Path planning methods and devices for autonomous vehicles and autonomous vehicles
By predicting the probability of collision with obstacles in autonomous vehicles and triggering a lightweight planning algorithm, the collision problem caused by obstacle response delay is solved, achieving fast response and reducing the probability of collision.
Patent Information
- Application Number
- CN202410036696.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-01-09
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2044-01-09
AI Technical Summary
In existing autonomous driving technologies, the long response time to obstacles increases the probability of collisions, making it highly dangerous.
By determining whether there are target obstacles in the environment around the autonomous vehicle, the probability of collision between the obstacle and the vehicle is predicted, and a lightweight planning algorithm is used to plan the path to prevent collisions.
This reduces the amount of computation, enabling autonomous vehicles to respond quickly in a short time and lowering the probability of collisions with obstacles.
Smart Images

Figure CN117870710B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of autonomous driving, and more specifically, to a path planning method for an autonomous vehicle, a path planning device for an autonomous vehicle, a storage medium, an electronic device, and an autonomous vehicle. Background Technology
[0002] Generally, the framework of autonomous driving consists of a perception module (which uses lidar to scan obstacles and process them), a prediction module (which predicts the future trajectory of obstacles), a planning module (which calculates the vehicle's trajectory based on obstacle information), and a control module (which converts the calculated trajectory into control signals and transmits them to the vehicle). Each obstacle must pass through these modules sequentially before the trajectory change is executed, resulting in a relatively long delay—potentially 0.5 to 1 second before the vehicle can respond. This longer response time increases the probability of collisions with obstacles, posing a greater risk. Summary of the Invention
[0003] The main objective of this application is to provide a path planning method, a path planning device, a storage medium, an electronic device, and an autonomous vehicle for autonomous driving, so as to at least solve the problem in the prior art that the long response delay of autonomous driving to obstacles leads to an increased probability of collision with obstacles.
[0004] To achieve the above objectives, according to one aspect of this application, a path planning method for an autonomous vehicle is provided, comprising: determining whether a target obstacle exists in the surrounding environment of the autonomous vehicle, the target obstacle being an obstacle that poses a safety threat to the autonomous vehicle; if the target obstacle exists, predicting the probability of the target obstacle colliding with the autonomous vehicle within a preset time period in the future, and determining whether to trigger a lightweight planning algorithm based on the probability of collision; if it is determined that the lightweight planning algorithm is triggered, using the lightweight planning algorithm to perform path planning for the autonomous vehicle to prevent the autonomous vehicle from colliding with the target obstacle.
[0005] Optionally, determining whether to trigger the lightweight planning algorithm based on the probability of collision includes: determining to trigger the lightweight planning algorithm if the probability of collision is greater than or equal to a probability threshold; and determining not to trigger the lightweight planning algorithm if the probability of collision is less than the probability threshold.
[0006] Optionally, predicting the probability of the target obstacle colliding with the autonomous vehicle within a preset time period in the future includes: setting multiple pre-selected vehicle longitudinal accelerations and multiple pre-selected vehicle lateral steering wheel rotations, selecting one vehicle longitudinal acceleration and one vehicle lateral steering wheel rotation for any point in time within the preset time period in the future, forming multiple selection combinations; and determining the probability of the target obstacle colliding with the autonomous vehicle under any of the selection combinations.
[0007] Optionally, determining whether to trigger the lightweight planning algorithm based on the probability of collision includes: determining to trigger the lightweight planning algorithm if the target obstacle collides with the autonomous vehicle in all of the selected combinations; and determining not to trigger the lightweight planning algorithm if the target obstacle does not collide with the autonomous vehicle in at least one of the selected combinations.
[0008] Optionally, when the lightweight planning algorithm is triggered, the lightweight planning algorithm is used to plan the path of the autonomous vehicle to prevent the autonomous vehicle from colliding with the target obstacle, including: expanding the selection combination to obtain an expanded selection combination; obtaining the minimum distance between the autonomous vehicle and multiple target obstacles under each expanded selection combination; determining the selection combination corresponding to the maximum value among the multiple minimum distances as the final selection combination; and using the final selection combination to plan the path of the autonomous vehicle.
[0009] Optionally, setting a plurality of pre-selected vehicle longitudinal accelerations and a plurality of pre-selected vehicle lateral steering wheel rotations includes: determining a plurality of corresponding vehicle lateral accelerations based on the plurality of vehicle longitudinal accelerations, wherein the vehicle longitudinal accelerations and vehicle lateral accelerations correspond one-to-one; and determining a plurality of vehicle lateral steering wheel rotations based on the plurality of vehicle lateral accelerations, wherein the vehicle lateral accelerations and vehicle lateral steering wheel rotations correspond one-to-one.
[0010] Optionally, the plurality of vehicle longitudinal accelerations include at least one deceleration acceleration and at least one acceleration acceleration, and the plurality of vehicle lateral steering wheel rotations include at least one negative steering wheel rotation and at least one positive steering wheel rotation.
