WO2023201954A1 - 一种环岛路径规划方法及装置 - Google Patents

一种环岛路径规划方法及装置 Download PDF

Info

Publication number
WO2023201954A1
WO2023201954A1 PCT/CN2022/115691 CN2022115691W WO2023201954A1 WO 2023201954 A1 WO2023201954 A1 WO 2023201954A1 CN 2022115691 W CN2022115691 W CN 2022115691W WO 2023201954 A1 WO2023201954 A1 WO 2023201954A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
road
roundabout
information
lane
Prior art date
Application number
PCT/CN2022/115691
Other languages
English (en)
French (fr)
Inventor
隋记魁
孟丽芬
陈远龙
李勇
李超群
罗凤梅
Original Assignee
合众新能源汽车股份有限公司
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 合众新能源汽车股份有限公司 filed Critical 合众新能源汽车股份有限公司
Publication of WO2023201954A1 publication Critical patent/WO2023201954A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3407—Route searching; Route guidance specially adapted for specific applications
    • G01C21/3415—Dynamic re-routing, e.g. recalculating the route when the user deviates from calculated route or after detecting real-time traffic data or accidents
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
    • G01S13/867—Combination of radar systems with cameras
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/87—Combinations of radar systems, e.g. primary radar and secondary radar
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
    • G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/86—Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
    • G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles

