规划模块,根据所述车辆的当前位置、所述车辆的目的位置以及存储的地图,确定所述当前位置和所述目的位置之间的车道的连接路线;所述地图以车道为基本元素存储;
    控制模块,用于控制所述车辆按照确定的车道的连接路线行驶。
  16. 一种智能驾驶设备,包括:处理器、存储器和总线,所述存储器存储有所述处理器可执行的机器可读指令,当所述智能驾驶设备行驶时,所述处理器与所述存储器之间通过所述总线通信,所述机器可读指令被所述处理器执行时执行如权利要求1-14任一所述的导航方法的步骤。
  17. 一种计算机可读存储介质,该计算机可读存储介质上存储有计算机程序,该计算机程序被处理器运行时执行如权利要求1-14任一所述的导航方法的步骤。
PCT/CN2021/102864 2020-10-30 2021-06-28 导航方法、装置、智能驾驶设备及存储介质 WO2022088722A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011185601.6A CN112325896B (zh) 2020-10-30 2020-10-30 导航方法、装置、智能行驶设备及存储介质
CN202011185601.6 2020-10-30

Publications (1)

Publication Number Publication Date
WO2022088722A1 true WO2022088722A1 (zh) 2022-05-05

Family

ID=74297522

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/102864 WO2022088722A1 (zh) 2020-10-30 2021-06-28 导航方法、装置、智能驾驶设备及存储介质

Country Status (2)

Country Link
CN (1) CN112325896B (zh)
WO (1) WO2022088722A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115755400A (zh) * 2022-11-21 2023-03-07 江苏泽景汽车电子股份有限公司 一种信息显示方法及装置、存储介质、电子设备
WO2023232119A1 (zh) * 2022-06-01 2023-12-07 驭势(上海)汽车科技有限公司 一种车辆控制方法、装置、设备、介质及车辆

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112325896B (zh) * 2020-10-30 2023-03-14 上海商汤临港智能科技有限公司 导航方法、装置、智能行驶设备及存储介质
CN113008260B (zh) * 2021-03-26 2024-03-22 上海商汤临港智能科技有限公司 一种导航信息处理方法、装置、电子设备及存储介质
CN113008261B (zh) * 2021-03-30 2023-02-28 上海商汤临港智能科技有限公司 一种导航方法、装置、电子设备及存储介质
CN112985444B (zh) * 2021-03-31 2023-03-24 上海商汤临港智能科技有限公司 一种地图中导航元素构建方法及装置
CN116394938A (zh) * 2023-03-29 2023-07-07 高德软件有限公司 一种虚拟车道的确定方法、装置、介质及计算设备

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1497242A (zh) * 2002-10-07 2004-05-19 ��ʽ�����װ 对自动行驶道路优先的汽车导航系统
US20070106460A1 (en) * 2005-10-31 2007-05-10 Aisin Aw Co., Ltd. Route guidance system, methods and programs
JP2011069828A (ja) * 2006-12-04 2011-04-07 Mitsubishi Electric Corp ナビゲーション装置
CN108534790A (zh) * 2018-02-27 2018-09-14 吉林省行氏动漫科技有限公司 无人驾驶车辆导航方法、装置及无人驾驶车辆
CN109387210A (zh) * 2017-08-02 2019-02-26 腾讯科技(深圳)有限公司 车辆导航方法及其装置
CN209355944U (zh) * 2018-10-24 2019-09-06 北京汽车集团有限公司 导航装置、车载导航主机及车辆
CN111289006A (zh) * 2020-03-20 2020-06-16 上海商汤临港智能科技有限公司 车道导航路径生成方法及装置、驾驶控制方法及装置
CN111337045A (zh) * 2020-03-27 2020-06-26 北京百度网讯科技有限公司 车辆导航方法和装置
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
CN111623795A (zh) * 2020-05-28 2020-09-04 北京百度网讯科技有限公司 实景导航图标显示方法、装置、设备和介质
CN112325896A (zh) * 2020-10-30 2021-02-05 上海商汤临港智能科技有限公司 导航方法、装置、智能行驶设备及存储介质

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103292816B (zh) * 2012-02-23 2016-08-03 北京四维图新科技股份有限公司 电子地图生成方法、装置及路径规划方法、装置
CN108663059A (zh) * 2017-03-29 2018-10-16 高德信息技术有限公司 一种导航路径规划方法和装置
CN108151751B (zh) * 2017-11-21 2020-04-21 武汉中海庭数据技术有限公司 一种基于高精度地图和传统地图结合的路径规划方法及装置
CN111238504B (zh) * 2018-11-29 2023-04-07 沈阳美行科技股份有限公司 道路地图的道路线段建模数据生成方法、装置及相关系统
CN110174114B (zh) * 2019-06-05 2021-03-30 北京四维图新科技股份有限公司 车道线级路径生成方法、装置和存储介质
CN111664864A (zh) * 2020-05-31 2020-09-15 武汉中海庭数据技术有限公司 一种基于自动驾驶的动态规划方法及装置