[0011] Optionally, the minimum deceleration is related to the vehicle's braking performance, and the maximum acceleration is related to the vehicle's acceleration performance.
[0012] Optionally, the method further includes: if it is determined that the lightweight planning algorithm will not be triggered, performing path planning for the autonomous vehicle using a conventional algorithm, wherein the conventional algorithm includes a perception module, a prediction module, a planning module, and a control module; and performing path planning for the autonomous vehicle using the conventional algorithm if there is no target obstacle in the surrounding environment of the autonomous vehicle.
[0013] Optionally, the target obstacle includes at least one of the following: an obstacle whose distance from the autonomous vehicle is less than a lower distance limit, the first obstacle directly in front of the autonomous vehicle, an obstacle behind or to the side of the autonomous vehicle, an obstacle crossing the road in front of the autonomous vehicle, a pedestrian with a running start, or a non-motorized vehicle with a sudden start.
[0014] According to another aspect of this application, a path planning device for an autonomous vehicle is provided, comprising: a determining unit, configured to determine whether a target obstacle exists in the surrounding environment of the autonomous vehicle, the target obstacle being an obstacle that poses a safety threat to the autonomous vehicle; a prediction determining unit, configured to, in the presence of the target obstacle, predict the probability of the target obstacle colliding with the autonomous vehicle within a preset time period in the future, and determine whether to trigger a lightweight planning algorithm based on the collision probability; and a planning unit, configured to, in the case that the lightweight planning algorithm is determined to be triggered, use the lightweight planning algorithm to plan a path for the autonomous vehicle to prevent the autonomous vehicle from colliding with the target obstacle.
[0015] Optionally, the prediction and determination unit includes a prediction module, which is used to predict the probability of the target obstacle colliding with the autonomous vehicle within a preset time period in the future. The prediction module includes: a setting submodule, used to set multiple pre-selected vehicle longitudinal accelerations and multiple pre-selected vehicle lateral steering wheel speeds, and to select one vehicle longitudinal acceleration and one vehicle lateral steering wheel speed for any time point within the preset time period in the future, forming multiple selection combinations; and a determination submodule, used to determine the probability of the target obstacle colliding with the autonomous vehicle under any of the selection combinations.
[0016] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to perform any of the aforementioned path planning methods for autonomous vehicles.
[0017] According to another aspect of this application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including a path planning method for performing any of the aforementioned autonomous vehicle.
[0018] According to another aspect of this application, an autonomous vehicle includes: a computing device that executes any of the path planning methods for the autonomous vehicle described above.
[0019] The technical solution of this application first determines whether there is a target obstacle in the surrounding environment of the autonomous vehicle, and the target obstacle is an obstacle that poses a threat to the safety of the autonomous vehicle. Then, if a target obstacle exists, the probability of the target obstacle colliding with the autonomous vehicle within a preset time period in the future is predicted, and a lightweight planning algorithm is triggered based on the collision probability. Finally, if the lightweight planning algorithm is triggered, it is used to plan a path for the autonomous vehicle to prevent collisions with the target obstacle. This application reduces the computational load by predicting the probability of a collision between the target obstacle and the autonomous vehicle to determine whether to trigger the lightweight planning algorithm, achieving a faster response time for the autonomous vehicle. This solves the problem in the prior art where the long response time of autonomous vehicles to obstacles leads to an increased probability of collision. Attached Figure Description
[0020] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:
[0021] Figure 1 A hardware structure block diagram of a mobile terminal for performing a path planning method for an autonomous vehicle, according to an embodiment of this application, is shown.
[0022] Figure 2 A flowchart illustrating a path planning method for an autonomous vehicle according to an embodiment of this application is shown.
[0023] Figure 3 A structural block diagram of a path planning method apparatus for an autonomous vehicle provided according to an embodiment of this application is shown. Detailed Implementation
[0024] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.
[0025] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.
[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0027] As described in the background section, any obstacle requires passing through multiple modules sequentially before the trajectory change can be executed, resulting in a long delay. The vehicle may not respond for 0.5s to 1s. The long response time increases the probability of collision with obstacles, posing a significant risk. To address the problem of long response delays to obstacles in existing autonomous driving technologies, which increases the probability of collisions, embodiments of this application provide a path planning method for autonomous vehicles.
[0028] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.
[0029] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a path planning method for an autonomous vehicle according to an embodiment of the present invention. For example... Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.
[0030] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the path planning method for autonomous vehicles in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.
[0031] This embodiment provides a path planning method for an autonomous vehicle running on a mobile terminal, computer terminal, or similar computing device. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.
[0032] Figure 2 This is a flowchart of a path planning method for an autonomous vehicle according to an embodiment of this application. Figure 2 As shown, the method includes the following steps:
[0033] Step S201: Determine whether there is a target obstacle in the surrounding environment of the autonomous vehicle. The target obstacle is an obstacle that poses a threat to the safety of the autonomous vehicle.