Definitions

  • the present invention relates to the technical field of path planning, and in particular to a method and device for planning a path around an island.
  • a roundabout also known as a roundabout, is a special form of traffic node. It is a plane road intersection.
  • the roundabout section is also commonly known as a roundabout, a roundabout, etc. It is composed of a circular lane and a central island. This setting makes it possible to move in any direction. After the incoming traffic enters the roundabout, it must rotate in a single direction around the center circle of the roundabout until it turns to the required driving direction and leaves.
  • roundabouts are an important part of the complex urban environment for unmanned vehicles.
  • urban roundabouts often have many intersections, many path choices, and more traffic. Therefore, if autonomous vehicles want to pass smoothly, safely, and quickly in roundabouts, they need to adjust their driving paths. Make plans.
  • path planning for roundabout roads often uses the reference line path at the roundabout provided by high-precision maps, and uses planning algorithms to optimize the reference line path.
  • high-precision maps cannot guarantee the accuracy of the reference line path at roundabouts.
  • roundabout roads with many dynamic obstacles there is the disadvantage of being unable to plan a suitable path, which has a negative impact on the traffic of unmanned vehicles.
  • the present invention provides a round-island path planning method and device.
  • the main purpose is to solve the problem of vehicles being unable to plan a suitable path due to the poor accuracy of high-precision maps, thereby ensuring smooth, safe and fast passage of vehicles. .
  • the present invention proposes the following solutions:
  • the present invention provides a round-island path planning method, which method includes:
  • the lane-level optimal driving path is optimized based on the obstacle information in the designated road section and the driving information of the vehicle to obtain the real-time driving path of the vehicle in the roundabout.
  • the present invention provides a round-island path planning device, which includes:
  • the collection unit is used to collect road information and obstacle information around the vehicle in real time when the vehicle enters the roundabout area;
  • a planning unit configured to use the road information obtained in the collection unit and the corresponding high-precision map information to plan a lane-level optimal driving path for the vehicle within the designated road section;
  • An optimization unit configured to optimize the lane-level optimal driving path obtained in the planning unit based on the obstacle information in the designated road section and the driving information of the vehicle to obtain the real-time driving path of the vehicle in the roundabout.
  • a storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to perform the above-mentioned first aspect. Roundabout path planning method.
  • a processor is provided, the processor is used to run a program, wherein when the program is running, the island roundabout path planning method of the first aspect is executed.
  • the present invention provides a roundabout path planning method and device.
  • the road information and obstacle information around the vehicle are collected in real time.
  • the road information and corresponding high-precision map information to plan the lane-level optimal driving path for the vehicle in the designated road section, and finally optimize the lane-level optimal driving path based on the obstacle information and vehicle driving information in the designated road section. Get the real-time driving path of the vehicle in the roundabout.
  • the road information collected in real time by the vehicle can be integrated with the corresponding high-precision map, thereby improving the accuracy of the high-precision map so that the vehicle can plan optimal driving at the lane level within the designated road section. path, and then further optimize the lane-level optimal driving path through the obstacle information in the designated road section collected by the vehicle in real time, so that when there are many dynamic obstacles in the roundabout road, the vehicle can automatically plan the most appropriate driving path in real time, thus Ensure the smooth, safe and fast passage of vehicles in the roundabout.
  • Figure 1 shows a flow chart of a round-island path planning method provided by an embodiment of the present invention
  • Figure 2 shows a flow chart of another roundabout path planning method provided by an embodiment of the present invention
  • Figure 3 shows a block diagram of a roundabout path planning device provided by an embodiment of the present invention
  • Figure 4 shows a block diagram of another roundabout path planning device provided by an embodiment of the present invention.
  • Figure 5 shows a schematic diagram of a roundabout road network model after dividing road sections according to an embodiment of the present invention
  • Figure 6 shows a schematic diagram of the shortest paths for different exits in the roundabout road network model provided by the embodiment of the present invention.
  • Roundabout also known as circular traffic
  • a traffic node It is a plane road intersection with a circular intersection and is composed of a circular lane and a central island. This kind of road setting requires traffic from any direction to enter the roundabout and rotate in a single direction around the center circle of the roundabout until it turns to the required driving direction and leaves.
  • Roundabouts are one of the more difficult scenes for unmanned vehicles to overcome in complex urban scenes. Since urban roundabouts often have many intersections, many path choices, and more traffic flow, if unmanned vehicles want to drive smoothly, safely, and quickly in roundabouts, To pass, the driving path needs to be planned.
  • Embodiments of the present invention provide a round-island path planning method, which can solve the problem of vehicles being unable to plan a suitable path due to poor accuracy of high-precision maps, thereby ensuring smooth, safe, and fast passage of vehicles.
  • the execution steps are shown in Figure 1, including:
  • the road information and obstacle information around the vehicle can be collected in real time by sensors such as laser radar, cameras, and millimeter wave radars.
  • the road information mainly refers to the static factors that affect the normal passage of vehicles in each lane of the roundabout, such as Factors such as lane width, lateral clearance, road surface properties and conditions, the actual sight distance length that can be guaranteed, the size and length of longitudinal slopes, etc.
  • the obstacle information mainly refers to the dynamic factors that affect the normal passage of vehicles in each lane of the roundabout, such as Road congestion caused by vehicles or people, construction conditions, traffic accidents, traffic control conditions, weather conditions and other factors. Therefore, through real-time collection of road information and obstacle information around the vehicle, the vehicle can pass on the roundabout along the correct road.
  • HD Map High Definition Map
  • high-precision maps can also provide lane-level navigation information in addition to road (link) level navigation information.
  • link road level navigation information.
  • Its main users are automobile autonomous driving systems. Specifically, you can first construct a local map of the roundabout based on the road information collected in real time by vehicles, then build a road network model around the island based on the local map of the roundabout and the corresponding high-precision map, and build a partial map of the roundabout based on the road information composed of multi-sensor fusion data.
  • the lane-level optimal driving path is planned within the designated road section.
  • the lane-level optimal driving path represents the path for vehicles to travel based on the optimal lane in different road sections under the premise that there are no people and no cars in the roundabout. Based on the above method, the lane-level optimal driving path can be planned for the vehicle in the designated road section for subsequent execution of step 103.
  • the vehicle's driving information refers to the vehicle's driving speed, start-stop frequency, start-stop time and other driving data.
  • the lane-level optimal driving path represents the premise that there are no people and no cars in the roundabout.
  • the vehicle travels on the optimal lane in different road sections. Therefore, when the vehicle travels on the lane-level optimal travel path, it is also necessary to consider the impact of obstacles in the designated road section on its normal passage. Therefore, the judgment steps can be 101 Whether the obstacle information collected in real time meets the traffic rules of the vehicle, operations such as changing the lane of the vehicle on the designated road section can optimize the lane-level optimal driving path, thereby ensuring smooth, safe and fast passage of vehicles in the roundabout.
  • the roundabout path planning method proposed by the embodiment of the present invention is to plan the driving path of the vehicle in the roundabout.
  • the vehicle enters the roundabout area it collects the surrounding information of the vehicle in real time.
  • Road information and obstacle information then use the road information and corresponding high-precision map information to plan the lane-level optimal driving path for the vehicle in the designated road section, and finally calculate the lane-level optimal driving path based on the obstacle information and vehicle driving information in the designated road section. Optimize the optimal driving path to obtain the real-time driving path of the vehicle in the roundabout.
