Automatic driving human-like trajectory planning method and device, equipment and storage medium

Abstract

The invention provides an automatic driving human-like trajectory planning method and device, equipment and a storage medium, and belongs to the technical field of intelligent driving, and the automatic driving human-like trajectory planning method comprises the steps: collecting real vehicle driving data including at least one trajectory type, and forming a real vehicle trajectory data set; dividing track data in the real vehicle track data set to obtain a plurality of track sub-data sets; performing trajectory sampling on each trajectory sub-data set by adopting a farthest point sampling algorithm to obtain a target trajectory cluster set; and in combination with sensor sensing information of an automatic driving system, selecting a corresponding target track in the target track cluster set as course output of track planning. According to the invention, the track characteristics of human driving data are fully mined, effective calculation of real distribution of real vehicle track data is realized, any driving environment can be handled, and the anthropomorphism, smoothness and comfort of automatic driving track planning are improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent driving technology, and in particular to an autonomous driving humanoid trajectory planning method, device, equipment, and storage medium. Background Technology

[0002] Autonomous driving is a key area of ​​focus in automotive intelligence. It refers to using vehicle sensors such as cameras and radar to perceive surrounding information and leveraging computer vision and artificial intelligence technologies to plan the optimal driving trajectory in real time, thereby achieving autonomous driving. Trajectory clusters are a crucial component of vehicle trajectory planning; a good candidate trajectory cluster can represent a better distribution of the actual trajectory, thus planning a safe and comfortable driving path.

[0003] Among existing popular methods, trajectory cluster generation mainly takes two forms: The first is based on image perception data and vehicle status, calculating the trajectory using a series of driving rules, such as obstacle avoidance and parallelism between the trajectory and lane lines. However, this method suffers from insufficient trajectory diversity and failure to satisfy dynamic constraints. The second method is based on real human driving data, using a series of mathematical methods to fit real trajectories, such as polynomial fitting, to obtain trajectory clusters. However, this method suffers from poor trajectory continuity and smoothness. Summary of the Invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art, and proposes an autonomous driving humanoid trajectory planning method, device, equipment, and storage medium.

[0005] In a first aspect, embodiments of the present invention provide an autonomous driving human-like trajectory planning method, comprising:

[0006] Collect real-vehicle driving data containing at least one trajectory type to form a real-vehicle trajectory dataset;

[0007] The trajectory data in the real vehicle trajectory dataset is divided to obtain multiple trajectory subset datasets;

[0008] The farthest point sampling algorithm is used to sample the trajectory of each of the aforementioned trajectory subsets to obtain a set of target trajectory clusters.

[0009] By combining the sensor perception information of the autonomous driving system, the target trajectory corresponding to the target trajectory cluster set is selected as the heading output for trajectory planning.

[0010] Furthermore, the trajectory type includes at least one of the following: parking trajectory, straight-going trajectory, left / right lane change trajectory, left / right turn trajectory, U-turn trajectory, parking, acceleration trajectory, constant speed trajectory, and deceleration trajectory.

[0011] Furthermore, before dividing the trajectory data in the real vehicle trajectory dataset, the method further includes:

[0012] Preprocessing of the trajectory data in the real vehicle trajectory dataset specifically includes:

[0013] Extract multiple vehicle positioning information from the trajectory data, and use the vehicle positioning information to fuse wheel speed to obtain multiple vehicle trajectories;

[0014] Remove abnormal data from the vehicle trajectory; and / or detect the continuity of each vehicle trajectory and remove discontinuous vehicle trajectories to obtain preprocessed trajectory data.

[0015] Furthermore, the target trajectory data in the real vehicle trajectory dataset is divided by length to obtain multiple trajectory subsets, including:

[0016] The trajectory data in the real vehicle trajectory dataset is divided into multiple trajectory sub-datasets according to multiple preset speed ranges and / or multiple preset length ranges.