[0034] The target obstacle in the above steps is an obstacle that poses a threat to the safety of the autonomous vehicle (e.g., an obstacle that is relatively close). Obstacles that are relatively far away generally do not pose a threat to the safety of the autonomous vehicle. That is, whether an object is a target obstacle can be determined by the distance between the object and the autonomous vehicle.
[0035] In one optional embodiment, an autonomous vehicle is driving normally on the road when suddenly a flock of sheep appears in front of it. At this time, based on the previous walking speed of the sheep and the driving speed of the vehicle, it is determined whether there is a time interval between the walking sheep and the driving vehicle that is less than a set value. If there is, then the flock of sheep is the target obstacle; if not, then the flock of sheep is not the target obstacle.
[0036] Step S202: In the presence of a target obstacle, predict the probability of the target obstacle colliding with the autonomous vehicle within a preset time period in the future, and determine whether to trigger the lightweight planning algorithm based on the probability of collision.
[0037] Among them, lightweight planning algorithms have a much smaller computational load than conventional planning algorithms, by several orders of magnitude. Therefore, using lightweight planning algorithms can save a lot of time, make a rapid response, and prevent collisions.
[0038] Specifically, given that a target obstacle already exists, it is necessary to predict the probability of a collision between the target obstacle and the autonomous vehicle. This can be done by determining the probability of a collision between the autonomous vehicle and the target obstacle over a period of time, such as predicting the probability of a collision within the next 3 seconds. If this probability is high, a lightweight planning algorithm is triggered; if this probability is low, a conventional approach is used to respond. In other words, the autonomous vehicle responds sequentially in the order of the perception module, prediction module, planning module, and control module.
[0039] Step S203: If it is determined that the lightweight planning algorithm is triggered, the lightweight planning algorithm is used to plan the path for the autonomous vehicle to prevent the autonomous vehicle from colliding with the target obstacle.
[0040] In an optional embodiment, the vehicle trajectory is enumerated using longitudinal acceleration and lateral steering wheel rotation speed. Each second, one longitudinal acceleration and one lateral steering wheel rotation speed are selected for execution; by determining the time interval, the number of possibilities can be determined. If multiple possibilities indicate a collision, a lightweight planning algorithm is triggered. When determining which scheme to use in triggering the lightweight planning algorithm, more possibilities are determined using the enumerated longitudinal acceleration and enumerated lateral steering wheel rotation speed. Among these more possibilities, the scheme with the greatest possible "minimum distance to all obstacles" is selected and sent to the underlying control logic. In this way, collision detection uses a relatively conservative method to roughly calculate whether a collision has occurred, and since more options are available when selecting a scheme, the likelihood of avoiding a collision is increased.
[0041] The technical solution of this application first determines whether there is a target obstacle in the surrounding environment of the autonomous vehicle, and the target obstacle is an obstacle that poses a threat to the safety of the autonomous vehicle. Then, if a target obstacle exists, the probability of the target obstacle colliding with the autonomous vehicle within a preset time period in the future is predicted, and a lightweight planning algorithm is triggered based on the collision probability. Finally, if the lightweight planning algorithm is triggered, it is used to plan a path for the autonomous vehicle to prevent collisions with the target obstacle. This application reduces the computational load by predicting the probability of a collision between the target obstacle and the autonomous vehicle to determine whether to trigger the lightweight planning algorithm, achieving a faster response time for the autonomous vehicle. This solves the problem in the prior art where the long response time of autonomous vehicles to obstacles leads to an increased probability of collision.
[0042] Optionally, determining whether to trigger the lightweight programming algorithm based on the probability of collision includes: triggering the lightweight programming algorithm if the probability of collision is greater than or equal to a probability threshold; and not triggering the lightweight programming algorithm if the probability of collision is less than the probability threshold. In other words, the triggering of the lightweight programming algorithm is determined by a probability threshold. The probability threshold can be set according to actual needs.
[0043] Optionally, predicting the probability of a target obstacle colliding with an autonomous vehicle within a preset time period in the future includes: setting multiple pre-selected longitudinal accelerations and multiple pre-selected lateral steering wheel rotations. For example, the multiple longitudinal accelerations can be longitudinal accelerations {-5m / s^2, 0m / s^2, +1m / s^2}; the multiple lateral steering wheel rotations can be lateral steering wheel rotations {-180deg / s, 0deg / s, 180deg / s}. For any point in time within the preset time period, a vehicle longitudinal acceleration and a vehicle lateral steering wheel rotation are selected to form multiple selection combinations. These multiple selection combinations can be obtained through enumeration. The probability of a target obstacle colliding with an autonomous vehicle under any selection combination is then determined.
[0044] Optionally, the triggering of the lightweight planning algorithm is determined based on the probability of collision. This includes: triggering the lightweight planning algorithm if the target obstacle collides with the autonomous vehicle under all selection combinations; and not triggering the lightweight planning algorithm if the target obstacle does not collide with the autonomous vehicle under at least one selection combination. Triggering the lightweight planning algorithm only when the probability of collision is high ensures that the algorithm is triggered only when the probability is low; otherwise, conventional planning methods are sufficient. This avoids false triggering.