  • the road information collected in real time by the vehicle can be integrated with the corresponding high-precision map, thereby improving the accuracy of the high-precision map so that the vehicle can plan optimal driving at the lane level within the designated road section. path, and then further optimize the lane-level optimal driving path through the obstacle information in the designated road section collected by the vehicle in real time, so that when there are many dynamic obstacles in the roundabout road, the vehicle can automatically plan the most appropriate driving path in real time, thus Ensure the smooth, safe and fast passage of vehicles in the roundabout.
  • step 101 The content of this step is the same as step 101 in the above embodiment.
  • step 101 For details, please refer to the content in the above step, and will not be described again here.
  • the local map of the roundabout is constructed based on the road information collected by the vehicle in real time, and the corresponding algorithm for constructing the local map of the roundabout includes but is not limited to the laser Slam algorithm and other map construction algorithms.
  • the subsequent step 203 can be facilitated. When integrating medium and high-precision maps, it can quickly and accurately find the current location of the vehicle and restore the environment around the vehicle.
  • the high-precision map can be pre-stored in the vehicle's autonomous driving system.
  • the vehicle When the vehicle enters the roundabout area, it can automatically obtain the high-precision map corresponding to the current roundabout area, thereby obtaining exit information and lane information on the roundabout road. etc., by integrating with the local map of the roundabout, the current location of the vehicle and the environmental information surrounding the vehicle can be quickly and accurately determined, so that the information on the high-precision map can be supplemented and corrected in the constructed roundabout road network model, so that the constructed The roundabout road network model is more accurate and comprehensive, ensuring the accuracy of subsequent vehicle planning paths in the roundabout.
  • the preset rules refer to the representation equations that divide each lane into road segments in the roundabout road network model. Specifically, the exit position, number of exits, and number of lanes in the roundabout road network model are substituted into the representation equation that divides each lane into road segments in the roundabout road network model to determine the ability of vehicles in the roundabout road network model for different exit locations. Corresponding to different sections of driving.
  • O i represents the roundabout exit
  • N o represents the number of roundabout exits
  • O 0 represents the lane where the vehicle is located
  • O t represents the target exit lane
  • R j represents the road segment in the road network
  • N r represents The number of lanes in the roundabout
  • M(i,j) represents the R j segment on the road segment O i O i+1 .
  • the current position of the vehicle can be obtained in real time
  • the target exit can also be obtained when the vehicle enters the roundabout area
  • the vehicle's location on the roundabout can be determined through the current position of the vehicle and the target exit.
  • the driving section in the network model needs to be passed
  • the target driving section refers to the driving section that the vehicle needs to pass in the roundabout road network model.
  • the target driving road section refers to the driving road section that the vehicle needs to pass through in the roundabout road network model. Therefore, the target driving road section can be determined as the designated road section for the vehicle to travel, so as to execute Next step 207.
  • the driving road section that needs to be passed through in the roundabout road network model can be quickly determined, thereby determining the designated road section for the vehicle to travel, so that the vehicle's driving path can be determined according to Different road sections are planned in the roundabout road network model, making the planning of driving paths more precise and accurate.
  • the preset algorithm is an algorithm set to ensure the shortest driving path length of the vehicle.
  • the MinRoad algorithm can be used for calculation. Assuming that the road segment length is represented by LM(i,j), the specific algorithm for calculating the shortest path from the vehicle position to the target exit is as follows:
  • a road network table corresponding to the shortest path based on different target exits can also be created, based on Figure 6 As shown in the figure, the number of exits is 4 and the number of lanes is 2.
  • the specific road network table is as follows:
  • the vehicle's driving path can be planned based on different lanes in the designated road section, so that the vehicle can Drive the shortest path from the current location to the target exit, allowing vehicles to quickly pass through the roundabout, ensuring the efficiency of vehicle traffic in the roundabout.
  • the traffic rules are rules set to ensure the traffic efficiency of vehicles in the roundabout, and factors that affect traffic efficiency include but are not limited to road congestion caused by vehicles or people, construction conditions, traffic accidents, traffic Control conditions, weather conditions, etc. Since the above factors will affect the driving status of the vehicle, the obstacle information of the current lane can be judged by obtaining the driving information of the vehicle in real time. If satisfied, continue along the designated road section. Driving in the current lane, if not satisfied, step 210 is executed.
  • the vehicle driving information obtained in real time can be used as a determining factor of whether the vehicle complies with the traffic rules when driving on the current lane in the designated road section, thereby further ensuring the traffic efficiency of the vehicle in the designated road section.
  • the lane is used as the lane to be changed. Specifically, the road information of other lanes in the specified road section and the traffic speed and quantity of each obstacle in the obstacle information can be obtained respectively, and the above information is jointly determined based on the road information and the traffic speed and quantity of each obstacle.
  • road information is used to determine whether the road conditions of other lanes can ensure the normal passage of vehicles, and the traffic speed and number of each obstacle can be used to determine whether an obstacle moves faster in other lanes that can ensure the normal passage of vehicles. , a smaller number of optimal lanes, thereby determining the optimal lane as the vehicle's lane to be changed.
  • the space can be divided according to the obstacle information, and its Add hard constraints to the path change to ensure that it is changed in a smoother curve (smaller curvature). Constraints can be made by adding a cost function that can make the path curve smooth and continuous. The specific method is as follows:
  • the path curve when the vehicle enters or exits the roundabout, switches lanes between adjacent road sections, and changes lanes in real time can be smooth and continuous, thereby obtaining the real-time driving path of the vehicle in the roundabout, that is, the current vehicle Lane-level optimal driving path within a specified road segment.
  • the optimal driving lane in the other lanes can be quickly determined through the road information and obstacle information of other lanes in the designated road section, and the The optimal driving lane is used as the lane to be changed for vehicles to change, thereby ensuring the traffic efficiency of vehicles within the designated road section, allowing the vehicle to pass smoothly and quickly within the designated road section, and in the process of determining its change path, it can be based on the settings
  • the constraint function can make the path curve smooth and continuous when the vehicle enters or exits the roundabout, switches lanes between adjacent road sections, and changes lanes in real time, thereby obtaining the real-time driving path of the vehicle in the roundabout, that is, the vehicle is in the specified Lane-level optimal driving path within the road segment.
  • the roundabout path planning method proposed by the embodiment of the present invention is to plan the driving path of the vehicle in the roundabout. First, when the vehicle enters the roundabout area, the surrounding information of the vehicle is collected in real time.
  • the roundabout road in the roundabout road network model is divided into multiple sections according to the preset rules, and the roundabout road can be In the network model, each lane is divided into road sections, and then the different road sections that the vehicle can drive corresponding to different exit positions in the roundabout road network model are obtained, and then the vehicle's location in the roundabout road network model is determined based on the current position of the vehicle and the target exit.
  • Target driving road section and determine the target driving road section as the designated road section for the vehicle to drive. Through the current position of the vehicle and the target exit, the driving section that needs to be passed through in the roundabout road network model can be quickly determined, thereby determining the road section for the vehicle to drive.
  • Designated road sections enable the vehicle's driving path to be planned according to different road sections in the roundabout road network model, thereby making the driving path planning more precise and accurate, and then use preset algorithms to plan the vehicle's driving path within the designated road section.
  • the vehicle's driving path can be planned based on different lanes in the specified road segment, so that the vehicle can travel from the current position to the target exit in the shortest path, allowing the vehicle to quickly pass through the roundabout.