[0017] Furthermore, the step of using the farthest point sampling algorithm to sample the trajectory from each of the trajectory subsets to obtain a target trajectory cluster set includes:

[0018] Step S1: Determine multiple subsets of the trajectory datasets { The first trajectory subset in} In the first trajectory subset dataset Randomly select a trajectory data point and fill it into the first trajectory cluster subset. ;

[0019] Step S2: Extract the first trajectory cluster subset The last trajectory data in the dataset is used to calculate the relationship between the last trajectory data and the first trajectory subset. The distance between each trajectory data point;

[0020] Step S3: Extract the first trajectory subset dataset Mid-distance first trajectory cluster subset The last trajectory data in the dataset represents the farthest target trajectory data, which is then added to the first trajectory cluster subset. ;

[0021] Step S4: Repeat steps S2 to S3 above until the first subset of trajectory clusters containing the target trajectory number is obtained. ;

[0022] Step S5: For multiple said trajectory subsets { Repeat steps S1-S4 for other trajectory subsets in the target subset until a uniformly distributed subset of trajectory clusters is obtained. };

[0023] Step S6: Subset the uniformly distributed trajectory cluster { } as a set of target trajectory clusters .

[0024] Furthermore, the calculation of the last trajectory data and the first trajectory subset dataset... The distance between each trajectory data point is expressed mathematically as follows:

[0025]

[0026] in, This represents the distance between the last trajectory data in the first trajectory cluster subset and the trajectory data in the first trajectory subset dataset; This represents the coordinates of each trajectory point contained in the last trajectory data in the first trajectory cluster subset; The trajectory data in the first trajectory subset contains the coordinates of each trajectory point; This indicates the number of trajectory points.

[0027] Furthermore, the method also includes:

[0028] Target trajectory points are sampled for the target trajectory, and the speed output of the trajectory planning is optimized using the target trajectory points.

[0029] Secondly, embodiments of the present invention provide an autonomous driving human-like trajectory planning device, comprising:

[0030] The data acquisition module is used to collect real vehicle driving data containing at least one trajectory type to form a real vehicle trajectory dataset;

[0031] The trajectory segmentation module is used to segment the trajectory data in the real vehicle trajectory dataset to obtain multiple trajectory subsets;

[0032] The trajectory sampling module is used to perform trajectory sampling on each of the said trajectory subsets using the farthest point sampling algorithm to obtain a set of target trajectory clusters.

[0033] The heading output module is used to combine the sensor perception information of the autonomous driving system and select the target trajectory corresponding to the target trajectory cluster set as the heading output for trajectory planning.

[0034] Thirdly, embodiments of the present invention provide an electronic device, comprising:

[0035] one or more processors;

[0036] a memory for storing one or more programs;

[0037] When the one or more programs are executed by the one or more processors, the one or more processors implement the autonomous driving humanoid trajectory planning method as described in any one of the first aspects.

[0038] Fourthly, embodiments of the present invention provide a computer-readable medium storing a computer program, which, when executed by a processor, implements the steps of the autonomous driving humanoid trajectory planning method as described in any one of the first aspects.

[0039] This invention provides a human-like trajectory planning method for autonomous driving. It involves collecting real-vehicle driving data containing at least one trajectory type to form a real-vehicle trajectory dataset; dividing the trajectory data in the real-vehicle trajectory dataset into multiple trajectory subsets; using a farthest point sampling algorithm to sample the trajectories of each trajectory subset to obtain a target trajectory cluster set; and combining sensor perception information from the autonomous driving system, selecting the corresponding target trajectory from the target trajectory cluster set as the heading output for trajectory planning. This fully leverages the trajectory characteristics of human driving data, achieves effective calculation of the true distribution of real-vehicle trajectory data, and improves the human-likeness, smoothness, and comfort of autonomous driving trajectory planning. Attached Figure Description

[0040] Figure 1 This is a flowchart illustrating an embodiment of the human-like trajectory planning method for autonomous driving provided by the present invention.

[0041] Figure 2 This is a schematic diagram of the trajectory sampling process provided in an embodiment of the present invention;

[0042] Figure 3 This is a schematic diagram illustrating the distribution of a real vehicle trajectory dataset provided in an embodiment of the present invention;

[0043] Figure 4 This is a schematic diagram of the distribution of trajectory clusters after processing by the trajectory sampling method provided in an embodiment of the present invention;

[0044] Figure 5 This is a schematic diagram of the structure of an autonomous driving humanoid trajectory planning device provided in an embodiment of the present invention;

[0045] Figure 6 This is a schematic diagram of the structure of an autonomous driving humanoid trajectory planning device provided in another embodiment of the present invention;

[0046] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0047] To enable those skilled in the art to better understand the technical solutions of the present invention, exemplary embodiments of the present invention are described below in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0048] Where there is no conflict, the various embodiments of the present invention and the features thereof may be combined with each other.