[0045] In one specific embodiment, the vehicle trajectory is enumerated using longitudinal acceleration {-5m / s², 0m / s², +1m / s²} and lateral steering wheel rotation speed {-180deg / s, 0deg / s, 180deg / s}. Each second, one longitudinal acceleration and one lateral steering wheel rotation speed are selected for execution. Considering a 3-second interval, there are 9³ = 729 possibilities. The lightweight planning algorithm is only triggered if a collision occurs in all 729 possibilities.
[0046] Optionally, when it is determined that the lightweight planning algorithm is triggered, the lightweight planning algorithm is used to plan the path of the autonomous vehicle to prevent the autonomous vehicle from colliding with the target obstacle, including: expanding the selection combination to obtain the expanded selection combination, obtaining the minimum distance between the autonomous vehicle and multiple target obstacles under each expanded selection combination; determining the selection combination corresponding to the maximum value among multiple minimum distances as the final selection combination; and using the final selection combination to plan the path of the autonomous vehicle.
[0047] In a specific embodiment, if a collision is triggered due to 729 possible scenarios, when determining which scheme to use in the lightweight planning algorithm, the enumerated accelerations are {-7.5m / s², -5m / s², -2.5m / s², 0m / s², +1m / s²}, and the enumerated lateral steering wheel rotation speeds are {-180deg / s, 0, 180deg / s}, resulting in 3375 possibilities. That is, the expanded selection combination mentioned above selects the scheme with the largest possible distance to all obstacles from these 3375 possibilities. In other words, the final selection combination is sent to the underlying control logic. In this way, collision detection uses a relatively conservative method to roughly calculate whether a collision has occurred. Since there are more options to choose from when selecting a scheme, the probability of avoiding a collision is increased.
[0048] Optionally, multiple pre-selected vehicle longitudinal accelerations and multiple pre-selected vehicle lateral steering wheel rotation speeds are set, including: determining multiple corresponding vehicle lateral accelerations based on the multiple vehicle longitudinal accelerations, with a one-to-one correspondence between the longitudinal and lateral accelerations; and determining multiple vehicle lateral steering wheel rotation speeds based on the multiple vehicle lateral accelerations, with a one-to-one correspondence between the lateral accelerations and the lateral steering wheel rotation speeds. Specifically, the longitudinal acceleration has a constraining effect on the lateral acceleration; for example, if the longitudinal acceleration is too large, the lateral acceleration needs to be set smaller to prevent danger.
[0049] Optionally, the longitudinal accelerations of the multiple vehicles include at least one deceleration acceleration, i.e., -5 m / s² in the longitudinal acceleration {-5 m / s², 0 m / s², +1 m / s²}, and at least one acceleration acceleration, i.e., 1 m / s². Similarly, the lateral steering wheel rotation speeds of the multiple vehicles include at least one negative steering wheel rotation speed and at least one positive steering wheel rotation speed. In other words, this combination of considerations provides a more comprehensive picture, leading to more accurate planning.
[0050] Optionally, the minimum deceleration is related to the vehicle's braking performance, and the maximum acceleration is related to the vehicle's acceleration performance. That is, different vehicle performance characteristics result in different deceleration and acceleration accelerations. For example, if the vehicle's maximum braking acceleration is -10 m / s², half of -10 m / s² is chosen as the selected deceleration acceleration; if the vehicle's acceleration acceleration is +2 m / s², half of +2 m / s² is chosen as the selected acceleration acceleration. Of course, this setting takes into account the constraint effect of longitudinal acceleration on lateral acceleration.
[0051] Optionally, the method further includes: when it is determined that the lightweight planning algorithm will not be triggered, using a conventional algorithm to plan the path for the autonomous vehicle, the conventional algorithm including a perception module, a prediction module, a planning module, and a control module; when there are no target obstacles in the surrounding environment of the autonomous vehicle, using a conventional algorithm to plan the path for the autonomous vehicle. Further, the perception module is used to scan obstacles with LiDAR and process them; the prediction module is used to predict the future trajectory of the obstacles; the planning module is used to calculate the vehicle's motion trajectory based on the obstacle information; and the control module is used to convert the calculated motion trajectory into a control signal and transmit it to the vehicle.
[0052] Optionally, the target obstacle includes at least one of the following: an obstacle whose distance from the autonomous vehicle is less than a lower distance limit, the first obstacle directly in front of the autonomous vehicle, an obstacle behind or to the side of the autonomous vehicle, an obstacle crossing the road in front of the autonomous vehicle, a pedestrian taking off, or a non-motorized vehicle suddenly starting. Further, the speed of the aforementioned target obstacle can be obtained by predicting the speed of the target obstacle previously.
[0053] This application also provides a path planning device for an autonomous vehicle. It should be noted that the path planning device for an autonomous vehicle in this application can be used to execute the path planning method for autonomous vehicles provided in this application. This device is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.