  • ensuring the traffic efficiency of vehicles in the roundabout while obtaining the vehicle's driving information in real time, and based on the driving information, it is judged whether the obstacle information of the current lane in the designated road section meets the vehicle's preset traffic rules, and the vehicle driving information obtained in real time can be As the determining factor of whether the vehicle complies with the traffic rules when driving on the current lane in the designated road section, it further ensures the traffic efficiency of the vehicle in the designated road section. Finally, it is determined based on the road information and obstacle information of other lanes in the designated road section that the vehicle is in the designated road section.
  • the lane to be changed within the lane is updated according to the lane to be changed.
  • the lane-level optimal driving path is updated according to the lane to be changed.
  • the optimal driving lane in the lane is used as the lane to be changed for vehicles to change, thereby ensuring the traffic efficiency of vehicles in the designated road section, allowing vehicles to pass smoothly and quickly in the designated road section, and in The process of determining the path change can be based on the set constraint function, so that the path curve can be smooth and continuous when the vehicle enters or exits the roundabout, switches lanes between adjacent road sections, and changes lanes in real time, thereby obtaining the path curve of the vehicle in the roundabout.
  • the real-time driving path is the lane-level optimal driving path of the vehicle within the specified road segment.
  • the embodiment of the present invention provides a round-island path planning device, which is used to solve the problem that the vehicle cannot plan a suitable path due to the poor accuracy of high-precision maps. path problems to ensure the smooth, safe and fast passage of vehicles.
  • the embodiment of the device corresponds to the foregoing method embodiment. For the convenience of reading, this embodiment will not elaborate on the details of the foregoing method embodiment one by one. However, it should be clear that the device in this embodiment can correspondingly implement the foregoing method implementation. All content in the example. As shown in Figure 3, the device includes:
  • the collection unit 31 is used to collect road information and obstacle information around the vehicle in real time when the vehicle enters the roundabout area;
  • the planning unit 32 is configured to use the road information obtained in the collection unit 31 and the corresponding high-precision map information to plan a lane-level optimal driving path for the vehicle in the designated road section;
  • the optimization unit 33 is configured to optimize the lane-level optimal driving path obtained in the planning unit 32 according to the obstacle information in the designated road section and the driving information of the vehicle, so as to obtain the real-time information of the vehicle in the roundabout. Driving path.
  • the planning unit 32 includes:
  • the establishment module 322 is configured to establish a road network model around the island based on the partial map of the island obtained by the construction module 321 and the corresponding high-precision map;
  • the dividing module 333 is used to divide the roundabout road in the roundabout road network model obtained by the establishment module 322 into multiple road segments according to the preset rules;
  • the planning module 334 is used to plan the lane-level optimal driving path within the designated road section obtained by the dividing module 333 .
  • the division module 333 is also used to substitute the exit position, number of exits, and number of lanes in the roundabout road network model into road segments for each lane in the roundabout road network model. in the characterization equation to determine the different road sections that the vehicle can travel corresponding to different exit positions in the roundabout road network model.
  • the planning module 334 includes:
  • the first determination sub-module 3341 is used to determine the target driving section of the vehicle in the roundabout road network model based on the current location of the vehicle and the target exit;
  • the second determination sub-module 3342 is used to determine the target driving road section obtained by the first determination sub-module 3341 as the designated road section to be traveled by the vehicle;
  • Planning sub-module 3343 is used to use a preset algorithm to plan the driving path of the vehicle within the designated road segment obtained by the second determination sub-module 3342 to obtain the lane-level optimal driving path.
  • the preset The algorithm is an algorithm set up to ensure that the driving path length of the vehicle is the shortest.
  • the optimization unit 33 includes:
  • the acquisition module 331 is used to acquire the driving information of the vehicle in real time
  • the judgment module 332 is configured to judge whether the obstacle information of the current lane in the designated road section satisfies the preset traffic rules of the vehicle based on the driving information obtained by the acquisition module 331;
  • the determination module 333 is configured to determine where the vehicle is located based on the road information and obstacle information of other lanes in the designated road section if the obstacle information of the current lane in the designated road section does not meet the preset traffic rules of the vehicle. The lane to be changed within the specified road section;
  • the update module 334 is configured to update the lane-level optimal driving path according to the lane to be changed obtained by the determination module 333 .
  • the determination module 333 includes:
  • the acquisition sub-module 3331 is used to obtain the road information of other lanes in the designated road section and the traffic speed and quantity of each obstacle in the obstacle information;
  • the third determination sub-module 3332 is used to jointly determine the lane to be changed based on the road information obtained by the acquisition sub-module 3331 and the traffic speed and number of each obstacle.
  • an embodiment of the present invention also provides a storage medium, the storage medium is used to store a computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the island roundabout described in Figures 1-2. Path planning methods.
  • an embodiment of the present invention further provides a processor, the processor being configured to run a program, wherein when the program is running, the island-circuit path planning method described in Figure 1-2 is executed.
  • memory may include non-volatile memory in computer-readable media, random access memory (RAM) and/or non-volatile memory in the form of read-only memory (ROM) or flash memory (flash RAM).
  • RAM random access memory
  • ROM read-only memory
  • flash RAM flash RAM
  • Memory includes At least one memory chip.
  • embodiments of the present application may be provided as methods, systems or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
  • computer-usable storage media including, but not limited to, disk storage, CD-ROM, optical storage, etc.
  • These computer program instructions may also be stored in a computer-readable memory that causes a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction means, the instructions
  • the device implements the functions specified in a process or processes of the flowchart and/or a block or blocks of the block diagram.
  • These computer program instructions may also be loaded onto a computer or other programmable data processing device, causing a series of operating steps to be performed on the computer or other programmable device to produce computer-implemented processing, thereby executing on the computer or other programmable device.
  • Instructions provide steps for implementing the functions specified in a process or processes of a flowchart diagram and/or a block or blocks of a block diagram.
  • a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • Memory may include non-volatile memory in computer-readable media, random access memory (RAM) and/or non-volatile memory in the form of read-only memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
  • RAM random access memory
  • ROM read-only memory
  • flash RAM flash memory
  • Computer-readable media includes both persistent and non-volatile, removable and non-removable media that can be implemented by any method or technology for storage of information.
  • Information may be computer-readable instructions, data structures, modules of programs, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), and read-only memory.
  • PRAM phase change memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • RAM random access memory
  • read-only memory read-only memory
  • ROM read-only memory
  • EEPROM electrically erasable programmable read-only memory
  • flash memory or other memory technology
  • compact disc read-only memory CD-ROM
  • DVD digital versatile disc
  • Magnetic tape cassettes tape magnetic disk storage or other magnetic storage devices or any other non-transmission medium can be used to store information that can be accessed by a computing device.
  • computer-readable media does not include transitory media, such as modulated data signals and carrier waves.
  • embodiments of the present application may be provided as methods, systems or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
  • computer-usable storage media including, but not limited to, disk storage, CD-ROM, optical storage, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Electromagnetism (AREA)
  • Automation & Control Theory (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种环岛路径规划方法及装置，涉及路径规划技术领域，主要目的在于解决因高精地图的精确性差而导致车辆无法规划出合适路径的问题，从而保证车辆的顺利、安全、快速的通行。方法包括：在车辆进入环岛区域时，实时采集车辆周边的道路信息与障碍物信息（101）；利用道路信息与对应的高精地图信息为车辆在指定路段内规划车道级最优行驶路径（102）；根据指定路段内的障碍物信息以及车辆的行驶信息对车道级最优行驶路径进行优化，得到车辆在环岛中的实时行驶路径（103）。