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1497242A (zh) * 2002-10-07 2004-05-19 ��ʽ�����װ 对自动行驶道路优先的汽车导航系统
US20070106460A1 (en) * 2005-10-31 2007-05-10 Aisin Aw Co., Ltd. Route guidance system, methods and programs
JP2011069828A (ja) * 2006-12-04 2011-04-07 Mitsubishi Electric Corp ナビゲーション装置
CN109387210A (zh) * 2017-08-02 2019-02-26 腾讯科技(深圳)有限公司 车辆导航方法及其装置
CN108534790A (zh) * 2018-02-27 2018-09-14 吉林省行氏动漫科技有限公司 无人驾驶车辆导航方法、装置及无人驾驶车辆
CN209355944U (zh) * 2018-10-24 2019-09-06 北京汽车集团有限公司 导航装置、车载导航主机及车辆
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
CN111289006A (zh) * 2020-03-20 2020-06-16 上海商汤临港智能科技有限公司 车道导航路径生成方法及装置、驾驶控制方法及装置
CN111337045A (zh) * 2020-03-27 2020-06-26 北京百度网讯科技有限公司 车辆导航方法和装置
CN111623795A (zh) * 2020-05-28 2020-09-04 北京百度网讯科技有限公司 实景导航图标显示方法、装置、设备和介质
CN112325896A (zh) * 2020-10-30 2021-02-05 上海商汤临港智能科技有限公司 导航方法、装置、智能行驶设备及存储介质

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023232119A1 (zh) * 2022-06-01 2023-12-07 驭势(上海)汽车科技有限公司 一种车辆控制方法、装置、设备、介质及车辆
CN115755400A (zh) * 2022-11-21 2023-03-07 江苏泽景汽车电子股份有限公司 一种信息显示方法及装置、存储介质、电子设备
CN115755400B (zh) * 2022-11-21 2023-10-27 江苏泽景汽车电子股份有限公司 一种信息显示方法及装置、存储介质、电子设备

Also Published As

Publication number Publication date
CN112325896A (zh) 2021-02-05
CN112325896B (zh) 2023-03-14

Similar Documents

Publication Publication Date Title
WO2022088722A1 (zh) 导航方法、装置、智能驾驶设备及存储介质
EP3901782B1 (en) Lane-centric road network model for navigation
EP3290952B1 (en) Automatic localization geometry detection
US10809073B2 (en) Local window-based 2D occupancy grids for localization of autonomous vehicles
CN110832417B (zh) 使用高清地图为自主车辆生成路线
US10628671B2 (en) Road modeling from overhead imagery
US11093759B2 (en) Automatic identification of roadside objects for localization
US10118614B2 (en) Detailed map format for autonomous driving
KR102603648B1 (ko) 자율 주행을 위한 약도
EP3693701A2 (en) Intersection area road network data generation method and apparatus
EP3836116A1 (en) System and method to generate traffic congestion estimation data for calculation of traffic condition in a region
JP2022535351A (ja) 車両ナビゲーションのためのシステム及び方法
GB2622490A (en) Systems and methods for vehicle navigation
CN111837014A (zh) 用于匿名化导航信息的系统和方法
CN112880693A (zh) 地图生成方法、定位方法、装置、设备及存储介质
CN109426256A (zh) 自动驾驶车辆的基于驾驶员意图的车道辅助系统
KR102427961B1 (ko) 정밀지도 데이터 기반 가상환경 생성 방법 및 시스템
CN108332761B (zh) 一种使用及创建路网地图信息的方法与设备
JP2023539868A (ja) マップベースの現実世界モデル化のシステム及び方法
WO2023179030A1 (zh) 一种道路边界检测方法、装置、电子设备、存储介质和计算机程序产品
CN114771510A (zh) 基于路线图的泊车方法、泊车系统及电子设备
WO2021242416A1 (en) Systems and methods of translating routing constraints to a map
WO2023274309A1 (zh) 一种地图生成、使用方法及装置
WO2023040684A1 (zh) 一种交通信息获取方法、装置及存储介质
CN117711202A (zh) 路口通行方法、装置、设备及存储介质

Legal Events

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

Ref document number: 21884463

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

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

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205N DATED 21/06/2023)

122 Ep: pct application non-entry in european phase

Ref document number: 21884463

Country of ref document: EP

Kind code of ref document: A1