[0054] The following describes the path planning device for autonomous vehicles provided in the embodiments of this application.
[0055] Figure 3 This is a schematic diagram of a path planning device for an autonomous vehicle according to an embodiment of this application. Figure 3 As shown, the device includes:
[0056] The determining unit 31 is used to determine whether there is a target obstacle in the surrounding environment of the autonomous vehicle, and the target obstacle is an obstacle that poses a threat to the safety of the autonomous vehicle.
[0057] The prediction and determination unit 32 is used to predict the probability of a target obstacle colliding with an autonomous vehicle within a preset time period in the presence of a target obstacle, and to determine whether to trigger a lightweight planning algorithm based on the probability of collision.
[0058] Planning unit 33 is used to perform path planning for autonomous vehicles using a lightweight planning algorithm when it is determined that the lightweight planning algorithm is triggered, in order to prevent autonomous vehicles from colliding with target obstacles.
[0059] Optionally, the prediction and determination unit includes a prediction module, which is used to predict the probability of a target obstacle colliding with an autonomous vehicle within a preset time period in the future. The prediction module includes: a setting submodule, used to set multiple pre-selected vehicle longitudinal accelerations and multiple pre-selected vehicle lateral steering wheel speeds, and to select a vehicle longitudinal acceleration and a vehicle lateral steering wheel speed for any time point within the preset time period in the future, forming multiple selection combinations; and a first determination submodule, used to determine the probability of a target obstacle colliding with an autonomous vehicle under any selection combination.
[0060] Optionally, the prediction and determination unit further includes a first determination module, used to determine whether to trigger the lightweight planning algorithm when the probability of collision is greater than or equal to a probability threshold; and a second determination module, used to determine whether to trigger the lightweight planning algorithm when the probability of collision is less than the probability threshold.
[0061] Optionally, the prediction and determination unit further includes a setting module, which sets multiple pre-selected vehicle longitudinal accelerations and multiple pre-selected vehicle lateral steering wheel speeds, and selects a vehicle longitudinal acceleration and a vehicle lateral steering wheel speed for any time point within a preset time period in the future, forming multiple selection combinations; the third determination module is used to determine the probability of the target obstacle colliding with the autonomous vehicle under any selection combination.
[0062] Optionally, the prediction and determination unit further includes: a third determination module, used to determine whether to trigger the lightweight planning algorithm when the target obstacle collides with the autonomous vehicle under all selection combinations; and a fourth determination module, used to determine whether to not trigger the lightweight planning algorithm when the target obstacle does not collide with the autonomous vehicle under at least one selection combination.
[0063] Optionally, the third determining module includes: an acquisition submodule, used to expand the selection combination to obtain an expanded selection combination, and to obtain the minimum distance between the autonomous vehicle and multiple target obstacles under each expanded selection combination; a second determining submodule, used to determine the selection combination corresponding to the maximum value among multiple minimum distances as the final selection combination; and a planning submodule, used to perform path planning for the autonomous vehicle using the final selection combination.
[0064] Optionally, the setting module includes: a third determining submodule, used to determine the corresponding lateral accelerations of multiple vehicles based on the longitudinal accelerations of multiple vehicles, with a one-to-one correspondence between the longitudinal accelerations and the lateral accelerations of the vehicles; and a fourth determining submodule, used to determine the lateral steering wheel rotation speeds of multiple vehicles based on the lateral accelerations of multiple vehicles, with a one-to-one correspondence between the lateral accelerations and the lateral steering wheel rotation speeds of the vehicles.
[0065] Optionally, the planning unit includes: a first planning module, used to perform path planning for the autonomous vehicle using a conventional algorithm when it is determined that the lightweight planning algorithm will not be triggered, the conventional algorithm including a perception module, a prediction module, a planning module and a control module; and a second planning module, used to perform path planning for the autonomous vehicle using a conventional algorithm when there are no target obstacles in the surrounding environment of the autonomous vehicle.
[0066] The technical solution of this application includes a determining unit for determining whether a target obstacle exists in the surrounding environment of the autonomous vehicle, wherein the target obstacle is an obstacle that poses a safety threat to the autonomous vehicle; a prediction determining unit for predicting the probability of a collision between the target obstacle and the autonomous vehicle within a preset time period in the presence of a target obstacle, and determining whether to trigger a lightweight planning algorithm based on the collision probability; and a planning unit for using the lightweight planning algorithm to plan a path for the autonomous vehicle to prevent collisions with the target obstacle if the lightweight planning algorithm is triggered. This application achieves the goal of reducing computational load by determining whether to trigger a lightweight planning algorithm based on the probability of a collision between the target obstacle and the autonomous vehicle, thus achieving a faster response time for the autonomous vehicle and solving the problem in the prior art where the long response delay of autonomous vehicles to obstacles leads to an increased probability of collision.