[0049] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0050] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used herein, the singular forms “a” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that when the terms “comprising” and / or “made of” are used in this specification, the presence of the stated feature, integral, step, operation, element, and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof is not excluded. Terms such as “connected” or “linked” are not limited to physical or mechanical connections but can include electrical connections, whether direct or indirect.

[0051] Unless otherwise specified, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having the meaning consistent with their meaning in the context of the relevant art and the invention, and will not be interpreted as having an idealized or overly formal meaning unless expressly so defined herein.

[0052] In the technical solution of this invention, the collection, storage, use, processing, transmission, provision, and disclosure of user personal information all comply with relevant laws and regulations and do not violate public order and good morals. The use of user data in this technical solution follows relevant national laws and regulations (e.g., the "Information Security Technology - Personal Information Security Specification"). For example: appropriate measures are taken for personal information access control; restrictions are imposed on the display of personal information; the purpose of using personal information does not exceed the scope of direct or reasonable association; and explicit identity targeting is eliminated when using personal information to avoid precisely locating a specific individual.

[0053] In related technologies, trajectory cluster generation mainly involves two methods: The first is based on image perception data and the vehicle's state, calculating trajectory clusters through a series of driving rules, such as obstacle avoidance and parallelism between the trajectory and lane lines. However, this method suffers from insufficient diversity in the calculated trajectory clusters: trajectory clusters calculated based on preset anthropomorphic conditions exhibit rigidity; trajectory clusters calculated based on certain conditions, such as speed, acceleration, and trajectory curvature, have fixed patterns and are prone to getting trapped in local optima. Moreover, they may not meet the vehicle's kinematic and dynamic constraints, making actual control difficult after trajectory distribution and limiting practicality. The second method is based on real human driving data, using a series of mathematical methods to fit the real trajectory, such as polynomial fitting to obtain trajectory clusters. However, this method suffers from poor trajectory continuity and smoothness: the mathematical model-fitted trajectory still differs from the real trajectory, resulting in jittery driving trajectory, insufficient smoothness, and poor driving comfort.

[0054] To address at least one of the technical problems existing in the aforementioned related technologies, this invention provides a method for planning human-like trajectories for autonomous driving. For example... Figure 1 As shown, the autonomous driving humanoid trajectory planning method provided by this embodiment of the invention may include at least the following steps S101~S104:

[0055] Step S101: Collect real vehicle driving data containing at least one trajectory type to form a real vehicle trajectory dataset.

[0056] The autonomous driving human-like trajectory planning method proposed in this invention relies on a large amount of real-vehicle driving data collected on actual roads. In order to ensure that the quantity and diversity of real-vehicle driving data are sufficient, in practical applications, it is necessary to collect real-vehicle driving data corresponding to various trajectory types, including parking trajectory, straight-going trajectory, left / right lane change trajectory with different curvatures, left / right turn trajectory with different curvatures, U-turn trajectory with different curvatures, parking (vehicle speed is 0), acceleration trajectory with different accelerations, constant speed trajectory with different speeds, and deceleration trajectory with different decelerations, to form a real-vehicle trajectory dataset.

[0057] Step S102: Divide the trajectory data in the real vehicle trajectory dataset to obtain multiple trajectory subsets.

[0058] To ensure the validity and usability of the trajectory data, before dividing the trajectory data in the real vehicle trajectory dataset, this embodiment of the invention can also preprocess the trajectory data in the real vehicle trajectory dataset. Specifically, multiple vehicle positioning information is extracted from the trajectory data, and the wheel speed is fused using the vehicle positioning information to obtain multiple vehicle trajectories; abnormal data in the vehicle trajectories are removed, and the continuity of each vehicle trajectory is detected, and discontinuous vehicle trajectories are eliminated to obtain preprocessed trajectory data.

[0059] In practical applications, vehicle positioning information (GPS+IMU) can be extracted from the vehicle's CAN signal, and wheel speed can be fused to obtain vehicle coordinates at a certain frequency (e.g., 10Hz). The vehicle coordinates at the current moment are taken as the vehicle's trajectory points, and trajectory points at multiple moments (e.g., 5-second intervals) constitute the vehicle's trajectory. However, due to positioning errors in the actual collected data, the vehicle positioning information needs to be processed. Specifically, because GPS does not update at certain times, such as under overpasses or in tunnels, positioning errors exist, and abnormal trajectory data needs to be removed. In addition, due to the unavoidable frame drop problem during long-term collection, i.e., a small amount of positioning is lost, the continuity of the vehicle trajectory can also be measured to remove discontinuous trajectories.