Description

一种环岛路径规划方法及装置 技术领域
本发明涉及路径规划技术领域，尤其涉及一种环岛路径规划方法及装置。
背景技术
环岛也称环形交通，是交通节点的一种特殊形式，属于平面道路交叉，而环形交叉的地段也俗称环岛、转盘等，其是由环形车道和一个中心岛组成，这种设置使得任何一个方向而来的交通流量进入环岛后，均需以环岛的中心圈以单一方向旋转行驶，直至转向所需的行驶方向而离开，而伴随着无人车技术的发展，环岛是无人车在城市复杂场景中较难克服的场景之一，由于城市环岛往往路口多，路径选择多，车流也较多，因此，无人车若想在环岛中顺利、安全、快速的通行，则需要对其行驶路径进行规划。
目前针对于环岛道路的路径规划往往应用高精地图提供的环岛处的参考线路径，并加持规划算法对参考线路径进行优化。然而，高精地图并不能保证环岛处的参考线路径的精确性，对于动态障碍物较多的环岛道路，存在无法规划出合适路径的弊端，从而对无人车的通行造成不良影响。
发明内容
鉴于上述问题，本发明提供一种环岛路径规划方法及装置，主要目的是为了解决因高精地图的精确性差而导致车辆无法规划出合适路径的问题，从而保证车辆的顺利、安全、快速的通行。
为解决上述技术问题，本发明提出以下方案：
第一方面，本发明提供了一种环岛路径规划方法，所述方法包括：
在车辆进入环岛区域时，实时采集车辆周边的道路信息与障碍物信息；
利用所述道路信息与对应的高精地图信息为所述车辆在指定路段内规划车道级最优行驶路径；
根据所述指定路段内的障碍物信息以及所述车辆的行驶信息对所述车道级最优行驶路径进行优化，得到所述车辆在环岛中的实时行驶路径。
第二方面，本发明提供了一种环岛路径规划装置，所述装置包括：
采集单元，用于在车辆进入环岛区域时，实时采集车辆周边的道路信息与障碍物信息；
规划单元，用于利用所述采集单元中获得的道路信息与对应的高精地图信息为所述车辆在指定路段内规划车道级最优行驶路径；
优化单元，用于根据所述指定路段内的障碍物信息以及所述车辆的行驶信息对所述规划单元中获得的车道级最优行驶路径进行优化，得到所述车辆在环岛中的实时行驶路径。
为了实现上述目的，根据本发明的第三方面，提供了一种存储介质，所述存储介质包括存储的程序，其中，在所述程序运行时控制所述存储介质所在设备执行上述第一方面的环岛路径规划方法。
为了实现上述目的，根据本发明的第四方面，提供了一种处理器，所述处理器用于运行程序，其中，所述程序运行时执行上述第一方面的环岛路径规划方法。
借由上述技术方案，本发明提供的一种环岛路径规划方法及装置，是对车辆在环岛内的行驶路径进行规划时，首先在车辆进入环岛区域时实时采集车辆周边的道路信息与障碍物信息，接着利用道路信息与对应的高精地图信息为车辆在指定路段内规划车道级最优行驶路径，最后根据指定路段内的障碍物信息以及车辆的行驶信息对车道级最优行驶路径进行优化，得到车辆在环岛中的实时行驶路径。通过本发明实施例提供的环岛路径规划方案，可通过车辆实时采集的道路信息与对应的高精地图进行融合，从而提升高精地图的精确性，以便车辆在指定路段内规划车道级最优行驶路径，再通过车辆实时采集的指定路段内的障碍物信息对车道级最优行驶路径进一步优化，使得在环岛道路内的动态障碍物较多时，车辆能够自动实时规划出最合适的行驶路径，从而保证车辆在环岛中顺利、安全、快速的通行。
上述说明仅是本发明技术方案的概述，为了能够更清楚了解本发明的技术手段，而可依照说明书的内容予以实施，并且为了让本发明的上述和其他目的、特征和优点能够更明显易懂，以下特举本发明的具体实施方式。
附图说明
通过阅读下文优选实施方式的详细描述，各种其他的优点和益处对于本领域普通技术人员将变得清楚明了。附图仅用于示出优选实施方式的目的，而并不认为是对本发明的限制。而且在整个附图中，用相同的参考符号表示相同的部件。在附图中：
图1示出了本发明实施例提供的一种环岛路径规划方法流程图；
图2示出了本发明实施例提供的另一种环岛路径规划方法流程图；
图3示出了本发明实施例提供的一种环岛路径规划装置的组成框图；
图4示出了本发明实施例提供的另一种环岛路径规划装置的组成框图；
图5示出了本发明实施例提供的划分路段后的环岛路网模型示意图；
图6示出了本发明实施例提供的环岛路网模型中针对不同出口的最短路径示意图。
具体实施方式
下面将参照附图更详细地描述本公开的示例性实施例。虽然附图中显示了本公开的示例性实施例，然而应当理解，可以以各种形式实现本公开而不应被这里阐述的实施例所限制。相反，提供这些实施例是为了能够更透彻地理解本公开，并且能够将本公开的范围完整地传达给本领域的技术人员。
环岛也称环形交通，是交通节点中一种特殊的道路形式，属于平面道路交叉，有环形交叉，由环形车道和一个中心岛组成。这种道路设置使得任何一个方向而来的交通流量进入环岛后，均需以环岛的中心圈以单一方向旋转行驶，直至转向所需的行驶方向而离开，而伴随着无人车技术的发展，环岛是无人车在城市复杂场景中较难克服的场景之一，由于城市环岛往往路口多，路径选择多，车流也较多，因此，无人车若想在环岛中顺利、安全、快速的通行，则需要对其行驶路径进行规划，而现有技术则基于高精地图自带的路径引导线作为行驶路径规划的基础，并在其基础上进行优化，但这种方式存在弊端，一方面由于高精地图并不能保证环岛处的参考线路径的精确性，另一方面由于环岛道路中的动态障碍物较多，容易导致车辆无法规划出合适路径，从而影响无人车的通行。本发明实施例提供了一种环岛路径规划方法，通过该方法能够解决因高精地图的精确性差而导致车辆无法规划出合适路径的问题，从而保证车辆的顺利、安全、快速的通行，其具体执行步骤如图1所示，包括：
101、在车辆进入环岛区域时，实时采集车辆周边的道路信息与障碍物信息。
在本步骤中，车辆周边的道路信息与障碍物信息可以由激光雷达、摄像头、毫米波雷达等传感器进行实时采集，其中，道路信息主要是指环岛各个车道上影响车辆正常通行的静态因素，例如车道宽度、侧向净空、路面性质和状况、实际能保证的视距长度、纵坡的大小和坡长等因素，而障碍物信息主要是指环岛各个车道上影响车辆正常通行的动态因素，例如由车辆或人造成的道路拥堵情况、施工情况、交通事故、交通管制情况、天气情况等因素。因此，通过对车辆周边道路信息与障碍物信息的实时采集，即可使得车辆可沿着正确的道路在环岛上通行。
102、利用道路信息与对应的高精地图信息为车辆在指定路段内规划车道级最优行驶路径。
本步骤中，高精地图(HD Map，High Definition Map)是一种具备高定位精度、能实时更新数据的地图。与传统地图不同的是，高精度地图除了能提供的道路(link)级别的导航信息外，还能够提供车道(lane)级别的导航信息，其主要使用者为汽车自动驾驶系统。具体的，可以先通过车辆实时采集的道路信息构建环岛局部地图，再基于 环岛局部地图与对应的高精地图建立环岛路网模型，而通过多传感器融合数据组成的道路信息构建环岛的局部地图，可以补偿高精地图的精度误差，使得环岛路网模型的构建更为精准，接着依照预置规则将环岛路网模型中的环岛道路划分为多个路段，使得车辆可通过不同的路段进行行驶，最后在指定路段内规划车道级最优行驶路径，其中，车道级最优行驶路径则代表环岛内无人无车的前提下车辆在不同路段内基于最优车道行驶的路径。而基于上述方式，即可为车辆在指定路段内规划车道级最优行驶路径，以便后续执行步骤103。
103、根据指定路段内的障碍物信息以及车辆的行驶信息对车道级最优行驶路径进行优化，得到车辆在环岛中的实时行驶路径。
在本步骤中，车辆的行驶信息是指车辆的行驶速度、启停频率、启停时间等行驶数据，由上述步骤102可知，车道级最优行驶路径则代表环岛内无人无车的前提下车辆在不同路段内基于最优车道行驶的路径，因此，当车辆在车道级最优行驶路径上行驶时，还需要考虑指定路段内的障碍物对其正常通行的影响，因此，可通过判断步骤101实时采集的障碍物信息是否满足车辆的通行规则在指定路段对车辆行驶的车道进行变更等操作实现对车道级最优行驶路径的优化，从而保证车辆在环岛中顺利、安全、快速的通行。
基于上述图1的实现方式可以看出，本发明实施例所提出的一种环岛路径规划方法，是对车辆在环岛内的行驶路径进行规划时，首先在车辆进入环岛区域时实时采集车辆周边的道路信息与障碍物信息，接着利用道路信息与对应的高精地图信息为车辆在指定路段内规划车道级最优行驶路径，最后根据指定路段内的障碍物信息以及车辆的行驶信息对车道级最优行驶路径进行优化，得到车辆在环岛中的实时行驶路径。通过本发明实施例提供的环岛路径规划方案，可通过车辆实时采集的道路信息与对应的高精地图进行融合，从而提升高精地图的精确性，以便车辆在指定路段内规划车道级最优行驶路径，再通过车辆实时采集的指定路段内的障碍物信息对车道级最优行驶路径进一步优化，使得在环岛道路内的动态障碍物较多时，车辆能够自动实时规划出最合适的行驶路径，从而保证车辆在环岛中顺利、安全、快速的通行。