[0067] The path planning device for the autonomous vehicle includes a processor and a memory. The aforementioned determination unit, prediction determination unit, and planning unit are all stored as program units in the memory, and the processor executes these program units stored in the memory to achieve the corresponding functions. All of the above modules are located in the same processor; alternatively, the modules may be located in different processors in any combination.
[0068] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and adjusting kernel parameters can address the problem in existing technologies where long response times to obstacles in autonomous driving lead to an increased probability of collisions.
[0069] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.
[0070] This invention provides a computer-readable storage medium including a stored program, wherein the program, when running, controls the device containing the computer-readable storage medium to execute a path planning method for an autonomous vehicle.
[0071] Specifically, the path planning methods for autonomous vehicles include:
[0072] Step S201: Determine whether there is a target obstacle in the surrounding environment of the autonomous vehicle. The target obstacle is an obstacle that poses a threat to the safety of the autonomous vehicle.
[0073] Step S202: In the presence of a target obstacle, predict the probability of the target obstacle colliding with the autonomous vehicle within a preset time period in the future, and determine whether to trigger the lightweight planning algorithm based on the probability of collision.
[0074] Step S203: If it is determined that the lightweight planning algorithm is triggered, the lightweight planning algorithm is used to plan the path for the autonomous vehicle to prevent the autonomous vehicle from colliding with the target obstacle.
[0075] Optionally, determining whether to trigger the lightweight programming algorithm based on the probability of collision includes: determining to trigger the lightweight programming algorithm if the probability of collision is greater than or equal to a probability threshold; and determining not to trigger the lightweight programming algorithm if the probability of collision is less than the probability threshold.
[0076] Optionally, predicting the probability of a target obstacle colliding with an autonomous vehicle within a preset time period in the future includes: setting multiple pre-selected longitudinal accelerations and multiple pre-selected lateral steering wheel speeds of vehicles, selecting one vehicle longitudinal acceleration and one vehicle lateral steering wheel speed for any point in time within the preset time period in the future to form multiple selection combinations; and determining the probability of a target obstacle colliding with an autonomous vehicle under any selection combination.
[0077] Optionally, determining whether to trigger the lightweight planning algorithm based on the probability of collision includes: determining to trigger the lightweight planning algorithm if the target obstacle and the autonomous vehicle collide in all selection combinations; and determining not to trigger the lightweight planning algorithm if the target obstacle and the autonomous vehicle do not collide in at least one selection combination.
[0078] Optionally, when it is determined that the lightweight planning algorithm is triggered, the lightweight planning algorithm is used to plan the path of the autonomous vehicle to prevent the autonomous vehicle from colliding with the target obstacle, including: expanding the selection combination to obtain the expanded selection combination, obtaining the minimum distance between the autonomous vehicle and multiple target obstacles under each expanded selection combination; determining the selection combination corresponding to the maximum value among multiple minimum distances as the final selection combination; and using the final selection combination to plan the path of the autonomous vehicle.
[0079] Optionally, multiple pre-selected vehicle longitudinal accelerations and multiple pre-selected vehicle lateral steering wheel rotation speeds are set, including: determining multiple corresponding vehicle lateral accelerations based on the multiple vehicle longitudinal accelerations, with a one-to-one correspondence between the vehicle longitudinal accelerations and vehicle lateral accelerations; and determining multiple vehicle lateral steering wheel rotation speeds based on the multiple vehicle lateral accelerations, with a one-to-one correspondence between the vehicle lateral accelerations and vehicle lateral steering wheel rotation speeds.
[0080] Optionally, the longitudinal accelerations of the multiple vehicles include at least one deceleration acceleration and at least one acceleration acceleration, and the lateral steering wheel rotations of the multiple vehicles include at least one negative steering wheel rotation and at least one positive steering wheel rotation.
[0081] This invention provides a processor for running a program, wherein the program executes a path planning method for an autonomous vehicle.
[0082] Specifically, the path planning methods for autonomous vehicles include:
[0083] Step S201: Determine whether there is a target obstacle in the surrounding environment of the autonomous vehicle. The target obstacle is an obstacle that poses a threat to the safety of the autonomous vehicle.
[0084] Step S202: In the presence of a target obstacle, predict the probability of the target obstacle colliding with the autonomous vehicle within a preset time period in the future, and determine whether to trigger the lightweight planning algorithm based on the probability of collision.
[0085] Step S203: If it is determined that the lightweight planning algorithm is triggered, the lightweight planning algorithm is used to plan the path for the autonomous vehicle to prevent the autonomous vehicle from colliding with the target obstacle.
[0086] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps:
[0087] Step S201: Determine whether there is a target obstacle in the surrounding environment of the autonomous vehicle. The target obstacle is an obstacle that poses a threat to the safety of the autonomous vehicle.
[0088] Step S202: In the presence of a target obstacle, predict the probability of the target obstacle colliding with the autonomous vehicle within a preset time period in the future, and determine whether to trigger the lightweight planning algorithm based on the probability of collision.