[0060] Furthermore, after preprocessing the trajectory data in the real vehicle trajectory dataset, these trajectory data can be divided into multiple trajectory subsets according to multiple preset speed ranges and / or multiple preset length ranges.

[0061] To sample a prior trajectory cluster that is as diverse and evenly distributed as possible, this embodiment of the invention first divides the trajectory data in the real vehicle trajectory dataset according to trajectory speed and / or trajectory length. In practical applications, multiple continuous trajectory speed ranges can be set, for example, with a speed interval of 5 km / h. The preset speed range can be set to [0~5 km / h), [5~10 km / h), [10~15 km / h), etc., and trajectory data falling into different trajectory speed ranges are divided. Similarly, multiple continuous trajectory length ranges can also be set, and trajectory data falling into different trajectory length ranges are divided. Thus, we can obtain... Trajectory Subdataset { }

[0062] Step S103: The farthest point sampling algorithm is used to sample the trajectory of each trajectory subset to obtain the target trajectory cluster set.

[0063] like Figure 2 As shown, the trajectory sampling method provided in this embodiment of the invention may include at least the following steps S1031~S1035:

[0064] Step S1031: Determine multiple trajectory subsets { The first trajectory subset in} In the first trajectory subset dataset Randomly select a trajectory data point and fill it into the first trajectory cluster subset. .

[0065] Step S1032: Extract the first trajectory cluster subset The last trajectory data in the dataset is used to calculate the relationship between the last trajectory data and the first trajectory subset. The distance between each trajectory data point.

[0066] Specifically, to calculate the distance between the last trajectory data and the other trajectory data, we can calculate the L2 normal form of the corresponding trajectory points in sequence, and sum the distances between all corresponding trajectory points as the distance between the two trajectory data. The mathematical expression is as follows:

[0067]

[0068] in, This represents the distance between the last trajectory data in the first trajectory cluster subset and the trajectory data in the first trajectory subset dataset; This represents the coordinates of each trajectory point contained in the last trajectory data in the first trajectory cluster subset; The trajectory data in the first trajectory subset contains the coordinates of each trajectory point; This indicates the number of trajectory points.

[0069] It should be noted that in practical applications, the method for calculating the distance between two trajectory data can be set according to actual needs, such as Manhattan distance, Chebyshev distance, Minkowski distance, etc.

[0070] Step S1033: Extract the first trajectory subset dataset Mid-range first trajectory cluster subset The last trajectory data in the dataset represents the farthest target trajectory data. This target trajectory data is then added to the first trajectory cluster subset. .

[0071] Step S1034: Repeat steps S2 to S3 above until the first subset of trajectory clusters containing the target trajectory number is obtained. .

[0072] Step S1035: For multiple trajectory subsets { Repeat steps S1-S4 for other trajectory subsets in the target subset until a uniformly distributed subset of trajectory clusters is obtained. };

[0073] Step S1036: Subset of uniformly distributed trajectory clusters { } as a set of target trajectory clusters .

[0074] like Figure 3 The image shows a schematic diagram illustrating the distribution of the real vehicle trajectory dataset; as shown... Figure 4The diagram shown illustrates the distribution of trajectory clusters processed by the trajectory sampling method provided in an embodiment of the present invention (trajectory length intervals are 10 km). (Comparison) Figure 3 and Figure 4 Obviously, the trajectory clusters obtained through trajectory sampling are smoother, resulting in a more comfortable driving experience.

[0075] Step S104: Combining the sensor perception information of the autonomous driving system, select the target trajectory corresponding to the target trajectory cluster set as the heading output for trajectory planning.

[0076] For existing autonomous driving systems, based on the established prior trajectory cluster distribution, combined with sensor perception information, such as monitoring information from cameras, lidar and other devices, the corresponding trajectory in the target trajectory cluster set can be selected as the heading output for trajectory planning.

[0077] Furthermore, embodiments of the present invention can also sample trajectory points for the target trajectory to optimize the trajectory speed planned and output by the autonomous driving system, thereby achieving smoother and more comfortable autonomous driving.