进一步的，本发明优选实施例是在上述图1的基础上，针对环岛路径规划的过程进行的详细说明，其具体步骤如图2所示，包括：
201、在车辆进入环岛区域时，实时采集车辆周边的道路信息与障碍物信息。
本步骤的内容同上述实施例中的步骤101，具体可参见上述步骤中的内容，此处不 再赘述。
202、根据道路信息构建环岛局部地图。
在本步骤中，环岛局部地图基于车辆实时采集的道路信息构建的，而对应构建环岛局部地图算法包括但不限于激光Slam算法等地图构建算法，通过对环岛局部地图的构建，可便于后续步骤203中与高精地图融合时快速、准确找到车辆当前所在位置以及还原车辆周边的环境情况。
203、基于环岛局部地图与对应的高精地图建立环岛路网模型。
在本步骤中，高精地图可预先存储在车辆的自动驾驶系统内，当车辆驶入环岛区域时，可自动获取当前环岛区域对应的高精地图，从而获得环岛道路上的出口信息、车道信息等，通过与环岛局部地图融合，可以快速、准确的确定车辆当前所在位置以及车辆周边的环境信息，从而在构建的环岛路网模型中对高精地图上的信息进行补充和修正，使得构建的环岛路网模型更为准确、全面，保证了后续车辆在环岛中规划路径的精确性。
204、依照预置规则将环岛路网模型中的环岛道路划分为多个路段。
在本步骤中，预置规则是指在环岛路网模型中对各个车道进行路段划分的表征方程。具体的，将环岛路网模型中的出口位置、出口数量、车道数量代入在环岛路网模型中对各个车道进行路段划分的表征方程中，以确定环岛路网模型中车辆针对不同出口位置所能够对应行驶的不同路段。
其中，所述表征方程具体如下：
Figure PCTCN2022115691-appb-000001
如图5所示，其中，O i表示为环岛出口，N o表示环岛出口的数量，O 0表示本车所在车道，O t表示目标出口车道；R j表示路网中的路段，N r表示环岛内车道的数量，M(i,j)表示路段O iO i+1上的R j路段。通过上述方式，可以对环岛路网模型中对各个车道进行路段划分，进而获得车辆在环岛路网模型中针对不同出口位置所能够对应行驶的不同路段，以便执行后续步骤205。
205、根据车辆的当前位置与目标出口确定车辆在环岛路网模型中的目标行驶路段。
在本步骤中，车辆的当前位置是可以通过实时获取到的，而目标出口也是车辆在车辆驶入环岛区域内时可以获知的，而通过车辆的当前位置与目标出口即可确定车辆在环岛路网模型中的需要经过的行驶路段，而目标行驶路段即是指车辆在环岛路网模型中的需要经过的行驶路段。
206、将目标行驶路段确定为车辆待行驶的指定路段。
在本步骤中，基于上述步骤205可知，目标行驶路段即是指车辆在环岛路网模型中的需要经过的行驶路段，因此，可将目标行驶路段，确定为车辆待行驶的指定路段，以便执行后续步骤207。
根据步骤206-207的方法，通过车辆的当前位置与目标出口，可以快速确定在环岛路网模型中的需要经过的行驶路段，从而确定为车辆待行驶的指定路段，使得车辆的行驶路径可根据环岛路网模型中不同的路段进行规划，从而使得行驶路径的规划更加精细、准确。
207、利用预置算法在指定路段内对车辆的行驶路径进行规划，以获得车道级最优行驶路径。
其中，预置算法是用于保证车辆的行驶路径长度最短而设置的算法。在本步骤中，可使用MinRoad算法进行计算，假设路段长度为LM(i,j)来表示，则计算从车辆位置到目标出口的最短路径的具体算法如下：
Figure PCTCN2022115691-appb-000002
针对上述算法所获得的最短路径，为了便于后续车辆在进入环岛区域内可以无需重复计算而直接获悉对应的最短路径，还可以创建基于不同目标出口而对应的最短路径的路网表，基于图6所示，其出口数量为4个，车道为2个，具体路网表如 下：
出口号/车辆位置 O 0
O 1 R1：M(0，2)
O 2 R2：M(0，1)-＞M(1，1)
O 3 R3：M(0，1)-＞M(1，1)-＞M(2，1)
O 4 R4：M(0，1)-＞M(1，1)-＞M(2，1)-＞M(3，2)
根据本步骤的方法，因在步骤206中已经确定了车辆待行驶的指定路段，因此，根据预置算法的设置，可以基于指定路段内的不同车道对车辆的行驶路径进行规划，从而使得车辆可从当前位置以长度最短的路径行驶至目标出口，使得车辆可快速在环岛中通过，保证了车辆在环岛中的通行效率。
208、实时获取车辆的行驶信息。
在本步骤中，由于车辆在车道级最优行驶路径上是动态行驶的，因此，就需要对车辆自身的行驶信息进行实时获取，以便执行后续步骤209。
209、基于行驶信息判断指定路段内当前车道的障碍物信息是否满足车辆预设的通行规则。
在本步骤中，通行规则是用于保证车辆在环岛内的通行效率而设置的规则，而影响通行效率的因素包括但不限于由车辆或人造成的道路拥堵情况、施工情况、交通事故、交通管制情况、天气情况等，由于上述因素均会对车辆的行驶状态造成影响，因此可通过实时获取车辆的行驶信息对当前车道的障碍物信息进行判断，若满足，则继续沿着指定路段内的当前车道进行行驶，若不满足，则执行步骤210。
根据步骤208-209的方法，可将实时获取的车辆行驶信息作为车辆在指定路段内当前车道上行驶时是否符合通行规则的决定因素，从而进一步保证车辆在指定路段内的通行效率。
210、基于指定路段内其他车道的道路信息以及障碍物信息确定车辆在指定路段内的待变更车道。
在本步骤中，由于在上述步骤209中已经确定指定路段内的当前车道不能满足其预设的通行规则，而为了保证车辆的顺利通行，就需要在指定路段内的其他车道中选择一个最佳车道作为待变更车道，具体的，可以分别获取指定路段内其他车道的道路信息以及障碍物信息中各个障碍物的通行速率和数量，根据道路信息以及各个障碍物的通行速率和数量共同确定所述待变更车道，其中，通过道路信息确定其他车道的路况是否能够保证车辆的正常通行，而各个障碍物的通行速率和数量可以在能够保证车辆正常通行的 其他车道中确定一条障碍物移动速率更快、数量更少的最佳车道，从而将确定最佳车道作为车辆的待变更车道。
211、根据待变更车道更新车道级最优行驶路径。
在本步骤中，因车辆需要从指定路段内的当前车道切换至待变更车道，以更新车道级最优行驶路径，而在其变更路径确定的过程中，可根据障碍物信息划分空间，为其变更路径添加硬约束，以保证其以曲线更平滑(曲率更小)的方式进行变更，可通过添加能够使路径曲线平滑、连续的cost函数的方式进行约束，具体方式如下：
Figure PCTCN2022115691-appb-000003
Figure PCTCN2022115691-appb-000004
Figure PCTCN2022115691-appb-000005
Figure PCTCN2022115691-appb-000006
Figure PCTCN2022115691-appb-000007
l″ i+1＝l″ i+l″′ i→i+1×Δs
通过上述cost函数进行约束，可使得车辆驶入或驶出环岛、相邻路段间车道切换以及车道实时变更时的路径曲线平滑、连续，从而得到车辆在环岛中的实时行驶路径，即本次车辆在指定路段内的车道级最优行驶路径。
根据步骤210-211的方法，可在指定路段内当前车道无法满足预设的通行规则时，通过指定路段内其他车道的道路信息和障碍物信息快速确定其他车道中最优的行驶车道，并将最优的行驶车道作为待变更车道供车辆进行变更，从而保证车辆在指定路段内的通行效率，使得车辆可在指定路段内顺利、快速的通行，并且在其变更路径确定的过程中可基于设置的约束函数，使可使得车辆驶入或驶出环岛、相邻路段间车道切换以及车道实时变更时的路径曲线平滑、连续，从而得到车辆在环岛中的实时行驶路径，即本次车辆在指定路段内的车道级最优行驶路径。