[0089] Step S203: If it is determined that the lightweight planning algorithm is triggered, the lightweight planning algorithm is used to plan the path for the autonomous vehicle to prevent the autonomous vehicle from colliding with the target obstacle.
[0090] The devices mentioned in this article can be servers, PCs, tablets, mobile phones, etc.
[0091] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having at least the following method steps:
[0092] Step S201: Determine whether there is a target obstacle in the surrounding environment of the autonomous vehicle. The target obstacle is an obstacle that poses a threat to the safety of the autonomous vehicle.
[0093] Step S202: In the presence of a target obstacle, predict the probability of the target obstacle colliding with the autonomous vehicle within a preset time period in the future, and determine whether to trigger the lightweight planning algorithm based on the probability of collision.
[0094] Step S203: If it is determined that the lightweight planning algorithm is triggered, the lightweight planning algorithm is used to plan the path for the autonomous vehicle to prevent the autonomous vehicle from colliding with the target obstacle.
[0095] This application also provides an autonomous vehicle, specifically, the path planning method for the autonomous vehicle includes:
[0096] Step S201: Determine whether there is a target obstacle in the surrounding environment of the autonomous vehicle. The target obstacle is an obstacle that poses a threat to the safety of the autonomous vehicle.
[0097] Step S202: In the presence of a target obstacle, predict the probability of the target obstacle colliding with the autonomous vehicle within a preset time period in the future, and determine whether to trigger the lightweight planning algorithm based on the probability of collision.
[0098] Step S203: If it is determined that the lightweight planning algorithm is triggered, the lightweight planning algorithm is used to plan the path for the autonomous vehicle to prevent the autonomous vehicle from colliding with the target obstacle.
[0099] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.
[0100] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can 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.) containing computer-usable program code.
[0101] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will 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 program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0102] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0103] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0104] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0105] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0106] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can 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), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
[0107] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0108] As can be seen from the above description, the embodiments of this application achieve the following technical effects:
[0109] 1) Applying the technical solution of this application, firstly, it is determined whether there is a target obstacle in the surrounding environment of the autonomous vehicle. The target obstacle is an obstacle that poses a threat to the safety of the autonomous vehicle. Then, if a target obstacle exists, the probability of the target obstacle colliding with the autonomous vehicle within a preset time period in the future is predicted, and a lightweight planning algorithm is determined based on the collision probability. Finally, if the lightweight planning algorithm is determined to be triggered, it is used to plan the path for the autonomous vehicle to prevent collisions with the target obstacle. This application achieves the goal of reducing computational load by determining whether to trigger the lightweight planning algorithm based on the probability of collision between the target obstacle and the autonomous vehicle, thus achieving the effect of rapid response of the autonomous vehicle. This solves the problem in the prior art where the long response delay of autonomous vehicles to obstacles leads to an increased probability of collision.
[0110] 2) Applying the technical solution of this application, a determining unit is used to determine whether a target obstacle exists in the surrounding environment of the autonomous vehicle. The target obstacle is an obstacle that poses a threat to the safety of the autonomous vehicle. A prediction determining unit is used to predict the probability of the target obstacle colliding with the autonomous vehicle within a preset time period in the presence of a target obstacle, and to determine whether to trigger a lightweight planning algorithm based on the probability of collision. A planning unit is used to perform path planning for the autonomous vehicle using a lightweight planning algorithm when it is determined that the lightweight planning algorithm will be triggered to prevent the autonomous vehicle from colliding with the target obstacle. This application achieves the goal of reducing computational load by determining whether to trigger a lightweight planning algorithm based on the probability of collision between the target obstacle and the autonomous vehicle, thus achieving the effect of rapid response of the autonomous vehicle in a short time. This solves the problem in the prior art where the long response delay of autonomous vehicles to obstacles leads to an increased probability of collision.
[0111] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.
Claims
1. A path planning method for an autonomous vehicle, characterized in that, include: Determine whether there is a target obstacle in the surrounding environment of the autonomous vehicle, wherein the target obstacle is an obstacle that poses a threat to the safety of the autonomous vehicle; In the presence of the target obstacle, predict the probability of the target obstacle colliding with the autonomous vehicle within a preset time period in the future, and determine whether to trigger the lightweight planning algorithm based on the probability of collision. If the lightweight planning algorithm is triggered, the lightweight planning algorithm is used to plan the path for the autonomous vehicle to prevent the autonomous vehicle from colliding with the target obstacle. Predicting the probability of the target obstacle colliding with the autonomous vehicle within a future preset time period includes: setting multiple pre-selected vehicle longitudinal accelerations and multiple pre-selected vehicle lateral steering wheel rotations; selecting one vehicle longitudinal acceleration and one vehicle lateral steering wheel rotation for any time point within the future preset time period to form multiple selection combinations; and determining the probability of the target obstacle colliding with the autonomous vehicle under any of the selection combinations. Determining whether to trigger the lightweight planning algorithm based on the probability of collision includes: determining whether to trigger the lightweight planning algorithm if the target obstacle collides with the autonomous vehicle in all of the selected combinations; and determining whether to not trigger the lightweight planning algorithm if the target obstacle does not collide with the autonomous vehicle in at least one of the selected combinations. When the lightweight planning algorithm is triggered, the lightweight planning algorithm is used to plan the path of the autonomous vehicle to prevent the autonomous vehicle from colliding with the target obstacles. This includes: expanding the selection combination to obtain an expanded selection combination; obtaining the minimum distance between the autonomous vehicle and multiple target obstacles under each expanded selection combination; determining the selection combination corresponding to the maximum value among the multiple minimum distances as the final selection combination; and using the final selection combination to plan the path of the autonomous vehicle.