[0078] This invention provides a human-like trajectory planning method for autonomous driving. It involves collecting real-vehicle driving data containing at least one trajectory type to form a real-vehicle trajectory dataset; dividing the trajectory data in the real-vehicle trajectory dataset into multiple trajectory subsets; using a farthest point sampling algorithm to sample the trajectories of each trajectory subset to obtain a target trajectory cluster set; and combining sensor perception information from the autonomous driving system, selecting the corresponding target trajectory from the target trajectory cluster set as the heading input for trajectory planning. Based on this invention's human-like trajectory planning method for autonomous driving, a method for constructing an autonomous driving real-vehicle trajectory dataset and an abnormal data cleaning mechanism are designed. By fully exploring the trajectory characteristics of human driving data based on real driving data, the method can effectively calculate the true distribution of real-vehicle trajectory data, improving the human-likeness, diversity, smoothness, and comfort of autonomous driving trajectory planning.

[0079] Based on the same inventive concept, as Figure 1 In a specific implementation, this invention also provides an autonomous driving human-like trajectory planning device, such as... Figure 5 As shown, the device may include: a data acquisition module 510, a trajectory division module 520, a trajectory sampling module 530, and a heading output module 540.

[0080] Data acquisition module 510 can be used to collect real vehicle driving data containing at least one trajectory type to form a real vehicle trajectory dataset;

[0081] The trajectory segmentation module 520 can be used to segment the trajectory data in the real vehicle trajectory dataset to obtain multiple trajectory subsets;

[0082] The trajectory sampling module 530 can be used to sample each trajectory subset using the farthest point sampling algorithm to obtain a set of target trajectory clusters.

[0083] The heading output module 540 can be used to combine the sensor perception information of the autonomous driving system and select the corresponding target trajectory in the target trajectory cluster set as the heading output for trajectory planning.

[0084] Optionally, such as Figure 6 As shown, another embodiment of the present invention provides an autonomous driving humanoid trajectory planning device, which further includes a speed output module 550.

[0085] The speed output module 550 can be used to sample target trajectory points for a target trajectory and use these target trajectory points to optimize the speed output of trajectory planning.

[0086] It should be noted that other corresponding descriptions of the functional modules involved in the autonomous driving humanoid trajectory planning device provided in this embodiment of the invention can be found in the following references. Figure 1 The corresponding descriptions of the methods shown will not be repeated here.

[0087] Based on the same inventive concept, embodiments of the present invention also provide an electronic device. Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Figure 7 As shown, an embodiment of the present invention provides an electronic device including: one or more processors 701, a memory 702, and one or more I / O interfaces 703. The memory 702 stores one or more programs, which, when executed by the one or more processors, enable the one or more processors to implement the autonomous driving humanoid trajectory planning method as described in the above embodiment; the one or more I / O interfaces 703 are connected between the processors and the memory, configured to enable information interaction between the processors and the memory.

[0088] Among them, processor 701 is a device with data processing capabilities, including but not limited to central processing unit (CPU); memory 702 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory (FLASH); I / O interface (read-write interface) 703 is connected between processor 701 and memory 702, and can realize information interaction between processor 701 and memory 702, including but not limited to data bus (Bus).

[0089] In some embodiments, the processor 701, memory 702, and I / O interface 703 are interconnected via bus 704, and thus connected to other components of the computing device.

[0090] In some embodiments, the one or more processors 701 include a field-programmable gate array.

[0091] This invention also provides a computer-readable medium. The computer-readable medium stores a computer program, which, when executed by a processor, implements the steps in the autonomous driving humanoid trajectory planning method described in the above embodiments. The computer-readable storage medium can be volatile or non-volatile.

[0092] This invention also provides a computer program product, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code. When the computer-readable code is run in the processor of an electronic device, the processor in the electronic device executes the steps in the autonomous driving humanoid trajectory planning method as described in the above embodiments.

[0093] It will be understood by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware implementation, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable storage medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium).

[0094] As is well known to those skilled in the art, the term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information (such as computer-readable program instructions, data structures, program modules or other data). Computer storage media includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technology, portable compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, as is well known to those skilled in the art, communication media typically contains computer-readable program instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0095] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0096] The computer program instructions used to perform the operations of this invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing state information from the computer-readable program instructions. This electronic circuitry can execute the computer-readable program instructions to implement various aspects of the invention.

[0097] The computer program product described herein can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0098] Various aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0099] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0100] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0101] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0102] Example embodiments have been disclosed herein, and while specific terminology has been used, it is for illustrative purposes only and should be construed as such, and is not intended to be limiting. In some instances, it will be apparent to those skilled in the art that features, characteristics, and / or elements described in conjunction with particular embodiments may be used alone, or in combination with features, characteristics, and / or elements described in conjunction with other embodiments, unless otherwise expressly indicated. Therefore, those skilled in the art will understand that various changes in form and detail may be made without departing from the scope of the invention as set forth in the appended claims.