基于上述图2的实现方式可以看出，本发明实施例所提出的一种环岛路径规划方法，是对车辆在环岛内的行驶路径进行规划时，首先在车辆进入环岛区域时实时采集车辆周边的道路信息与障碍物信息，再根据道路信息构建环岛局部地图，可准确找到车辆当前 所在位置以及还原车辆周边的环境情况，接着基于环岛局部地图与对应的高精地图建立环岛路网模型，使得高精地图中的信息通过与环岛局部地图融合，可以快速、准确的确定车辆当前所在位置以及车辆周边的环境信息，从而在构建的环岛路网模型中对高精地图上的信息进行补充和修正，使得构建的环岛路网模型更为准确、全面，保证了后续车辆在环岛中规划路径的精确性，然后依照预置规则将环岛路网模型中的环岛道路划分为多个路段，可以对环岛路网模型中对各个车道进行路段划分，进而获得车辆在环岛路网模型中针对不同出口位置所能够对应行驶的不同路段，随之根据车辆的当前位置与目标出口确定车辆在环岛路网模型中的目标行驶路段，并将目标行驶路段确定为车辆待行驶的指定路段，能够通过车辆的当前位置与目标出口，可以快速确定在环岛路网模型中的需要经过的行驶路段，从而确定为车辆待行驶的指定路段，使得车辆的行驶路径可根据环岛路网模型中不同的路段进行规划，从而使得行驶路径的规划更加精细、准确，继而利用预置算法在指定路段内对车辆的行驶路径进行规划，以获得车道级最优行驶路径，能够基于指定路段内的不同车道对车辆的行驶路径进行规划，从而使得车辆可从当前位置以长度最短的路径行驶至目标出口，使得车辆可快速在环岛中通过，保证了车辆在环岛中的通行效率，同时实时获取车辆的行驶信息，并基于行驶信息判断指定路段内当前车道的障碍物信息是否满足车辆预设的通行规则，可将实时获取的车辆行驶信息作为车辆在指定路段内当前车道上行驶时是否符合通行规则的决定因素，从而进一步保证车辆在指定路段内的通行效率，最后基于指定路段内其他车道的道路信息以及障碍物信息确定车辆在指定路段内的待变更车道，根据待变更车道更新车道级最优行驶路径，可在指定路段内当前车道无法满足预设的通行规则时，通过指定路段内其他车道的道路信息和障碍物信息快速确定其他车道中最优的行驶车道，并将最优的行驶车道作为待变更车道供车辆进行变更，从而保证车辆在指定路段内的通行效率，使得车辆可在指定路段内顺利、快速的通行，并且在其变更路径确定的过程中可基于设置的约束函数，使可使得车辆驶入或驶出环岛、相邻路段间车道切换以及车道实时变更时的路径曲线平滑、连续，从而得到车辆在环岛中的实时行驶路径，即本次车辆在指定路段内的车道级最优行驶路径。
进一步的，作为对上述图1-2所示方法实施例的实现，本发明实施例提供了一种环岛路径规划装置，该装置用于解决因高精地图的精确性差而导致车辆无法规划出合适路径的问题，从而保证车辆的顺利、安全、快速的通行。该装置的实施例与前述方法实施例对应，为便于阅读，本实施例不再对前述方法实施例中的细节内容进行逐一赘述， 但应当明确，本实施例中的装置能够对应实现前述方法实施例中的全部内容。具体如图3所示，该装置包括：
采集单元31，用于在车辆进入环岛区域时，实时采集车辆周边的道路信息与障碍物信息；
规划单元32，用于利用所述采集单元31中获得的道路信息与对应的高精地图信息为所述车辆在指定路段内规划车道级最优行驶路径；
优化单元33，用于根据所述指定路段内的障碍物信息以及所述车辆的行驶信息对所述规划单元32中获得的车道级最优行驶路径进行优化，得到所述车辆在环岛中的实时行驶路径。
进一步的，如图4所示，所述规划单元32包括：
构建模块321，用于根据所述道路信息构建环岛局部地图；
建立模块322，用于基于所述构建模块321获得的环岛局部地图与所述对应的高精地图建立环岛路网模型；
划分模块333，用于依照预置规则将所述建立模块322获得的环岛路网模型中的环岛道路划分为多个路段；
规划模块334，用于在所述划分模块333获得的指定路段内规划车道级最优行驶路径。
进一步的，如图4所示，所述划分模块333，还用于将所述环岛路网模型中的出口位置、出口数量、车道数量代入在所述环岛路网模型中对各个车道进行路段划分的表征方程中，以确定所述环岛路网模型中所述车辆针对不同出口位置所能够对应行驶的不同路段。
进一步的，如图4所示，所述规划模块334，包括：
第一确定子模块3341，用于根据所述车辆的当前位置与目标出口确定所述车辆在所述环岛路网模型中的目标行驶路段；
第二确定子模块3342，用于将所述第一确定子模块3341获得的目标行驶路段确定为所述车辆待行驶的指定路段；
规划子模块3343，用于利用预置算法在所述第二确定子模块3342获得的指定路段内对所述车辆的行驶路径进行规划，以获得所述车道级最优行驶路径，所述预置算法是用于保证所述车辆的行驶路径长度最短而设置的算法。
进一步的，如图4所示，所述优化单元33，包括：
获取模块331，用于实时获取所述车辆的行驶信息；
判断模块332，用于基于所述获取模块331获得的行驶信息判断所述指定路段内当前车道的障碍物信息是否满足所述车辆预设的通行规则；
确定模块333，用于若所述指定路段内当前车道的障碍物信息不满足所述车辆预设的通行规则，则基于所述指定路段内其他车道的道路信息以及障碍物信息确定所述车辆在所述指定路段内的待变更车道；
更新模块334，用于根据所述确定模块333获得的待变更车道更新所述车道级最优行驶路径。
进一步的，如图4所示，所述确定模块333，包括：
获取子模块3331，用于分别获取所述指定路段内其他车道的道路信息以及所述障碍物信息中各个障碍物的通行速率和数量；
第三确定子模块3332，用于根据所述获取子模块3331获得的道路信息以及所述各个障碍物的通行速率和数量共同确定所述待变更车道。
进一步的，本发明实施例还提供一种存储介质，所述存储介质用于存储计算机程序，其中，所述计算机程序运行时控制所述存储介质所在设备执行上述图1-2中所述的环岛路径规划方法。
进一步的，本发明实施例还提供一种处理器，所述处理器用于运行程序，其中，所述程序运行时执行上述图1-2中所述的环岛路径规划方法。
在上述实施例中，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。
可以理解的是，上述方法及装置中的相关特征可以相互参考。另外，上述实施例中的“第一”、“第二”等是用于区分各实施例，而并不代表各实施例的优劣。
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，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在此提供的算法和显示不与任何特定计算机、虚拟系统或者其他设备固有相关。各种通用系统也可以与基于在此的示教一起使用。根据上面的描述，构造这类系统所要求的结构是显而易见的。此外，本发明也不针对任何特定编程语言。应当明白，可以利用各种编程语言实现在此描述的本发明的内容，并且上面对特定语言所做的描述是为了披露本发明的最佳实施方式。
此外，存储器可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)，存储器包括至少一个存储芯片。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
在一个典型的配置中，计算设备包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
存储器可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)。存储器是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括，但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带，磁 带磁磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。按照本文中的界定，计算机可读介质不包括暂存电脑可读媒体(transitory media)，如调制的数据信号和载波。
还需要说明的是，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、商品或者设备不仅包括那些要素，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、商品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括要素的过程、方法、商品或者设备中还存在另外的相同要素。
本领域技术人员应明白，本申请的实施例可提供为方法、系统或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
以上仅为本申请的实施例而已，并不用于限制本申请。对于本领域技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原理之内所作的任何修改、等同替换、改进等，均应包含在本申请的权利要求范围之内。