2. The method according to claim 1, characterized in that, Set multiple pre-selected vehicle longitudinal accelerations and multiple pre-selected vehicle lateral steering wheel speeds, including: Multiple vehicle lateral accelerations are determined based on multiple vehicle longitudinal accelerations, and there is a one-to-one correspondence between the vehicle longitudinal accelerations and the vehicle lateral accelerations. Multiple vehicle lateral accelerations are determined based on multiple vehicle lateral accelerations, and the vehicle lateral accelerations and vehicle lateral steering wheel rotation speeds are in one-to-one correspondence.
3. The method according to claim 1, characterized in that, The longitudinal accelerations of the vehicles include at least one deceleration acceleration and at least one acceleration acceleration, and the lateral steering wheel rotations of the vehicles include at least one negative steering wheel rotation and at least one positive steering wheel rotation.
4. The method according to claim 3, characterized in that, The minimum deceleration is related to the vehicle's braking performance, while the maximum acceleration is related to the vehicle's acceleration performance.
5. The method according to claim 1, characterized in that, The method further includes: If it is determined that the lightweight planning algorithm will not be triggered, a conventional algorithm is used to plan the path for the autonomous vehicle. The conventional algorithm includes a perception module, a prediction module, a planning module, and a control module. If there are no target obstacles in the surrounding environment of the autonomous vehicle, the conventional algorithm is used to plan the path for the autonomous vehicle.
6. The method according to any one of claims 1 to 5, characterized in that, The target obstacle includes at least one of the following: Obstacles that are less than the minimum distance from the autonomous vehicle, the first obstacle directly in front of the autonomous vehicle, obstacles behind or to the side of the autonomous vehicle, obstacles crossing the road in front of the autonomous vehicle, pedestrians starting to run, and non-motorized vehicles suddenly starting to move.
7. A path planning device for an autonomous vehicle, characterized in that, include: A determining unit is used to determine whether there is a target obstacle in the surrounding environment of the autonomous vehicle, wherein the target obstacle is an obstacle that poses a threat to the safety of the autonomous vehicle; The prediction and determination unit is used to predict the probability of the target obstacle colliding with the autonomous vehicle within a preset time period in the presence of the target obstacle, and to determine whether to trigger the lightweight planning algorithm based on the probability of collision. The planning unit is used to perform path planning for the autonomous vehicle using the lightweight planning algorithm when it is determined that the lightweight planning algorithm is triggered, in order to prevent the autonomous vehicle from colliding with the target obstacle. The prediction and determination unit includes a prediction module, which predicts the probability of the target obstacle colliding with the autonomous vehicle within a preset time period in the future. The prediction module includes: a setting submodule, which sets multiple pre-selected vehicle longitudinal accelerations and multiple pre-selected vehicle lateral steering wheel speeds, and selects one vehicle longitudinal acceleration and one vehicle lateral steering wheel speed for any time point within the preset time period to form multiple selection combinations; and a determination submodule, which determines the probability of the target obstacle colliding with the autonomous vehicle under any of the selection combinations. The prediction and determination unit further includes: a third determination module, used to determine that the lightweight planning algorithm is triggered when the target obstacle collides with the autonomous vehicle under all the selection combinations; and a fourth determination module, used to determine that the lightweight planning algorithm is not triggered when the target obstacle does not collide with the autonomous vehicle under at least one of the selection combinations. The third determining module includes: an acquisition submodule, used to expand the selection combination to obtain an expanded selection combination, and to obtain the minimum distance between the autonomous vehicle and the multiple target obstacles under each expanded selection combination; a second determining submodule, used to determine the selection combination corresponding to the maximum value among the multiple minimum distances as the final selection combination; and a planning submodule, used to perform path planning for the autonomous vehicle using the final selection combination.
8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the path planning method for an autonomous vehicle as described in any one of claims 1 to 6.
9. An electronic device, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including a path planning method for performing an autonomous vehicle according to any one of claims 1 to 6.
10. An autonomous vehicle, characterized in that, include: A computing device that performs the path planning method for an autonomous vehicle as described in any one of claims 1 to 6.
Citation Information
Patent Citations
Lane changing control system and control method of vehicle
CN113525373A
System and Method for Predicting Road Collisions with a Host Vehicle
US20220161767A1