Claims

1. A method for planning human-like trajectories in autonomous driving, characterized in that, include: Collect real-vehicle driving data containing at least one trajectory type to form a real-vehicle trajectory dataset; The trajectory data in the real vehicle trajectory dataset is divided to obtain multiple trajectory subset datasets; The farthest point sampling algorithm is used to sample the trajectory of each of the aforementioned trajectory subsets to obtain a set of target trajectory clusters. By combining the sensor perception information of the autonomous driving system, the target trajectory corresponding to the target trajectory cluster set is selected as the heading output for trajectory planning.

2. The method according to claim 1, characterized in that, The trajectory types include at least one of the following: parking trajectory, straight-going trajectory, left / right lane change trajectory, left / right turn trajectory, U-turn trajectory, parking, acceleration trajectory, constant speed trajectory, and deceleration trajectory.

3. The method according to claim 1, characterized in that, Before dividing the trajectory data in the real vehicle trajectory dataset, the method further includes: Preprocessing of the trajectory data in the real vehicle trajectory dataset specifically includes: Extract multiple vehicle positioning information from the trajectory data, and use the vehicle positioning information to fuse wheel speed to obtain multiple vehicle trajectories; Remove abnormal data from the vehicle trajectory; and / or detect the continuity of each vehicle trajectory and remove discontinuous vehicle trajectories to obtain preprocessed trajectory data.

4. The method according to claim 1, characterized in that, The target trajectory data in the real vehicle trajectory dataset is divided by length to obtain multiple trajectory subsets, including: The trajectory data in the real vehicle trajectory dataset is divided into multiple trajectory sub-datasets according to multiple preset speed ranges and / or multiple preset length ranges.

5. The method according to claim 1, characterized in that, The method employs the farthest point sampling algorithm to sample the trajectory from each of the trajectory subsets, resulting in a target trajectory cluster set, including: Step S1: Determine multiple subsets of the trajectory datasets { The first trajectory subset in} In the first trajectory subset dataset Randomly select a trajectory data point and fill it into the first trajectory cluster subset. ; Step S2: Extract the first trajectory cluster subset The last trajectory data in the dataset is used to calculate the relationship between the last trajectory data and the first trajectory subset. The distance between each trajectory data point; Step S3: Extract the first trajectory subset dataset Mid-distance first trajectory cluster subset The last trajectory data in the dataset represents the farthest target trajectory data, which is then added to the first trajectory cluster subset. ; Step S4: Repeat steps S2 to S3 above until the first subset of trajectory clusters containing the target trajectory number is obtained. ; Step S5: For multiple said trajectory subsets { Repeat steps S1-S4 for other trajectory subsets in the target subset until a uniformly distributed subset of trajectory clusters is obtained. }; Step S6: Subset the uniformly distributed trajectory cluster { } as a set of target trajectory clusters .

6. The method according to claim 5, characterized in that, The calculation of the last trajectory data and the first trajectory subset dataset The distance between each trajectory data point is expressed mathematically as follows: in, This represents the distance between the last trajectory data in the first trajectory cluster subset and the trajectory data in the first trajectory subset dataset; This represents the coordinates of each trajectory point contained in the last trajectory data in the first trajectory cluster subset; The trajectory data in the first trajectory subset contains the coordinates of each trajectory point; This indicates the number of trajectory points.

7. The method according to any one of claims 1 to 6, characterized in that, The method further comprises: Target trajectory points are sampled for the target trajectory, and the speed output of the trajectory planning is optimized using the target trajectory points.

8. An autonomous driving humanoid trajectory planning device, characterized in that, include: The data acquisition module is used to collect real vehicle driving data containing at least one trajectory type to form a real vehicle trajectory dataset; The trajectory segmentation module is used to segment the trajectory data in the real vehicle trajectory dataset to obtain multiple trajectory subsets; The trajectory sampling module is used to perform trajectory sampling on each of the said trajectory subsets using the farthest point sampling algorithm to obtain a set of target trajectory clusters. The heading output module is used to combine the sensor perception information of the autonomous driving system and select the target trajectory corresponding to the target trajectory cluster set as the heading output for trajectory planning.

9. An electronic device, characterized in that, include: one or more processors; a memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the autonomous driving humanoid trajectory planning method as described in any one of claims 1 to 7.

10. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps in the autonomous driving humanoid trajectory planning method as described in any one of claims 1 to 7.

Images