Claims (10)

  1. 一种环岛路径规划方法，其特征在于，包括：
    在车辆进入环岛区域时，实时采集车辆周边的道路信息与障碍物信息；
    利用所述道路信息与对应的高精地图信息为所述车辆在指定路段内规划车道级最优行驶路径；
    根据所述指定路段内的障碍物信息以及所述车辆的行驶信息对所述车道级最优行驶路径进行优化，得到所述车辆在环岛中的实时行驶路径。
  2. 根据权利要求1所述的方法，其特征在于，利用所述道路信息与对应的高精地图信息为所述车辆在指定路段内规划车道级最优行驶路径，包括：
    根据所述道路信息构建环岛局部地图；
    基于所述环岛局部地图与所述对应的高精地图建立环岛路网模型；
    依照预置规则将所述环岛路网模型中的环岛道路划分为多个路段；
    在所述指定路段内规划车道级最优行驶路径。
  3. 根据权利要求2所述的方法，其特征在于，依照预置规则将所述环岛路网模型中的环岛道路划分为多个路段，包括：
    将所述环岛路网模型中的出口位置、出口数量、车道数量代入在所述环岛路网模型中对各个车道进行路段划分的表征方程中，以确定所述环岛路网模型中所述车辆针对不同出口位置所能够对应行驶的不同路段。
  4. 根据权利要求2所述的方法，其特征在于，在指定路段内规划车道级最优行驶路径，包括：
    根据所述车辆的当前位置与目标出口确定所述车辆在所述环岛路网模型中的目标行驶路段；
    将所述目标行驶路段确定为所述车辆待行驶的指定路段；
    利用预置算法在所述指定路段内对所述车辆的行驶路径进行规划，以获得所述车道级最优行驶路径，所述预置算法是用于保证所述车辆的行驶路径长度最短而设置的算法。
  5. 根据权利要求1所述的方法，其特征在于，根据所述指定路段内的障碍物信息以及所述车辆的行驶信息对所述车道级最优行驶路径进行优化，包括：
    实时获取所述车辆的行驶信息；
    基于所述行驶信息判断所述指定路段内当前车道的障碍物信息是否满足所述车辆 预设的通行规则；
    若不满足，则基于所述指定路段内其他车道的道路信息以及障碍物信息确定所述车辆在所述指定路段内的待变更车道；
    根据所述待变更车道更新所述车道级最优行驶路径。
  6. 根据权利要求5所述的方法，其特征在于，基于所述指定路段内其他车道的道路信息以及障碍物信息确定所述车辆在所述指定路段内的待变更车道，包括：
    分别获取所述指定路段内其他车道的所述道路信息以及所述障碍物信息中各个障碍物的通行速率和数量；
    根据所述道路信息以及所述各个障碍物的通行速率和数量共同确定所述待变更车道。
  7. 一种环岛路径规划装置，其特征在于，包括：
    采集单元，用于在车辆进入环岛区域时，实时采集车辆周边的道路信息与障碍物信息；
    规划单元，用于利用所述采集单元中获得的道路信息与对应的高精地图信息为所述车辆在指定路段内规划车道级最优行驶路径；
    优化单元，用于根据所述指定路段内的障碍物信息以及所述车辆的行驶信息对所述规划单元中获得的车道级最优行驶路径进行优化，得到所述车辆在环岛中的实时行驶路径。
  8. 根据权利要求7所述的装置，其特征在于，所述规划单元包括：
    构建模块，用于根据所述道路信息构建环岛局部地图；
    建立模块，用于基于所述构建模块获得的环岛局部地图与所述对应的高精地图建立环岛路网模型；
    划分模块，用于依照预置规则将所述建立模块获得的环岛路网模型中的环岛道路划分为多个路段；
    规划模块，用于在所述划分模块获得的指定路段内规划车道级最优行驶路径。
  9. 一种存储介质，其特征在于，所述存储介质包括存储的程序，其中，在所述程序运行时控制所述存储介质所在设备执行如权利要求1至权利要求6中任意一项所述的方法。
  10. 一种处理器，其特征在于，所述处理器用于运行程序，其中，所述程序运行时执行如权利要求1至权利要求6中任意一项所述的方法。
PCT/CN2022/115691 2022-04-21 2022-08-30 一种环岛路径规划方法及装置 WO2023201954A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210420539.7A CN114894207A (zh) 2022-04-21 2022-04-21 一种环岛路径规划方法及装置
CN202210420539.7 2022-04-21

Publications (1)

Publication Number Publication Date
WO2023201954A1 true WO2023201954A1 (zh) 2023-10-26

Family

ID=82717017

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/115691 WO2023201954A1 (zh) 2022-04-21 2022-08-30 一种环岛路径规划方法及装置

Country Status (2)

Country Link
CN (1) CN114894207A (zh)
WO (1) WO2023201954A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114894207A (zh) * 2022-04-21 2022-08-12 合众新能源汽车有限公司 一种环岛路径规划方法及装置

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101046382A (zh) * 2007-04-27 2007-10-03 江苏新科数字技术有限公司 导航仪的环岛导航方法
JP2019052903A (ja) * 2017-09-14 2019-04-04 アルパイン株式会社 表示制御装置および表示制御方法
CN110738870A (zh) * 2018-07-20 2020-01-31 沃尔沃汽车公司 用于避免碰撞路线的系统和方法
CN111731324A (zh) * 2020-05-29 2020-10-02 徐帅 一种基于视觉引导agv智能车的控制方法及系统
CN112735134A (zh) * 2020-12-30 2021-04-30 惠州华阳通用电子有限公司 一种自动驾驶车辆的多车道环岛进入方法
CN114116927A (zh) * 2021-09-10 2022-03-01 高德软件有限公司 环岛道路识别方法、装置、电子设备及存储介质
CN114894207A (zh) * 2022-04-21 2022-08-12 合众新能源汽车有限公司 一种环岛路径规划方法及装置

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101046382A (zh) * 2007-04-27 2007-10-03 江苏新科数字技术有限公司 导航仪的环岛导航方法
JP2019052903A (ja) * 2017-09-14 2019-04-04 アルパイン株式会社 表示制御装置および表示制御方法
CN110738870A (zh) * 2018-07-20 2020-01-31 沃尔沃汽车公司 用于避免碰撞路线的系统和方法
CN111731324A (zh) * 2020-05-29 2020-10-02 徐帅 一种基于视觉引导agv智能车的控制方法及系统
CN112735134A (zh) * 2020-12-30 2021-04-30 惠州华阳通用电子有限公司 一种自动驾驶车辆的多车道环岛进入方法
CN114116927A (zh) * 2021-09-10 2022-03-01 高德软件有限公司 环岛道路识别方法、装置、电子设备及存储介质
CN114894207A (zh) * 2022-04-21 2022-08-12 合众新能源汽车有限公司 一种环岛路径规划方法及装置

Also Published As

Publication number Publication date
CN114894207A (zh) 2022-08-12

Similar Documents

Publication Publication Date Title
US10816990B2 (en) Non-blocking boundary for autonomous vehicle planning
EP3699048A1 (en) Travelling track prediction method and device for vehicle
US10754341B2 (en) Systems and methods for accelerated curve projection
US10775801B2 (en) Determining speeds along a path for autonomous driving vehicles
US11520335B2 (en) Determining driving paths for autonomous driving vehicles based on map data
CN109955853B (zh) 用于操作自动驾驶车辆的方法、系统和存储介质
JP6545507B2 (ja) 自動運転支援システム、自動運転支援方法及びコンピュータプログラム
WO2020108207A1 (zh) 一种高精度地图的构建方法及装置
JP6614025B2 (ja) 自動運転支援装置及びコンピュータプログラム
US20190346275A1 (en) Vehicle route guidance
US10816985B2 (en) Method on moving obstacle representation for trajectory planning
CN108981730A (zh) 用于为操作自动驾驶车辆生成参考路径的方法和系统
CN109491377A (zh) 用于自动驾驶车辆的基于dp和qp的决策和规划
CN109489675A (zh) 用于自动驾驶车辆的基于成本的路径规划
CN111133277A (zh) 使用时间和空间生成路线的方法、设备和计算机程序产品
JP6638556B2 (ja) 自動運転支援装置及びコンピュータプログラム
CN108171967B (zh) 一种交通控制方法及装置
US11586209B2 (en) Differential dynamic programming (DDP) based planning architecture for autonomous driving vehicles
CN107664504A (zh) 一种路径规划装置
US20230339500A1 (en) System, Method, and Computer Program Product for Topological Planning in Autonomous Driving Using Bounds Representations
CN108332761B (zh) 一种使用及创建路网地图信息的方法与设备
JP2017181391A (ja) コスト算出データのデータ構造
WO2023201954A1 (zh) 一种环岛路径规划方法及装置
CN115265564A (zh) 一种车道线标注方法及装置
WO2022259733A1 (ja) 運転支援装置

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: 22938179

Country of ref document: EP

Kind code of ref document: A1